dev.rateapi/mcp

Est-ce que dev.rateapi/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.rateapi/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 89 outils

• add_campaign_recipients≈ 269 tokens

  Add recipients (email + optional name) to a campaign. Up to 50 per request, 200 per campaign. Duplicate addresses are ignored.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Campaign id. Required.
  • recipients · array · requis
    Recipients to add.

  Exemple d'appel

  {"name": "add_campaign_recipients", "arguments": {"id": "texte", "recipients": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"added": 1, "total": 1}}

• analyze_rent_vs_buy≈ 1996 tokens

  Compare projected cost of renting vs buying a home over a holding period, anchored to LIVE market mortgage rates. Given home price, down payment, monthly rent, and a holding period, returns year-by-year cumulative cost of each path (rent vs PITI), equity built, net cost of owning after sale, and the breakeven year where buying becomes cheaper than renting. If no rate is supplied, the current best market rate for the state is used. Use for 'should I rent or buy?' questions.

  Paramètres, retour & exemple (18)

  Paramètres

  • rate · number · optionnel
    Annual interest rate, e.g. 6.5. If omitted, best market rate for the state is used.
  • state · string · optionnel
    2-letter US state code for the market-rate lookup. Default CA.
  • pmi_rate · number · optionnel
    Annual PMI as % of loan balance. Default 0.5, applied only when LTV > 80%.
  • home_price · number · requis
    Purchase price in dollars. Required.
  • monthly_hoa · number · optionnel
    HOA dues in dollars/month. Default 0.
  • term_months · number · optionnel
    Loan term in months. Default 360.
  • down_payment · number · optionnel
    Cash down payment in dollars. Default 20% of home_price.
  • monthly_rent · number · requis
    Current monthly rent in dollars. Required.
  • annual_insurance · number · optionnel
    Homeowners insurance in dollars/year. Default max(800, 0.35% of home price).
  • closing_cost_pct · number · optionnel
    Buying closing costs as % of home price. Default 3.0.
  • maintenance_rate · number · optionnel
    Annual maintenance as % of home value. Default 1.0.
  • rent_growth_rate · number · optionnel
    Annual rent growth as %. Default 3.0.
  • selling_cost_pct · number · optionnel
    Selling costs as % of sale price. Default 6.0.
  • marginal_tax_rate · number · optionnel
    Marginal tax rate as %, used to model mortgage-interest/property-tax deduction. Default 0 (no deduction).
  • property_tax_rate · number · optionnel
    Annual property tax as % of home value. Default 1.1.
  • holding_period_years · number · optionnel
    How many years you plan to own. Default 7.
  • home_appreciation_rate · number · optionnel
    Annual home appreciation as %. Default 3.0.
  • investment_return_rate · number · optionnel
    Opportunity cost return on invested savings as %. Default 5.0.

  Exemple d'appel

  {"name": "analyze_rent_vs_buy", "arguments": {"home_price": 1, "monthly_rent": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"buy": {}, "rent": {}, "breakeven": {}, "rate_used": 1, "confidence": "texte", "disclosures": [], "rate_source": "texte", "next_actions": [], "summary_note": "texte", "recommendation": "texte", "assumed_defaults": []}}

• assess_buy_timing≈ 1844 tokens

  Frame a buy/refi-now vs wait recommendation. Combines recent rate movement (direction + magnitude over 1w/2w/4w) with break-even sensitivity on the borrower's loan to return a forward 'lock now' vs 'wait' lean, the bps swing that would change the call, and the cost of waiting. Use for 'should I lock now or wait for rates to drop?' questions. Distinct from get_rate_delta (raw historical deltas only) — this adds a forward recommendation. Not a rate forecast.

  Paramètres, retour & exemple (8)

  Paramètres

  • since · string · optionnel · 1w | 2w | 4w
    Movement window (default 4w)
  • state · string · requis
    2-letter US state code
  • loan_amount · number · requis
    Loan amount in dollars — drives break-even sensitivity
  • term_months · number · optionnel
    Loan term in months (default 360 for mortgage)
  • current_rate · number · optionnel
    Borrower's existing or quoted rate %, enables refi-now framing
  • product_type · string · requis · mortgage | mortgage_arm | auto_loan | rv | boat | motorcycle | powersports | heloc
    Loan product
  • closing_costs · number · optionnel
    Closing/refi costs in dollars (default 0)
  • rate_shift_bps · number · optionnel
    Hypothetical bps move if waiting; default derived from observed movement

  Exemple d'appel

  {"name": "assess_buy_timing", "arguments": {"state": "texte", "loan_amount": 1, "product_type": "mortgage"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"now": {}, "note": "texte", "state": "texte", "window": "texte", "movement": {}, "rationale": "texte", "break_even": {}, "confidence": "texte", "disclosures": [], "next_actions": [], "product_type": "texte", "wait_scenario": {}}}

• assess_rate_lock≈ 1953 tokens

  Lock-window-aware lock-vs-float-down recommendation for a deal already in the pipeline. Given a known lock-expiration date, the currently locked rate, and the float-down cost, returns a defensible hold-lock vs exercise-float-down call a loan officer can document — combining recent market movement (1w/2w/4w) with payment and break-even math on this loan. Builds on the same recent-movement signal as assess_buy_timing but framed around the lock window/expiration. Not a rate forecast.

  Paramètres, retour & exemple (10)

  Paramètres

  • since · string · optionnel · 1w | 2w | 4w
    movement window; default 4w
  • state · string · requis
    2-letter state code
  • loan_amount · number · requis
  • locked_rate · number · requis
    % already locked
  • term_months · number · optionnel
    default 360
  • product_type · string · requis · mortgage | mortgage_arm | auto_loan | rv | boat | motorcycle | powersports | heloc
  • float_down_bps · number · optionnel
    optional improvement in bps if float_down_rate omitted
  • float_down_cost · number · optionnel
    $ to exercise float-down; default 0
  • float_down_rate · number · optionnel
    optional explicit floated rate %
  • lock_expiration_date · string · requis
    ISO date YYYY-MM-DD

  Exemple d'appel

  {"name": "assess_rate_lock", "arguments": {"state": "texte", "loan_amount": 1, "locked_rate": 1, "product_type": "mortgage", "lock_expiration_date": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"lock": {}, "note": "texte", "state": "texte", "window": "texte", "movement": {}, "rationale": "texte", "confidence": "texte", "float_down": {}, "market_now": {}, "disclosures": [], "next_actions": [], "product_type": "texte"}}

• batch_decisions≈ 866 tokens

  Score an array of inline financing scenarios in one stateless call; returns ranked decisions and top offers per item — no persisted cohorts, no per-borrower HTTP loops.

  Paramètres, retour & exemple (4)

  Paramètres

  • state · string · optionnel
    Optional 2-letter default state applied to scenarios lacking one
  • scenarios · array · requis
    Inline scenarios to score in one stateless call (no persisted cohorts).
  • credit_score · number · optionnel
    Optional default credit score applied to scenarios lacking one
  • max_providers · number · optionnel
    Top-N offers returned per scenario (default 3)

  Exemple d'appel

  {"name": "batch_decisions", "arguments": {"scenarios": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "totals": {}, "results": []}}

• build_amortization_schedule≈ 1680 tokens

  Build a year-by-year amortization / payoff schedule for a loan: total lifetime interest, principal/interest split per period, and a what-if extra-payment accelerator showing months saved and interest saved. Resolves the market rate from real credit-union offers when no rate is provided.

  Paramètres, retour & exemple (9)

  Paramètres

  • rate · number · optionnel
    Annual interest rate as a percent (e.g. 6.5). If omitted, the market rate is resolved from real credit-union offers via the decision engine.
  • state · string · optionnel
    2-letter US state code; required only when rate is omitted (for market-rate lookup).
  • loan_amount · number · requis
    Loan principal in dollars (required, > 0).
  • term_months · number · requis
    Loan term in months, e.g. 360 or 180 (required).
  • credit_score · number · optionnel
    Optional borrower credit score used to qualify the market offer.
  • product_type · string · optionnel · mortgage | auto_loan | rv | boat | motorcycle | powersports | heloc | personal_loan
    Loan product; required only when rate is omitted. Default mortgage.
  • schedule_granularity · string · optionnel · year | month
    Schedule row granularity. Default year.
  • extra_monthly_payment · number · optionnel
    Optional extra principal paid each month. Drives the payoff-acceleration analysis (months saved, interest saved).
  • extra_one_time_payment · number · optionnel
    Optional one-time extra principal payment.

  Exemple d'appel

  {"name": "build_amortization_schedule", "arguments": {"loan_amount": 1, "term_months": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"rate": 1, "reason": "texte", "baseline": {}, "schedule": [], "with_extra": {}, "disclosures": [], "loan_amount": 1, "rate_source": "texte", "term_months": 1, "next_actions": [], "market_lender": "texte", "monthly_payment": 1}}

• check_advice_guardrails≈ 784 tokens

  Run compliance/suitability guardrails over a financing scenario and an optional recommendation. Returns flags (red/yellow with code + message) for things like DTI strain, long auto terms with negative-equity risk, possible balloon payments, and stale market data, plus generic disclaimers and an overall verdict (ok/caution/stop). Use this before presenting a rate recommendation to a borrower.

  Paramètres, retour & exemple (2)

  Paramètres

  • scenario · object · requis
    The borrower scenario.
  • recommendation · object · optionnel
    Optional recommended offer to evaluate.

  Exemple d'appel

  {"name": "check_advice_guardrails", "arguments": {"scenario": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"flags": [], "overall": "texte", "disclaimers": []}}

• check_competitive_position≈ 884 tokens

  LENDER-side 'is my offer competitive' check — input your OWN published rate for a state+product, get the market percentile, bps vs the state median, and a leading/competitive/overpriced verdict. This is for a loan officer or credit union benchmarking their published pricing against the live market distribution. Do NOT use this for a consumer's quote: if the user is a BORROWER asking whether a rate they were offered is fair, use rate_sanity_check instead.

  Paramètres, retour & exemple (4)

  Paramètres

  • apr · number · optionnel
    The lender's published APR. Optional — falls back to rate.
  • rate · number · requis
    The lender's OWN published note rate as a percentage (e.g. 6.49). Required.
  • state · string · requis
    US state code (2-letter, e.g. CA, TX). Required.
  • product · string · requis · 30yr_fixed | 15yr_fixed
    Mortgage product the lender publishes. Required.

  Exemple d'appel

  {"name": "check_competitive_position", "arguments": {"rate": 1, "state": "texte", "product": "30yr_fixed"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "state": "texte", "market": {}, "product": "texte", "verdict": "texte", "percentile": 1, "your_offer": {}, "bps_vs_median": 1}}

• check_membership_eligibility≈ 5894 tokens

  `relative_memberships` carries confirmed current/deceased relative membership scoped to one exact target credit union; one institution is never reused for another. Check whether a user can JOIN specific credit unions (field-of-membership eligibility). Batch-friendly: pass 1-50 credit_union_ids (from get_financing_decision offers, list_credit_unions, or get_credit_union) plus whatever is known about the user (home, worksite, and payroll geography are independent facts; employer, occupation, military_status, school plus school_relationship, and worship are also supported). City facts require their same-role state or a recognized same-role ZIP that uniquely identifies one state, and are accepted only when the closed Census gazetteer resolves them. Returns one row for every requested credit union. Positive outcomes include open_to_anyone, likely_eligible, eligible_via_employer, and eligible_via_military. A school name alone is not a positive signal: school_relationship is required to affirm a typed student, alumni, or school-employee path. Only a graph carrying exact active-publication lineage governs the top compatibility verdict; a publication-less shadow graph remains diagnostic and cannot replace the flat result. A non-match is returned as unknown, with `unknown_reason: fom_completeness_unaffirmed` when the published field-of-membership corpus is not attested complete. The legacy `geo_mismatch` enum value is reserved for wire compatibility and is not emitted by this MCP boundary without a future typed closed-world attestation. Verdicts are guidance based on each credit union's published membership criteria; the final membership determination is always the institution's. Non-matches carry `missing_facts` for the named institutions: the exact question to ask next, the `fact_field` an answer populates, and the institution's own words. A check that returns unknown for all of them and a question for each is a SUCCESSFUL call, not a failure — ask the questions, merge the answers into the same request, and call again. Home geography accepts both the original `zip`/`state`/`county` names and the `home_zip`/`home_state`/`home_county` aliases emitted by `missing_facts`; do not send conflicting values in both forms. Fact fields, in full — supply every one you know: `home_zip`, `home_state`, `home_county`, `home_city`; `work_zip`, `work_state`, `work_county`, `work_city`; `payroll_zip`, `payroll_state`, `payroll_county`, `payroll_city` (payroll can differ from the worksite and is a separate door); `property_zip`, `property_state`, `property_county`, `property_city` (where they OWN property — never inferred from where they live, and an absentee owner qualifies); `facility_zip`, `facility_state`, `facility_county`, `facility_city` (where their business maintains a location); `occupation`; `employer`; `school` plus `school_relationship` (student/alumni/employee — a school name without a relationship affirms nothing); `military_status` plus `military_service_state` (state National Guard doors need the state); `worship`; `family_relation` plus `relative_employers`, `relative_schools`, `relative_associations` (a great many people qualify only through a relative — ask); `applicant_kind` (person/trust/organization/partnership/corporation — some charters admit entities, and a person is never rejected by an entity-only door, only left unknown); and `asserted_org_qualifiers` (narrowings the person asserts about themselves, e.g. "assigned as a recruiter in Arkansas").

  Paramètres, retour & exemple (45)

  Paramètres

  • zip · string · optionnel
    User's US 5-digit ZIP or ZIP+4. Resolves to a county server-side; when state is supplied, the ZIP crosswalk must agree with it.
  • state · string · optionnel
    User's valid 50-state/DC code for geographic field-of-membership matching. Lowercase is accepted and normalized.
  • county · string · optionnel
    User's home county for residence matching. Original name; home_county is an equivalent merge-and-retry alias.
  • school · string · optionnel
    User's school/college/university. Supply school_relationship too; the school name alone does not affirm eligibility.
  • worship · string · optionnel
    User's place of worship, matched against worship-org affinity lists (yields likely_eligible).
  • employer · string · optionnel
    User's employer, matched against credit union employer/SEG membership lists.
  • home_zip · string · optionnel
    Alias for zip, accepted so missing_facts can be merged into this same tool request. It must agree with state/home_state when either is supplied; conflicting duplicate forms are rejected.
  • work_zip · string · optionnel
    User's US 5-digit work ZIP or ZIP+4. Resolves to a work county server-side; when work_state is supplied, the crosswalk must agree with it.
  • home_city · string · optionnel
    User's Census-recognized home city. Requires state or a recognized zip that uniquely identifies one state; unresolved labels are rejected rather than guessed.
  • work_city · string · optionnel
    Census-recognized city where the user works. Requires work_state or a recognized work_zip that uniquely identifies one state.
  • home_state · string · optionnel
    Alias for state, accepted so missing_facts can be merged into this same tool request. Conflicting duplicate forms are rejected.
  • occupation · string · optionnel
    User's occupation, matched against trade/industry/profession (TIP) charters.
  • work_state · string · optionnel
    Valid 50-state/DC code where the user works, for work-area membership matching. Lowercase is accepted and normalized.
  • home_county · string · optionnel
    Alias for county, accepted so missing_facts can be merged into this same tool request. Conflicting duplicate forms are rejected.
  • payroll_zip · string · optionnel
    ZIP from which the user's employer issues payroll. This is distinct from the worksite ZIP.
  • work_county · string · optionnel
    County where the user works, for work-area membership matching.
  • facility_zip · string · optionnel
    ZIP where the user's business maintains a location. Distinct from the worksite ZIP.
  • payroll_city · string · optionnel
    Census-recognized payroll city. Requires payroll_state or a recognized payroll_zip that uniquely identifies one state.
  • property_zip · string · optionnel
    ZIP where the user OWNS REAL PROPERTY. A door of its own — never inferred from where they live, and an absentee owner qualifies.
  • facility_city · string · optionnel
    Census-recognized city where the user's business maintains a location. Requires facility_state or a recognized facility_zip that uniquely identifies one state.
  • payroll_state · string · optionnel
    Valid state code from which the user's employer issues payroll. This is distinct from work_state.
  • property_city · string · optionnel
    Census-recognized city where the user owns real property. Requires property_state or a recognized property_zip that uniquely identifies one state.
  • applicant_kind · string · optionnel · person | trust | organization | partnership | corporation | other_legal_entity
    What the applicant IS. Some charters admit entities as well as people. Absent means a natural person; a person is never rejected by an entity-only door, only left unknown.
  • facility_state · string · optionnel
    State where the user's business maintains a location.
  • payroll_county · string · optionnel
    County from which the user's employer issues payroll. This is distinct from work_county.
  • property_state · string · optionnel
    State where the user owns real property. Distinct from home_state.
  • school_org_ids · array · optionnel
    Canonical school ids selected through resolve_eligibility_entities; never populate these from prose extraction.
  • facility_county · string · optionnel
    County where the user's business maintains a location.
  • family_relation · string · optionnel
    How the user relates to a RELATIVE whose own affiliations may qualify them (e.g. 'spouse', 'child', 'immediate family'). Required alongside relative_employers/relative_schools/relative_associations — without it there is nobody for those organizations to belong to. Many SEG lists read 'Employees of the following companies AND THEIR IMMEDIATE FAMILIES are eligible'; this is how that door is answered.
  • military_status · string · optionnel · active_duty | veteran | reservist | dod_civilian | military_family
    User's military affiliation, matched against military field-of-membership (yields eligible_via_military).
  • property_county · string · optionnel
    County where the user owns real property. Distinct from home_county.
  • worship_org_ids · array · optionnel
    Canonical worship-organization ids selected through resolve_eligibility_entities.
  • credit_union_ids · array · requis
    Credit union ids to check (1-50), e.g. from get_financing_decision offers or list_credit_unions. Required.
  • employer_org_ids · array · optionnel
    Canonical employer ids selected through resolve_eligibility_entities. The API revalidates entity type and active-publication authority before use.
  • relative_schools · array · optionnel
    Schools the RELATIVE named by family_relation attends. Optional; same unknown-by-default contract as relative_employers.
  • relative_employers · array · optionnel
    Employers of the RELATIVE named by family_relation (not the user's own employer). Optional; omitting it leaves compound family doors undecided (unknown), never negative.
  • association_org_ids · array · optionnel
    Canonical association ids selected through resolve_eligibility_entities; each is type- and publication-revalidated.
  • school_relationship · string · optionnel · student | alumni | employee
    How the user relates to the named school. Required with school to affirm a typed student, alumni, or school-employee path.
  • relative_memberships · array · optionnel
    Confirmed relative memberships scoped to one exact credit union. A membership at one institution is never reused for another; omit unconfirmed memberships and the corresponding family door remains unknown.
  • relative_associations · array · optionnel
    Associations the RELATIVE named by family_relation belongs to. Optional; same unknown-by-default contract as relative_employers.
  • military_service_state · string · optionnel
    The state the user serves, or served, in. State National Guard doors ("Oklahoma National Guard") need this; without it such a door reads unknown.
  • asserted_org_qualifiers · array · optionnel
    Narrowings the user asserts about themselves, quoted back from a missing_facts question (e.g. "assigned as Recruiters or ROTC Instructors within the State of Arkansas"). Absence caps a narrowed door rather than closing it.
  • relative_school_org_ids · array · optionnel
    Canonical school ids for the relative named by family_relation, never for the applicant.
  • relative_employer_org_ids · array · optionnel
    Canonical employer ids for the relative named by family_relation, never for the applicant.
  • relative_association_org_ids · array · optionnel
    Canonical association ids for the relative named by family_relation, never for the applicant.

  Exemple d'appel

  {"name": "check_membership_eligibility", "arguments": {"credit_union_ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "engine": "texte", "checked": 1, "summary": "texte", "verdicts": []}}

• compare_personal_access_catalogs≈ 6449 tokens

  Compare baseline and candidate confirmed person facts across the same 1-19 explicit products. Both catalogs use one pinned immutable eligibility graph snapshot; rate rows retain independent evidence and as_of. Returns access, membership-path, and like-for-like published-price basis-point deltas: APY for deposits, APR for lending when both sides publish APR, otherwise nominal rate only when both sides publish nominal rate. It never mixes APR and nominal rate. Never describe missing access as denial or infer savings, underwriting, approval, or final terms.

  Paramètres, retour & exemple (5)

  Paramètres

  • products · array · requis
  • total_limit · integer · optionnel
  • baseline_person · object · requis
    Explicit caller-supplied person facts. Unknown facts stay absent; do not infer them.
  • candidate_person · object · requis
    Explicit caller-supplied person facts. Unknown facts stay absent; do not infer them.
  • limit_per_product · integer · optionnel

  Exemple d'appel

  {"name": "compare_personal_access_catalogs", "arguments": {"products": [], "baseline_person": {}, "candidate_person": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"deltas": {}, "baseline": {}, "snapshot": {}, "candidate": {}, "semantics": "texte", "disclosure": "texte", "comparison_version": "texte"}}

• compare_products≈ 925 tokens

  Compare the best real rates across MULTIPLE lending products in a single call — e.g. show a buyer mortgage vs HELOC, or new vs used auto. Runs the decision engine for each product and returns a ranked, true-cost (APR + fees) table. Use this instead of calling get_financing_decision repeatedly. Each product returns its top offer with rate, APR, and monthly payment.

  Paramètres, retour & exemple (6)

  Paramètres

  • state · string · requis
    US state code, e.g. "CA"
  • amount · number · requis
    Loan/credit amount in dollars
  • intent · string · optionnel
    purchase | refinance | cash_out | balance_transfer | new_credit
  • term_months · number · optionnel
    Optional loan term in months
  • credit_score · number · optionnel
    Optional borrower credit score
  • product_types · array · requis
    Products to compare, e.g. ["mortgage","heloc"]. Any of: mortgage, mortgage_arm, auto, rv, boat, motorcycle, powersports, heloc, personal_loan, credit_card, student_loan. "mortgage" is fixed-rate and "mortgage_arm" is adjustable — comparing them side by side is meaningful, but they are never blended into one ranking. Boats/RVs/motorcycles/powersports are first-class product types; auto means cars.

  Exemple d'appel

  {"name": "compare_products", "arguments": {"state": "texte", "amount": 1, "product_types": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "state": "texte", "amount": 1, "intent": "texte", "products": [], "best_overall": "texte"}}

• compare_reachable_offers≈ 6150 tokens

  Compare one baseline person-fact panel with one candidate panel against the same active eligibility snapshot and exact product request. Use this for explicit what-if questions such as adding a confirmed employer or association. Newly reachable means current positive evidence now proves a path; no_longer_reachable or absence never proves ineligibility. Supply only facts the person confirmed, preferably canonical *_org_ids from resolve_eligibility_entities. Person facts are forwarded transiently and are not stored by this tool.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Visible items per bucket and delta list.
  • product · object · requis
    Exact product request used for both eligibility-backed rate evaluation and ranking.
  • baseline_person · object · requis
    Confirmed facts before the proposed change.
  • candidate_person · object · requis
    Confirmed facts after the proposed change.

  Exemple d'appel

  {"name": "compare_reachable_offers", "arguments": {"product": {}, "baseline_person": {}, "candidate_person": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"deltas": {}, "product": {}, "baseline": {}, "snapshot": {}, "candidate": {}, "semantics": "texte", "disclosure": "texte"}}

• compare_total_cost≈ 1542 tokens

  Apples-to-apples multi-lender ranking by TOTAL cost of a loan (upfront origination/lender fees + lifetime interest over the holding period), not just the headline rate. Re-ranks real credit union offers and flags when the lowest-rate lender is not the cheapest overall.

  Paramètres, retour & exemple (10)

  Paramètres

  • fees · object · optionnel
  • state · string · requis
    2-letter US state
  • amount · number · requis
    Loan principal
  • intent · string · optionnel · purchase | refinance
    default purchase
  • max_lenders · number · optionnel
    cap on ranked rows (default 10, max 25)
  • term_months · number · optionnel
  • credit_score · number · optionnel
  • product_type · string · requis · mortgage | auto_loan | rv | boat | motorcycle | powersports | personal_loan | heloc
    Loan product to rank
  • down_payment_percent · number · optionnel
  • holding_period_months · number · optionnel
    Horizon for total-cost; defaults to term_months

  Exemple d'appel

  {"name": "compare_total_cost", "arguments": {"state": "texte", "amount": 1, "product_type": "mortgage"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "state": "texte", "amount": 1, "intent": "texte", "ranked": [], "cheapest": {}, "reranked": true, "ranked_by": "texte", "disclosures": [], "rate_leader": {}, "term_months": 1, "next_actions": []}}

• create_competitor_monitor≈ 1278 tokens

  Subscribe a monitor to a SPECIFIC named credit union's published rate and alert via webhook when that CU changes its rate (vs the aggregate market-best decision). Returns the monitor with a webhook_signing_secret (shown once) and a baseline snapshot of the CU's current rate.

  Paramètres, retour & exemple (10)

  Paramètres

  • name · string · requis
    Descriptive monitor name. Required.
  • state · string · optionnel
    2-letter state for the CU published rate.
  • audience · string · optionnel · business | consumer
    Scope offers by WHO they are for: 'business' returns business-audience products (DSCR mortgages, commercial vehicle loans, SBA); 'consumer' excludes them. Omit for both.
  • occupancy · string · optionnel · primary | secondary | investment
    MORTGAGE/HELOC: property occupancy. 'investment' returns investor / non-owner-occupied / DSCR pricing; 'secondary' second-home pricing. Omit for standard primary-residence offers.
  • conditions · object · optionnel
    Alert conditions on the named CU rate. Default: any change.
  • webhook_url · string · requis
    HTTPS webhook. Required.
  • loan_program · string · optionnel
    e.g. '30-year-fixed'.
  • product_type · string · optionnel · mortgage | auto_loan | rv | boat | motorcycle | powersports | heloc | personal_loan
    Default mortgage.
  • cooldown_hours · number · optionnel
    1-168, default 24.
  • target_credit_union · object · requis
    The specific credit union whose published rate to watch. Required.

  Exemple d'appel

  {"name": "create_competitor_monitor", "arguments": {"name": "texte", "webhook_url": "texte", "target_credit_union": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"monitor": {}, "summary": "texte", "important": "texte", "disclosures": [], "next_actions": [], "webhook_signing_secret": "texte"}}

• create_email_campaign≈ 1103 tokens

  Create a branded rate-email campaign: on a cadence, email the campaign's recipient list the latest rates for one or more states (or a named region preset) under the org's branding, with ONE OR MORE products (1-5, no duplicates). Each product is one of: {category:'mortgage', subtype:'30-year-fixed'|'15-year-fixed'}, {category:'auto', condition:'new'|'used'|'any', term_months?:36|48|60|72|84} (auto = cars only), or {category:'rv'|'boat'|'motorcycle', condition:'new'|'used'|'any'}. Defaults to a single 30-year-fixed mortgage if products is omitted. Created 'paused'; add recipients, then activate via update_email_campaign (activation requires branding display_name + business_address). Requires a Pro plan. Provide exactly one of state_code, state_codes, or region.

  Paramètres, retour & exemple (7)

  Paramètres

  • name · string · requis
    Campaign label. Required.
  • region · string · optionnel · east_coast | west_coast | midwest | south | northeast | southeast | southwest | mountain_west
    Named region preset (e.g. east_coast); expands server-side to its member states.
  • cadence · string · optionnel · daily | weekly | monthly
    Send cadence (default weekly).
  • products · array · optionnel
    1-5 products to feature (no duplicates). Each is {category:'mortgage', subtype:'30-year-fixed'|'15-year-fixed'}, {category:'auto', condition:'new'|'used'|'any', term_months?:36|48|60|72|84}, or {category:'rv'|'boat'|'motorcycle', condition:'new'|'used'|'any'}.
  • state_code · string · optionnel
    Legacy single 2-letter US state code (e.g. CA). Prefer state_codes or region for multi-state coverage.
  • state_codes · array · optionnel
    2-letter US state codes (up to 25) — best rates are ranked ACROSS all of them, not per state.
  • intro_text_override · string · optionnel
    Per-campaign intro; falls back to branding intro_text.

  Exemple d'appel

  {"name": "create_email_campaign", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "amount": 1, "status": "texte", "cadence": "texte", "products": [], "created_at": 1, "state_code": "texte", "updated_at": 1, "last_run_at": 1, "state_codes": [], "term_months": 1}}

• create_monitor≈ 1074 tokens

  Create a new decision monitor that watches for rate changes and sends webhook notifications when conditions are met. Returns the monitor with a webhook_signing_secret for verifying webhook payloads.

  Paramètres, retour & exemple (7)

  Paramètres

  • name · string · requis
    A descriptive name for the monitor. Required.
  • conditions · array · requis
    Array of conditions that must be met to trigger the monitor. Required.
  • webhook_url · string · requis
    The URL to send webhook notifications to. Required.
  • cooldown_hours · number · optionnel
    Minimum hours between webhook triggers (1-168). Defaults to 24.
  • decision_context · object · requis
    The context for evaluating rate changes. Required.
  • subscribed_states · array · optionnel
    Optional array of state codes to monitor. If not provided, monitors all states.
  • subscribed_product_types · array · optionnel
    Optional array of product types to monitor (e.g., ["30yr_fixed", "15yr_fixed"]).

  Exemple d'appel

  {"name": "create_monitor", "arguments": {"name": "texte", "conditions": [], "webhook_url": "texte", "decision_context": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"monitor": {}, "summary": "texte", "important": "texte"}}

• delete_cohort≈ 158 tokens

  Permanently delete a saved cohort by id. This action cannot be undone.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Cohort id. Required.

  Exemple d'appel

  {"name": "delete_cohort", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"success": true}}

• delete_digest≈ 156 tokens

  Delete a scheduled digest by id. Stops the recurring email.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The digest id to delete.

  Exemple d'appel

  {"name": "delete_digest", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"success": true}}

• delete_email_campaign≈ 175 tokens

  Delete a branded rate-email campaign and its recipients. This cannot be undone.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Campaign id. Required.

  Exemple d'appel

  {"name": "delete_email_campaign", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"success": true}}

• delete_monitor≈ 247 tokens

  Permanently delete a monitor. This action cannot be undone.

  Paramètres, retour & exemple (1)

  Paramètres

  • monitor_id · string · requis
    The unique identifier of the monitor to delete. Required.

  Exemple d'appel

  {"name": "delete_monitor", "arguments": {"monitor_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "deleted": true, "summary": "texte", "monitor_id": "texte"}}

• delete_scenario≈ 147 tokens

  Delete a saved scenario by id.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Scenario id

  Exemple d'appel

  {"name": "delete_scenario", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"success": true}}

• deliver_test_webhook≈ 888 tokens

  Send a test webhook for a monitor using a simulated rate change. This actually delivers an HTTP request to the monitor's configured webhook URL. IMPORTANT: a test delivery is NOT signed with the monitor's signing secret — only a hash of that secret is stored, so test deliveries use a placeholder and will FAIL signature verification. Use this to test payload handling, not signature verification. Only use when the user explicitly requests a test webhook delivery.

  Paramètres, retour & exemple (2)

  Paramètres

  • monitor_id · string · requis
    The unique identifier of the monitor to test. Required.
  • rate_change · object · requis
    The simulated rate change event. Required.

  Exemple d'appel

  {"name": "deliver_test_webhook", "arguments": {"monitor_id": "texte", "rate_change": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "summary": "texte", "evaluation": {}, "rate_change": {}, "would_trigger": true, "webhook_delivery": {}}}

• estimate_affordability≈ 1363 tokens

  Borrower-facing home affordability estimate: given gross income, existing monthly debts, down payment, and front-end/back-end DTI caps, compute the max monthly payment, max loan amount, and max home price. Surfaces the max_loan annuity engine. If no rate is supplied, the current best market rate for the state is used.

  Paramètres, retour & exemple (9)

  Paramètres

  • rate · number · optionnel
    Optional annual interest rate, e.g. 6.5. If omitted, best market rate is used.
  • state · string · optionnel
    US state code for the market-rate lookup. Default CA.
  • term_months · number · optionnel
    Loan term in months. Default 360.
  • back_end_dti · number · optionnel
    Total-debt DTI cap as a decimal. Default 0.36.
  • down_payment · number · optionnel
    Cash down payment in dollars. Default 0.
  • product_type · string · optionnel
    Product for the market-rate lookup. Default mortgage.
  • front_end_dti · number · optionnel
    Housing-payment DTI cap as a decimal. Default 0.28.
  • income_annual · number · requis
    Gross annual income in dollars
  • monthly_debts · number · optionnel
    Existing recurring monthly debt payments. Default 0.

  Exemple d'appel

  {"name": "estimate_affordability", "arguments": {"income_annual": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "reason": "texte", "rate_used": "texte", "affordable": true, "disclosures": [], "rate_source": "texte", "down_payment": "texte", "next_actions": [], "max_home_price": "texte", "max_loan_amount": "texte", "assumed_defaults": {}, "max_payment_value": 1}}

• estimate_monthly_cost≈ 1588 tokens

  Total monthly housing cost (PITI): principal+interest plus property tax, homeowners insurance, PMI, and HOA, so affordability reflects real monthly outlay. If no rate is supplied, the current best market rate for the state is used.

  Paramètres, retour & exemple (11)

  Paramètres

  • rate · number · optionnel
    Annual interest rate, e.g. 6.5. If omitted, best market rate for the state is used.
  • state · string · optionnel
    2-letter US state code for the market-rate lookup. Default CA.
  • pmi_rate · number · optionnel
    Annual PMI as % of loan balance. Default 0.5, applied only when LTV > 80%.
  • home_price · number · optionnel
    Purchase price in dollars. Required unless loan_amount is given.
  • loan_amount · number · optionnel
    Optional explicit loan amount; overrides home_price - down_payment.
  • monthly_hoa · number · optionnel
    HOA dues in dollars/month. Default 0.
  • term_months · number · optionnel
    Loan term in months. Default 360.
  • credit_score · number · optionnel
    Optional borrower credit score, used for the market-rate lookup.
  • down_payment · number · optionnel
    Cash down payment in dollars. Default 0. loan_amount = home_price - down_payment.
  • annual_insurance · number · optionnel
    Homeowners insurance in dollars/year. Default max(800, 0.35% of home price).
  • property_tax_rate · number · optionnel
    Annual property tax as % of home value. Default 1.1.

  Exemple d'appel

  {"name": "estimate_monthly_cost", "arguments": {"rate": 1, "state": "texte", "pmi_rate": 1, "home_price": 1, "loan_amount": 1, "monthly_hoa": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ltv": "texte", "breakdown": {}, "rate_used": "texte", "home_price": "texte", "disclosures": [], "loan_amount": "texte", "monthly_hoa": "texte", "monthly_pmi": "texte", "pmi_applies": true, "rate_source": "texte", "annual_total": "texte", "down_payment": "texte"}}

• evaluate_eligibility_cohort≈ 3633 tokens

  Evaluate a caller-supplied panel of 1-10 named fact profiles for one exact product against one serving snapshot, deduplicating reachable institutions and exact offers. This is descriptive only for the supplied panel: never call it a population estimate, conversion rate, approval forecast, or negative eligibility result. Use neutral profile labels instead of names, emails, account numbers, or other direct identifiers. Profiles are forwarded transiently and are not stored by this tool; unknown remains unknown.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum aggregate institutions and deduplicated offers returned.
  • product · object · requis
    Exact product request used for both eligibility-backed rate evaluation and ranking.
  • profiles · array · requis
    Caller-supplied named panel. Names must be unique within this request.

  Exemple d'appel

  {"name": "evaluate_eligibility_cohort", "arguments": {"product": {}, "profiles": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"product": {}, "profiles": [], "snapshot": {}, "aggregate": {}, "semantics": "texte", "disclosure": "texte", "methodology": {}}}

• explain_ranking≈ 801 tokens

  Explain WHY each top lender ranked where it did for a financing decision. Takes a full decision scenario (same shape as get_financing_decision) and returns a structured per-offer cost breakdown (rate, points, fees, lifetime interest), scoring signals, how much each offer beats the next by, and a plain-language summary of the ranking weights. Use this when a user asks why one lender beat another.

  Paramètres, retour & exemple (7)

  Paramètres

  • state · string · requis
    US state code (2-letter). Required.
  • amount · number · requis
    Loan amount in dollars. Required.
  • intent · string · requis · purchase | refinance | cash_out | balance_transfer | new_credit
    The loan intent.
  • term_months · number · optionnel
    Loan term in months.
  • credit_score · number · optionnel
    Borrower's credit score (300-850).
  • product_type · string · optionnel · mortgage | mortgage_arm | auto_loan | rv | boat | motorcycle | powersports | personal_loan
    Type of financing product.
  • max_providers · number · optionnel
    Maximum number of lenders to explain (1-5). Defaults to 5.

  Exemple d'appel

  {"name": "explain_ranking", "arguments": {"state": "texte", "amount": 1, "intent": "purchase"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"offers": [], "summary": "texte", "request_id": "texte", "product_type": "texte"}}

• extract_eligibility_facts≈ 1479 tokens

  Turn a person's own words about themselves into the structured facts the eligibility tools accept. Pass their sentence verbatim ("I'm a nurse at a Tulsa hospital, I live in Broken Arrow, my late father was a TTCU member") and this returns each fact it could read, with the exact words it read it from, a confidence, and a needs_confirmation flag. THIS DOES NOT DECIDE ELIGIBILITY and never returns a credit union: it only fills in fields. Show the extracted facts to the user and get confirmation on every fact with needs_confirmation=true (family relationships, relatives' employers and associations, applicant kind, and asserted qualifiers are always flagged, because a wrong reading of those changes the answer). Then pass `person_search_body` — plus whatever the user confirmed — to find_eligible_credit_unions, which is what actually decides. If extraction is unavailable you get facts: [] and no eligibility signal at all; ask the user for fields directly instead. `confidence` is the extraction model's own uncalibrated self-report and gates only autofill — quote `evidence.quote` to the user, not the number. This call costs 3 API units.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    The person's own words, up to 2000 characters. Do not paraphrase or pre-structure it — the extractor needs the original sentence to anchor evidence spans.
  • known_facts · object · optionnel
    Optional. Fields you already know, in PersonSearch shape. These are echoed as source="supplied" and never overwritten.

  Exemple d'appel

  {"name": "extract_eligibility_facts", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "facts": [], "model": "texte", "sandbox": true, "billed_units": 1, "unparsed_spans": [], "extractor_version": "texte", "person_search_body": {}, "extraction_available": true, "confirmation_required": true, "confidence_is_model_self_reported": true}}

• find_credit_unions_near_zip≈ 850 tokens

  Use when someone asks for "credit unions near me," the closest credit union, local credit-union branches, or nearby alternatives to a bank. Given a 5-digit ZIP, returns credit unions ordered by the estimated straight-line distance to each institution's closest NCUA-reported branch. Includes approximate miles, branch address, and profile identifiers for checking rates, services, and membership. Distances use ZIP centers and are not driving distance.

  Paramètres, retour & exemple (2)

  Paramètres

  • zip · string · requis
    Five-digit US ZIP code used as the center of the nearest-branch search.
  • max_results · number · optionnel
    Maximum credit unions to return (1-25, default 10).

  Exemple d'appel

  {"name": "find_credit_unions_near_zip", "arguments": {"zip": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": {}, "summary": "texte", "disclosure": "texte", "credit_unions": [], "match_quality": "texte"}}

• find_eligible_credit_unions≈ 6430 tokens

  `relative_memberships` carries confirmed current/deceased relative membership scoped to one exact target credit union; one institution is never reused for another. `next_questions.unlocks_cu_count` counts membership decisions an answer may clarify, never guaranteed products. Discovery tool: find candidate credit unions a person may be able to JOIN, from their own facts rather than from a list of institutions. Pass any combination of home, worksite, or payroll geography (these are independent), occupation, employer, school (+school_relationship), associations, military_status, and worship; at least one discriminating fact is required, or pass willing_to_join_association=true as the sole discriminator to search documented joinable-association paths. City facts require their same-role state or a recognized same-role ZIP that uniquely identifies one state, and are accepted only when the closed Census gazetteer resolves them. This evaluates a bounded, prioritized candidate set, not the entire credit-union fleet: read `candidate_limit`, `candidate_set_truncated`, and `candidate_sources`, and never interpret an absent institution as unavailable or ineligible. Returns four buckets within that candidate set — eligible (a verified path already applies), conditionally_eligible (one more step, e.g. joining an association, with the cost and join URL when known), possibly_eligible (a path may apply but a requirement could not be confirmed), and unknown (we could not decide — either we hold no rules for the institution or the supplied facts cannot decide the rules we hold). Every non-positive entry carries a machine-readable `unknown_reason`: `geo_inputs_missing` / `org_inputs_missing` / `inputs_missing` mean ONE MORE FACT FROM THE USER would resolve it, so ask for it and call again; `no_rules` means we hold nothing for that institution and asking will not help; `incomplete_fom`, `fom_completeness_unaffirmed`, `low_confidence_rules` and `unmodeled_condition` mean we hold rules but will not turn a failure against them into a no. Each entry also carries `coverage` — {state, rules_held, last_confirmed_at, fom_affirmed} — describing what we HOLD about the institution as opposed to what we concluded about the person. Each entry carries the credit union id, name, state, confidence, and deterministic reasons. Use this to find supported candidates; use check_membership_eligibility when you already have specific credit_union_ids. Credit unions are never listed as ineligible — absence of evidence is never treated as evidence of absence, and the final membership determination is always the institution's. Every non-positive entry now also carries `missing_facts`: the exact question to ask the person next, the `fact_field` their answer populates, why it matters, and the institution's own words. The response's top-level `next_questions` ranks those questions across all institutions by how many they unlock — ASK THE TOP ONE TO THREE, MERGE THE ANSWERS INTO THE SAME REQUEST BODY, AND CALL AGAIN. Two or three turns is the intended shape of this tool; a single call is a first draft. Stop when `next_questions` is empty, when the top entry's `unlocks_cu_count` is below 2, or after three turns. `unanswerable` lists what no question can fix — institutions we hold no rules for, boundaries we can state but not decide (census tracts, school districts, a radius around an office the page never identifies), and rule sets whose completeness nobody affirmed; do not ask the user about those. Fact fields, in full — supply every one you know: `home_zip`, `home_state`, `home_county`, `home_city`; `work_zip`, `work_state`, `work_county`, `work_city`; `payroll_zip`, `payroll_state`, `payroll_county`, `payroll_city` (payroll can differ from the worksite and is a separate door); `property_zip`, `property_state`, `property_county`, `property_city` (where they OWN property — never inferred from where they live, and an absentee owner qualifies); `facility_zip`, `facility_state`, `facility_county`, `facility_city` (where their business maintains a location); `occupation`; `employer`; `school` plus `school_relationship` (student/alumni/employee — a school name without a relationship affirms nothing); `associations`; `military_status` plus `military_service_state` (state National Guard doors need the state); `worship`; `family_relation` plus `relative_employers`, `relative_schools`, `relative_associations` (a great many people qualify only through a relative — ask); `willing_to_join_association`; `applicant_kind` (person/trust/organization/partnership/corporation — some charters admit entities, and a person is never rejected by an entity-only door, only left unknown); and `asserted_org_qualifiers` (narrowings the person asserts about themselves, e.g. "assigned as a recruiter in Arkansas").

  Paramètres, retour & exemple (44)

  Paramètres

  • limit · number · optionnel
    Maximum entries per bucket (1-200). Default 50.
  • school · string · optionnel
    User's school/college/university, resolved to a canonical organization. Supply school_relationship too; a name alone is not a positive match.
  • worship · string · optionnel
    User's place of worship, resolved to a canonical organization.
  • employer · string · optionnel
    User's employer, resolved to a canonical organization for SEG matching.
  • home_zip · string · optionnel
    User's US 5-digit home ZIP or ZIP+4. Resolves to candidate counties; when home_state is supplied, the crosswalk must agree with it.
  • work_zip · string · optionnel
    User's US 5-digit work ZIP or ZIP+4. Resolves to candidate work counties; when work_state is supplied, the crosswalk must agree with it.
  • home_city · string · optionnel
    User's Census-recognized home city. Requires home_state or a recognized home_zip that uniquely identifies one state; unresolved labels are rejected rather than guessed.
  • work_city · string · optionnel
    Census-recognized city where the user works. Requires work_state or a recognized work_zip that uniquely identifies one state.
  • home_state · string · optionnel
    User's valid 50-state/DC code (e.g., CA, TX, NY). Lowercase is accepted and normalized.
  • occupation · string · optionnel
    User's occupation, matched against trade, industry, and profession fields of membership.
  • work_state · string · optionnel
    Valid 50-state/DC code where the user works (e.g., CA, TX, NY). Lowercase is accepted and normalized.
  • home_county · string · optionnel
    User's county. Wins over the ZIP-derived counties when supplied.
  • payroll_zip · string · optionnel
    ZIP from which the user's employer issues payroll; distinct from the worksite ZIP. When payroll_state is supplied, the ZIP must agree with it.
  • work_county · string · optionnel
    County where the user works. Wins over work-ZIP-derived counties when supplied.
  • associations · array · optionnel
    Associations, unions, or member organizations the user already belongs to.
  • facility_zip · string · optionnel
    ZIP where the user's business maintains a location. Distinct from the worksite ZIP.
  • payroll_city · string · optionnel
    Census-recognized city from which payroll is issued. Requires payroll_state or a recognized payroll_zip that uniquely identifies one state.
  • property_zip · string · optionnel
    ZIP where the user OWNS REAL PROPERTY. A door of its own — never inferred from where they live, and an absentee owner qualifies.
  • facility_city · string · optionnel
    Census-recognized city where the user's business maintains a location. Requires facility_state or a recognized facility_zip that uniquely identifies one state.
  • payroll_state · string · optionnel
    State from which the user's employer issues payroll; distinct from work_state.
  • property_city · string · optionnel
    Census-recognized city where the user owns real property. Requires property_state or a recognized property_zip that uniquely identifies one state.
  • applicant_kind · string · optionnel · person | trust | organization | partnership | corporation | other_legal_entity
    What the applicant IS. Some charters admit entities as well as people. Absent means a natural person; a person is never rejected by an entity-only door, only left unknown.
  • facility_state · string · optionnel
    State where the user's business maintains a location.
  • payroll_county · string · optionnel
    County from which the user's employer issues payroll; distinct from work_county.
  • property_state · string · optionnel
    State where the user owns real property. Distinct from home_state.
  • school_org_ids · array · optionnel
    Canonical school ids selected through resolve_eligibility_entities; never populate these from prose extraction.
  • facility_county · string · optionnel
    County where the user's business maintains a location.
  • family_relation · string · optionnel
    How the user relates to a RELATIVE whose own affiliations may qualify them (e.g. 'spouse', 'child', 'immediate family'). Required alongside relative_employers/relative_schools/relative_associations — without it there is nobody for those organizations to belong to. Many SEG lists read 'Employees of the following companies AND THEIR IMMEDIATE FAMILIES are eligible'; this is how that door is answered.
  • military_status · string · optionnel · active_duty | veteran | reservist | dod_civilian | military_family
    User's military affiliation, matched against military fields of membership.
  • property_county · string · optionnel
    County where the user owns real property. Distinct from home_county.
  • worship_org_ids · array · optionnel
    Canonical worship-organization ids selected through resolve_eligibility_entities.
  • employer_org_ids · array · optionnel
    Canonical employer ids selected through resolve_eligibility_entities. The API revalidates entity type and active-publication authority before use.
  • relative_schools · array · optionnel
    Schools the RELATIVE named by family_relation attends. Optional; same unknown-by-default contract as relative_employers.
  • relative_employers · array · optionnel
    Employers of the RELATIVE named by family_relation (not the user's own employer). Optional; omitting it leaves compound family doors undecided (unknown), never negative.
  • association_org_ids · array · optionnel
    Canonical association ids selected through resolve_eligibility_entities; each is type- and publication-revalidated.
  • school_relationship · string · optionnel · student | alumni | employee
    How the user relates to the school. Required with school to affirm a typed student, alumni, or school-employee path.
  • relative_memberships · array · optionnel
    Confirmed relative memberships scoped to one exact credit union. A membership at one institution is never reused for another; omit unconfirmed memberships and the corresponding family door remains unknown.
  • relative_associations · array · optionnel
    Associations the RELATIVE named by family_relation belongs to. Optional; same unknown-by-default contract as relative_employers.
  • military_service_state · string · optionnel
    The state the user serves, or served, in. State National Guard doors ("Oklahoma National Guard") need this; without it such a door reads unknown.
  • asserted_org_qualifiers · array · optionnel
    Narrowings the user asserts about themselves, quoted back from a missing_facts question (e.g. "assigned as Recruiters or ROTC Instructors within the State of Arkansas"). Absence caps a narrowed door rather than closing it.
  • relative_school_org_ids · array · optionnel
    Canonical school ids for the relative named by family_relation, never for the applicant.
  • relative_employer_org_ids · array · optionnel
    Canonical employer ids for the relative named by family_relation, never for the applicant.
  • willing_to_join_association · boolean · optionnel
    Set true to search documented joinable-association paths (valid as the sole discriminator). Set false only to suppress paths that require joining an association; false alone is not a discriminating search fact.
  • relative_association_org_ids · array · optionnel
    Canonical association ids for the relative named by family_relation, never for the applicant.

  Exemple d'appel

  {"name": "find_eligible_credit_unions", "arguments": {"limit": 1, "school": "texte", "worship": "texte", "employer": "texte", "home_zip": "texte", "work_zip": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "limit": 1, "counts": {}, "engine": "texte", "unknown": [], "eligible": [], "resolved": {}, "disclosure": "texte", "unanswerable": [], "next_questions": [], "candidate_limit": 1, "candidate_sources": {}}}

• find_product_rates_near_zip≈ 1320 tokens

  Use when someone asks for the best mortgage, auto-loan, HELOC, personal-loan, student-loan, equipment-loan, or credit-card rates near them and provides a ZIP. Finds the nearest NCUA-reported branch set, keeps credit unions with a current product-matched published rate, and ranks those offers by lowest APR with approximate distance as a tie-breaker. HELOC matching excludes closed-end home-equity loans. This is a local shopping shortlist: distance is straight-line, membership is not guaranteed, and published APR is not personalized approval.

  Paramètres, retour & exemple (5)

  Paramètres

  • zip · string · requis
    Five-digit US ZIP code used as the center of the nearby-branch search.
  • max_offers · number · optionnel
    Maximum product-matched offers to return (1-8, default 5).
  • term_months · number · optionnel
    Optional comparable loan term. For fixed mortgages, under 300 months selects the 15-year market and 300+ selects 30-year.
  • product_type · string · requis · mortgage | mortgage_arm | auto_loan | heloc | personal_loan | student_loan | equipment_loan | credit_card
    Product whose current published rates should be compared.
  • vehicle_condition · string · optionnel · new | used | certified_pre_owned | cpo
    Auto loans only. Omit to use the new-auto market.

  Exemple d'appel

  {"name": "find_product_rates_near_zip", "arguments": {"zip": "texte", "product_type": "mortgage"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"zip": "texte", "offers": [], "precision": "texte", "ranked_by": "texte", "disclosure": "texte", "product_type": "texte", "unavailable_reason": "texte", "nearby_credit_union_count": 1}}

• find_reachable_offers≈ 5955 tokens

  Find the best fresh, evidence-backed credit-union rates reachable from this person’s membership facts. This composed graph-first operation evaluates the complete active US credit-union fleet BEFORE rates are queried, so a strong out-of-state employer, association, school, military, family, property, work/payroll, or facility door is not lost behind a candidate cap or state-only rate search. `reachable_now` requires a verified membership path, satisfied supplied product dimensions, and fresh evidenced published pricing; `reachable_after_action` requires the same product proof plus a documented membership action. Unknown or mismatched term, intent, vehicle condition, or occupancy remains `unresolved`, never silently matched. `no_published_offer` means no matching fresh evidenced rate was found. Deposits rank published APY only. Lending ranks published APR rows first and separately labeled nominal-rate rows second, never comparing APR and rate as one measure. Every price includes verbatim evidence and as_of, and routed membership results preserve graph/publication lineage and source proof. Use product-aware questions only as bounded facts that may clarify. Published pricing is not approval or guaranteed final availability.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · number · optionnel
    Visible offers per bucket, 1-50. Candidate intersection happens before this cap.
  • person · object · requis
    Confirmed person facts accepted by find_eligible_credit_unions, including canonical *_org_ids selected through resolve_eligibility_entities. Unknown facts stay absent and canonical ids are revalidated by rates-api.
  • product · object · requis
    The financial product and matching attributes to route.

  Exemple d'appel

  {"name": "find_reachable_offers", "arguments": {"person": {}, "product": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"as_of": "texte", "counts": {}, "product": {}, "discovery": {}, "semantics": "texte", "disclosure": "texte", "unresolved": [], "completeness": {}, "ranking_basis": "texte", "reachable_now": [], "no_published_offer": [], "eligibility_snapshot": {}}}

• generate_client_report≈ 325 tokens

  Produce a clean, client-facing markdown rate comparison report a loan officer can share with a buyer. Pass either a saved scenario_id, or an inline client_name + comparison result (from get_financing_decision/compare_products).

  Paramètres, retour & exemple (4)

  Paramètres

  • result · object · optionnel
    The comparison result to format, if not using scenario_id
  • client_name · string · optionnel
    Client label, if not using scenario_id
  • scenario_id · string · optionnel
    Optional: a saved scenario id to build the report from
  • advisor_name · string · optionnel
    Optional advisor/company name for the report header

  Exemple d'appel

  {"name": "generate_client_report", "arguments": {"result": {}, "client_name": "texte", "scenario_id": "texte", "advisor_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"format": "texte", "markdown": "texte"}}

• generate_share_link≈ 298 tokens

  Turn a saved client scenario into a public, branded, shareable URL (https://app.rateapi.dev/r/TOKEN) that anyone can view without logging in. Returns a token and url. The link shows the client name, scenario inputs, and the ranked comparison with a "Powered by RateAPI" footer. Use revoke_share to disable a link later.

  Paramètres, retour & exemple (1)

  Paramètres

  • scenario_id · string · requis
    The saved scenario id to mint a share link for. Required.

  Exemple d'appel

  {"name": "generate_share_link", "arguments": {"scenario_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "token": "texte", "created_at": "texte", "scenario_id": "texte"}}

• get_benchmarks≈ 1196 tokens

  Get rate benchmark statistics (min/median/max APR) across all institutions. Use this for market analysis, comparing user quotes against market rates, or building benchmark dashboards. Returns statistics for mortgages (30yr fixed, 15yr fixed, and `mortgage_arm` — one bucket covering every adjustable-rate mortgage regardless of initial fixed period), auto loans (new/used — cars only), RV/boat/motorcycle/powersports (first-class vehicle categories), HELOCs, and personal loans. Each product shows the lowest APR institution, median APR, and count of institutions.

  Paramètres, retour & exemple (2)

  Paramètres

  • state · string · optionnel
    Filter to a specific US state (2-letter code). If omitted, returns nationwide benchmarks.
  • product_type · string · optionnel · mortgage_30yr | mortgage_15yr | mortgage_arm | auto_loan_new | auto_loan_used | rv | boat | motorcycle
    Filter to a specific product type. If omitted, returns benchmarks for all product types.

  Exemple d'appel

  {"name": "get_benchmarks", "arguments": {"state": "texte", "product_type": "mortgage_30yr"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"rawData": [], "summary": "texte", "benchmarks": [], "generatedAt": "texte", "stateFilter": "texte", "totalInstitutions": "texte"}}

• get_cohort≈ 534 tokens

  Get a single saved cohort by id, including all members and the last scan snapshot (triage list).

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Cohort id. Required.

  Exemple d'appel

  {"name": "get_cohort", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"triage": [], "changed": [], "scanned": 1}}

• get_coverage≈ 1606 tokens

  Introspect what mortgage/loan data the API covers BEFORE scanning — which states, lenders, and product types are present, row counts per segment, and last-updated freshness per segment. Returns a coverage matrix so an agent can pick a scannable state/product before calling scan_savings or get_financing_decision. Mirrors the /meta global counts, expanded into a per-segment matrix. Boats, RVs, motorcycles, and powersports are first-class product categories; auto means cars.

  Paramètres, retour & exemple (4)

  Paramètres

  • state · string · optionnel
    Optional 2-letter US state code to scope the matrix to a single state.
  • group_by · string · optionnel · state | product | state_product
    Optional segmentation axis. Default 'state'.
  • freshness_days · number · optionnel
    Optional uniform staleness window in days (1-90). OMIT to use per-category freshness windows — supplying a value overrides every category and is echoed back as freshness_mode=override.
  • product_category · string · optionnel · mortgage | auto | rv | boat | motorcycle | powersports | heloc | personal
    Optional. Restrict the matrix to one product category. Omit for all.

  Exemple d'appel

  {"name": "get_coverage", "arguments": {"state": "texte", "group_by": "state", "freshness_days": 1, "product_category": "mortgage"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "totals": {}, "coverage": {}, "segments": [], "disclosures": [], "generated_at": "texte", "next_actions": [], "freshness_days": 1, "freshness_mode": "texte", "institution_profiles": {}}}

• get_credit_union≈ 3391 tokens

  Reference tool: Get a credit union's rates, membership eligibility, and source-labelled NCUA quarterly profile: members, assets, year opened, charter, reported services, and branch locations. Eligibility annotates published criteria and never asserts that an individual is ineligible; profile facts are regulatory snapshots, not live prices. Use this when a user asks about a specific credit union. For personalized rate recommendations, use get_financing_decision instead.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Credit union slug (URL-friendly name, e.g., "navy-federal-credit-union"). Required.
  • state · string · requis
    US state code (2-letter, e.g., CA, TX, NY). Required.

  Exemple d'appel

  {"name": "get_credit_union", "arguments": {"slug": "texte", "state": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"widget": {}, "summary": "texte", "all_rates": [], "best_rate": {}, "eligibility": {}, "credit_union": {}, "ncua_profile": {}}}

• get_deposit_benchmarks≈ 1293 tokens

  Best/median/spread credit-union deposit APY by product, term, and state, with per-CU peer ranking. Pass the MCP field `product` using one exact underscore value: savings, cd, share_certificate, money_market, ira_cd, ira, or share_savings. The MCP server translates it to REST `product_category`; do not send `product_category`, `mma`, or `money-market` to this tool. Deposits quote APY (no APR); CDs/share certificates include term. Current + recent data; history is retention-bounded.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · number · optionnel
    Top N credit unions to rank (default 10, clamp 1..50).
  • state · string · optionnel
    2-letter US state code; omit for nationwide.
  • metric · string · optionnel · apy
    Deposits rank by APY, highest first. No APR.
  • product · string · optionnel · savings | cd | share_certificate | money_market | ira_cd | ira | share_savings
    MCP field for the deposit product category. Use an exact enum value such as `money_market`; do not use REST field name `product_category`, `mma`, or `money-market`. Omit for all deposit types.
  • term_months · number · optionnel
    For CD/share_certificate/ira_cd: filter to a specific term (savings_term_months).

  Exemple d'appel

  {"name": "get_deposit_benchmarks", "arguments": {"limit": 1, "state": "texte", "metric": "apy", "product": "savings", "term_months": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"best": {}, "note": "texte", "as_of": "texte", "count": 1, "state": "texte", "table": [], "market": {}, "term_months": 1, "product_category": "texte", "benchmark_balance": "texte", "total_credit_unions": 1}}

• get_deposit_beta≈ 1049 tokens

  Deposit beta (repricing sensitivity) = change in deposit APY per 100bps change in a benchmark/market rate — the core credit-union/bank ALM & interest-rate-risk (IRR) model input. Pass the MCP field `product` using an exact underscore value such as `money_market`; do not send `product_category`, `mma`, or `money-market`. Derived from RateAPI's retained published deposit-rate history. SHORT-WINDOW / retention-bounded: full-cycle beta needs multi-year history (roadmap) — results ship with an explicit confidence/depth caveat. Deposits quote APY, never APR. Aggregate published rates only — never member/borrower data.

  Paramètres, retour & exemple (6)

  Paramètres

  • state · string · optionnel
    2-letter US state code
  • window · string · optionnel · 90d | 180d | 365d
  • product · string · requis · savings | cd | share_certificate | money_market | ira_cd
    Required MCP product field. Use one exact underscore enum value; money market is `money_market`, never `mma` or `money-market`.
  • group_by · string · optionnel · overall | state | cu
  • benchmark · string · optionnel · cd_top_quartile | treasury | fed_funds
  • term_months · number · optionnel

  Exemple d'appel

  {"name": "get_deposit_beta", "arguments": {"product": "savings"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "peer": {}, "state": "texte", "window": "texte", "product": "texte", "group_by": "texte", "segments": [], "confidence": "texte", "data_source": "texte", "disclosures": [], "term_months": "texte", "benchmark_used": "texte"}}

• get_doc≈ 452 tokens

  DOCS: return the full text of one RateAPI documentation page by slug (from search_docs) or by its published URL. Documentation only — it describes the contract, not live rates. Available slugs: quickstart, authentication, rate-limits-and-pricing, coverage, freshness, evidence-and-methodology, quoting-rules, eligibility, endpoints, mcp-server, products-and-parameters, errors-and-troubleshooting, deprecation-policy.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · optionnel
    Alternatively, the canonical published URL of the page.
  • slug · string · optionnel · quickstart | authentication | rate-limits-and-pricing | coverage | freshness | evidence-and-methodology | quoting-rules | eligibility
    The page identifier returned by search_docs.

  Exemple d'appel

  {"name": "get_doc", "arguments": {"url": "texte", "slug": "quickstart"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "slug": "texte", "error": "texte", "title": "texte", "content": "texte", "summary": "texte", "available": []}}

• get_eligibility_changes≈ 681 tokens

  Read the bounded, cursor-paginated feed of currently active eligibility publication replacements since an ISO timestamp. Use it to invalidate caches keyed by credit_union_id or publication identity. It exposes aggregate publication metadata only: no personal facts, no historical verdict, and no claim that a person is eligible or ineligible.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum publication changes returned.
  • since · string · requis
    Exclusive ISO 8601 activation boundary with an offset.
  • cursor · string · optionnel
    Opaque next_cursor from the prior page; do not construct or modify it.

  Exemple d'appel

  {"name": "get_eligibility_changes", "arguments": {"since": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"since": "texte", "changes": [], "has_more": true, "ordering": [], "returned": 1, "semantics": "texte", "disclosure": "texte", "next_cursor": "texte"}}

• get_eligibility_coverage≈ 2367 tokens

  Enterprise RateAPI Routes coverage: how many US credit unions RateAPI holds live, verbatim-evidenced membership rules for (and what share of the active fleet that is), how the rules split by kind, how many counties, states and employers they name, verification status, and freshness. The `authority` object distinguishes exact immutable active publications from older graph and flat compatibility records; `evidence_sources` reports the public source mix. Returns a dated `headline` sentence that can be quoted verbatim. Use this BEFORE find_eligible_credit_unions or check_membership_eligibility when the user asks how complete, authoritative, or fresh the eligibility data is. Aggregate only — no institution-level rows; those come from the eligibility tools. Never reports credit data: the rule schema has no condition kind for credit score, income or debt. An institution absent from the graph is undecided, never ineligible.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_eligibility_coverage", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"as_of": "texte", "fleet": {}, "reach": {}, "rules": {}, "by_kind": [], "headline": "texte", "pipeline": [], "authority": {}, "semantics": "texte", "disclosure": "texte", "population": {}, "credit_data": {}}}

• get_email_branding≈ 376 tokens

  Get the organization's current email branding (display name, logo URL, brand color, intro, business address, reply-to).

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_email_branding", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"branding": {}}}

• get_extraction_stats≈ 997 tokens

  Get data extraction statistics showing the scale and health of rate data collection. Use this to understand extraction volumes, product coverage, and data freshness. Supports filtering by date range and product type. Great for building transparency dashboards or monitoring data collection health.

  Paramètres, retour & exemple (3)

  Paramètres

  • endTime · string · optionnel
    End of the time range. Supports ISO8601 or relative times. Defaults to "now".
  • startTime · string · optionnel
    Start of the time range. Supports ISO8601 (e.g., "2024-01-15T00:00:00Z") or relative times ("now-24h", "now-7d", "now-1m"). Defaults to "now-24h".
  • product_type · string · optionnel · mortgage | auto_loan | rv | boat | motorcycle | powersports | personal_loan | heloc
    Filter statistics to a specific product type. If omitted, returns stats for all product types.

  Exemple d'appel

  {"name": "get_extraction_stats", "arguments": {"endTime": "texte", "startTime": "texte", "product_type": "mortgage"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": {}, "stats": {}, "summary": "texte", "coverage": {}, "products": [], "dataQuality": {}, "generatedAt": "texte", "topProducts": "texte", "hourlyTrendSample": []}}

• get_financing_decision≈ 3601 tokens

  RECOMMENDED WHEN SHOPPING: Get personalized financing recommendations for ANY loan or credit product across every major type: mortgages (30yr/15yr/20yr/10yr fixed and ARMs), auto loans (new/used/CPO, 36-84 month terms), RV/boat/motorcycle/powersports loans, HELOCs (fixed/variable), personal loans (secured/unsecured), student loans, equipment loans, and credit cards (rewards, cash_back, secured, balance_transfer, low_rate, business, platinum, student). Analyzes current market offers and returns actionable recommendations with explanations. Use this instead of looking up raw rates when the user is asking "what rate can I get?" and does NOT yet have an offer. IMPORTANT: if the user ALREADY has a quoted rate and is asking whether it is good/fair/competitive ("I was quoted 6.9%, is that any good?"), call rate_sanity_check instead — it returns a percentile verdict on their specific number, which is what that question is actually asking. Provide the user's state, intent (purchase/refinance/cash_out/balance_transfer/new_credit), and amount for personalized advice.

  Paramètres, retour & exemple (23)

  Paramètres

  • zip · string · optionnel
    User's US 5-digit ZIP or ZIP+4. Resolves to a county server-side for membership-eligibility matching; its crosswalk state must agree with state.
  • state · string · requis
    Valid 50-state/DC code (2-letter, e.g., CA, TX, NY). Required; lowercase is accepted and normalized.
  • amount · number · requis
    Loan amount in dollars (minimum 1000). Required.
  • county · string · optionnel
    User's county for membership-eligibility matching (credit union field-of-membership). Helps flag which lenders the user can actually join.
  • intent · string · requis · purchase | refinance | cash_out | balance_transfer | new_credit
    The loan intent. For mortgages, use "purchase" or "refinance". For auto loans, use "purchase" (new/used car) or "refinance" (existing auto loan). Required.
  • school · string · optionnel
    User's school/college/university. Supply school_relationship too; a school name alone does not affirm a typed eligibility path.
  • worship · string · optionnel
    User's place of worship, used to annotate offers with worship-org-affinity eligibility.
  • employer · string · optionnel
    User's employer, matched against credit union employer/SEG membership lists for eligibility.
  • no_points · boolean · optionnel
    If true, prefer no-points loans only. Applies to mortgages.
  • current_apr · number · optionnel
    Current offer APR if refinancing (percentage).
  • term_months · number · optionnel
    Loan term in months (12-480). Defaults to 360 (30-year) for mortgages, 60 (5-year) for auto loans. Common auto loan terms: 36, 48, 60, 72, 84 months. Common mortgage terms: 180 (15-year), 360 (30-year).
  • credit_score · number · optionnel
    Borrower's credit score (300-850). Highly recommended for accurate rate matching.
  • current_rate · number · optionnel
    Current offer rate if refinancing (percentage, e.g., 6.5 for 6.5%).
  • product_type · string · optionnel · mortgage | mortgage_arm | auto_loan | rv | boat | motorcycle | powersports | personal_loan
    Type of financing product: "mortgage" (FIXED-rate home purchase/refinance), "mortgage_arm" (ADJUSTABLE-rate mortgage), "auto_loan" (vehicle financing), "heloc" (home equity line of credit), "personal_loan" (general purpose loans), "credit_card" (credit card offers), "student_loan" (student/education loans, incl. refinance and graduate loans), "equipment_loan" (farm/heavy equipment and tractor financing). Defaults to "mortgage". Pick "mortgage_arm" whenever the user says ARM, adjustable, or names a slash pair ("5/1", "5/5", "7/1", "10/1") — fixed and adjustable are ranked as SEPARATE markets, because an ARM intro rate sits structurally below a comparable fixed rate and a blended list would put every ARM on top and call it cheaper, which is true only until it resets. Within "mortgage", term_months selects 15- vs 30-year; it has no meaning for "mortgage_arm".
  • vehicle_type · string · optionnel · car | truck | suv | motorcycle | rv | boat
    AUTO LOANS ONLY: Type of vehicle being financed. Some lenders offer specialized rates by vehicle type.
  • vehicle_year · number · optionnel
    AUTO LOANS ONLY: Model year of the vehicle (e.g., 2024, 2020). Used to determine age-based rate tiers.
  • eligible_only · boolean · optionnel
    BETA (annotation-only): eligible_only is in beta pending identity-verification thresholds; offers are annotated, not filtered. Setting true adds an eligible_only_status notice to the response — eligibility annotates and re-ranks, but no offers are dropped. When an annotation comes back unknown, that is not a no: call find_eligible_credit_unions or check_membership_eligibility and read `missing_facts` — ask those questions before concluding no offers exist. eligible_only is beta.
  • max_providers · number · optionnel
    Maximum number of providers to return (1-5). Defaults to 5.
  • military_status · string · optionnel · active_duty | veteran | reservist | dod_civilian | military_family
    User's military affiliation. Annotates offers with eligible_via_military where the credit union has a military field of membership.
  • vehicle_condition · string · optionnel · new | used | certified_pre_owned | any
    AUTO LOANS ONLY: Condition of the vehicle being purchased or refinanced. Affects rate eligibility.
  • school_relationship · string · optionnel · student | alumni | employee
    How the user relates to the named school. Required with school to affirm a typed student, alumni, or school-employee path.
  • include_out_of_state · boolean · optionnel
    Optional: Include documented out-of-state open or multi-state credit-union candidates. Defaults to false, which preserves the requested-state candidate set.
  • include_institution_context · boolean · optionnel
    Optional: Include compact NCUA quarterly facts on each final offer (members, locations, assets, year opened, and selected relationship services).

  Exemple d'appel

  {"name": "get_financing_decision", "arguments": {"state": "texte", "amount": 1, "intent": "purchase"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"why": [], "summary": "texte", "tradeoffs": [], "rate_range": {}, "request_id": "texte", "top_offers": [], "recommendation": {}, "resolved_county": {}}}

• get_league_table≈ 1411 tokens

  Loan-officer competitive-landscape report: ranked roster of the top N lenders publishing a given mortgage product in a state today — per-lender rows (name, best APR/rate, product, position, bps above the leader) — plus the market min/median/max. The market median is INSTITUTION-level — one vote per lender, using each lender's best APR (basis = total_lenders, not market.count) — so a lender publishing a large rate matrix cannot pull it. Extends get_benchmarks (which returns only min/median/max + the single lowest institution) with the full ranked table.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · number · optionnel
    Top N lenders to return (default 10, clamped 1..50)
  • state · string · requis
    2-letter US state code, e.g. CA, TX, NY
  • metric · string · optionnel · apr | rate
    Rank by apr (default) or rate
  • product · string · requis · 30yr_fixed | 15yr_fixed
    Mortgage product
  • include_institution_context · boolean · optionnel
    Include compact NCUA member, location, asset, founding-year, and selected service facts per lender.

  Exemple d'appel

  {"name": "get_league_table", "arguments": {"state": "texte", "product": "30yr_fixed"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "as_of": "texte", "count": 1, "limit": 1, "state": "texte", "table": [], "market": {}, "metric": "texte", "product": "texte", "total_lenders": 1}}

• get_monitor≈ 498 tokens

  Get detailed information about a specific monitor by its ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • monitor_id · string · requis
    The unique identifier of the monitor. Required.

  Exemple d'appel

  {"name": "get_monitor", "arguments": {"monitor_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "monitor": {}, "summary": "texte"}}

• get_monitor_stats≈ 221 tokens

  Get rollup stats for the account's rate monitors: total, active, and webhooks sent. Complements list_monitors.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_monitor_stats", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"reset_date": "texte", "total_monitors": 1, "active_monitors": 1, "webhooks_sent_today": 1, "webhooks_sent_this_month": 1}}

• get_personal_access_catalog≈ 4042 tokens

  Evaluate one person across 1-19 explicit loan or deposit selectors using one exhaustive eligibility snapshot. Returns separate membership, published availability, product suitability, published pricing, underwriting, and approval layers. Lead only with reachable_now or reachable_after_action; unresolved and no_published_price are unknown, never a denial. Published APY, APR, or clearly labeled nominal rate is not a personalized quote, underwriting result, preapproval, commitment, or guarantee. Every returned published price carries source evidence and as_of.

  Paramètres, retour & exemple (4)

  Paramètres

  • person · object · requis
    Explicit caller-supplied person facts. Unknown facts stay absent; do not infer them.
  • products · array · requis
    One to nineteen unique explicit product selectors. Do not invent missing scenario facts.
  • total_limit · integer · optionnel
    Maximum detail rows across all selectors; must be at least the selector count. Default 50.
  • limit_per_product · integer · optionnel
    Maximum detail rows for each selector, subject to the total and plan caps. Default 5.

  Exemple d'appel

  {"name": "get_personal_access_catalog", "arguments": {"person": {}, "products": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"products": [], "snapshot": {}, "questions": {}, "semantics": "texte", "disclosure": "texte", "completeness": {}, "catalog_version": "texte"}}

• get_product_access_envelopes≈ 803 tokens

  Get non-personal, evidence-bound membership-access metadata for up to 50 exact deposit product references. Returns active-publication path kinds and documented joinable-association actions alongside the current evidenced product rate. This does NOT decide whether a person is eligible, easy to qualify, approved, or within a published balance/audience constraint; unavailable evidence stays unavailable.

  Paramètres, retour & exemple (1)

  Paramètres

  • products · array · requis
    Exact deposit product references; no fuzzy product matching is performed.

  Exemple d'appel

  {"name": "get_product_access_envelopes", "arguments": {"products": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"counts": {}, "envelopes": [], "semantics": "texte", "disclosure": "texte"}}

• get_rate_delta≈ 1024 tokens

  Compare the LIVE market rate distribution now vs ~1/2/4 weeks ago for a product and state. Returns now/then min, median, max, count plus the median and min delta and a direction (down/up/flat). Bounded by data retention — if no comparable historical snapshot exists, then is null with an explanatory note. Use this to show how rates have moved recently.

  Paramètres, retour & exemple (3)

  Paramètres

  • since · string · optionnel · 1w | 2w | 4w
    How far back to compare against. Defaults to "1w".
  • state · string · requis
    US state code (2-letter, e.g., CA, TX). Required.
  • product_type · string · requis · auto_loan | rv | boat | motorcycle | powersports | mortgage | heloc | personal_loan
    Type of financing product. Required.

  Exemple d'appel

  {"name": "get_rate_delta", "arguments": {"state": "texte", "product_type": "auto_loan"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"now": {}, "note": "texte", "then": {}, "state": "texte", "change": {}, "window": "texte", "data_source": "texte", "product_type": "texte"}}

• get_rate_history≈ 1138 tokens

  Historical rate time-series: a date-ranged array of {date, min/median/max APR, count} points per product/state for dashboards, charts, backtests, and timing confidence — bounded by data retention. Differs from get_rate_delta (a single now-vs-then comparison): this returns the full series. Boats, RVs, motorcycles, and powersports are first-class product types; auto_loan means cars. Calls the /v1/rate-history public API (single source of truth).

  Paramètres, retour & exemple (5)

  Paramètres

  • state · string · requis
    US state code (2-letter, e.g., CA, TX). Required.
  • window · string · optionnel · 30d | 60d | 90d | 180d | 365d
    Lookback window. Default "90d". Bounded by data retention.
  • interval · string · optionnel · day | week
    Bucket granularity per point. Default "week".
  • product_type · string · requis · auto_loan | rv | boat | motorcycle | powersports | mortgage | heloc | personal_loan
    Type of financing product. Required.
  • vehicle_condition · string · optionnel · new | used | cpo
    auto_loan only; selects the benchmark bucket. Default "new".

  Exemple d'appel

  {"name": "get_rate_history", "arguments": {"state": "texte", "product_type": "auto_loan"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "state": "texte", "series": [], "window": "texte", "summary": {}, "interval": "texte", "data_source": "texte", "product_type": "texte"}}

• get_scenario≈ 255 tokens

  Get a single saved scenario by id (inputs + stored comparison).

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Scenario id

  Exemple d'appel

  {"name": "get_scenario", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "error": "texte", "input": {}, "createdAt": "texte", "clientName": "texte", "resultSnapshot": "texte"}}

• get_usage≈ 294 tokens

  Check the calling account's API usage and remaining quota for this month (tier, used, remaining, limit, reset date). Use BEFORE running many calls to avoid hitting rate limits.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_usage", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"limit": 1, "remaining": 1, "reset_date": "texte", "requests_today": 1, "total_requests": 1, "requests_this_month": 1}}

• list_cohorts≈ 244 tokens

  List saved cohorts for the account (newest first). Returns id, name, member count, and last scan time. Keeps the payload small — use get_cohort for full member detail.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_cohorts", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "cohorts": []}}

• list_credit_unions≈ 827 tokens

  Reference tool: Discover credit unions by state or nearest to a 5-digit ZIP. State listings include rate availability, member count, and reported location count. ZIP discovery ranks NCUA-reported branches by estimated straight-line miles from the ZIP center. For personalized rate recommendations, use get_financing_decision instead.

  Paramètres, retour & exemple (2)

  Paramètres

  • zip · string · optionnel
    Optional: Find the closest credit unions by NCUA-reported branch location. Distances are ZIP-centroid straight-line estimates. When supplied, ZIP discovery takes precedence over state listing.
  • state · string · optionnel
    Optional: Filter to a specific state (2-letter code). If not provided, returns all states.

  Exemple d'appel

  {"name": "list_credit_unions", "arguments": {"zip": "texte", "state": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"state": "texte", "summary": "texte", "state_name": "texte", "with_rates": 1, "credit_unions": [], "total_credit_unions": 1, "verified_last_7_days": 1}}

• list_decision_logs≈ 377 tokens

  Recall past financing decisions made on this account (audit log). Filter by request_id to look up a specific prior decision, or paginate with limit/offset.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · number · optionnel
    Max rows (default 20, max 100)
  • offset · number · optionnel
    Pagination offset
  • request_id · string · optionnel
    Optional: look up a specific decision by its request_id

  Exemple d'appel

  {"name": "list_decision_logs", "arguments": {"limit": 1, "offset": 1, "request_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"logs": [], "total": 1, "has_more": true}}

• list_digests≈ 221 tokens

  List the account's scheduled digests (cohort, email, cadence, enabled, last run).

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_digests", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "digests": []}}

• list_email_campaigns≈ 228 tokens

  List the organization's branded rate-email campaigns (name, criteria, cadence, status, last run).

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_email_campaigns", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "campaigns": []}}

• list_monitors≈ 544 tokens

  List all monitors associated with your API key. Supports pagination and filtering by status.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · number · optionnel
    Maximum number of monitors to return (1-100). Defaults to 20.
  • offset · number · optionnel
    Number of monitors to skip for pagination. Defaults to 0.
  • status · string · optionnel · active | paused | disabled
    Filter monitors by status.

  Exemple d'appel

  {"name": "list_monitors", "arguments": {"limit": 1, "offset": 1, "status": "active"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"summary": "texte", "monitors": [], "pagination": {}}}

• list_rate_alerts≈ 520 tokens

  List the rate alerts subscribed for a given email (status, product, state, intent, target, last notified).

  Paramètres, retour & exemple (1)

  Paramètres

  • email · string · requis
    The email whose alerts to list. Required.

  Exemple d'appel

  {"name": "list_rate_alerts", "arguments": {"email": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "alerts": []}}

• list_rates≈ 1706 tokens

  List and filter raw rate rows (the core data primitive) by product, state, lender, and term with limit/offset pagination. Boats, RVs, motorcycles, and powersports are first-class product types; auto_loan means cars.

  Paramètres, retour & exemple (11)

  Paramètres

  • sort · string · optionnel · apr_asc | apr_desc | rate_asc | rate_desc | updated_desc
    Default apr_asc
  • limit · number · optionnel
    1-500, default 50
  • state · string · optionnel
    2-letter US state code; omit for all states
  • lender · string · optionnel
    Filter by credit-union name (substring, case-insensitive)
  • offset · number · optionnel
    Pagination offset, default 0
  • max_apr · number · optionnel
  • min_apr · number · optionnel
  • audience · string · optionnel · business | consumer
    WHO the product is for, orthogonal to product type: 'business' returns business-audience products across every category (DSCR mortgages, business deposits, SBA loans); 'consumer' excludes them.
  • term_months · number · optionnel
  • loan_program · string · optionnel
  • product_type · string · optionnel · mortgage | auto_loan | rv | boat | motorcycle | powersports | heloc | personal_loan

  Exemple d'appel

  {"name": "list_rates", "arguments": {"sort": "apr_asc", "limit": 1, "state": "texte", "lender": "texte", "offset": 1, "max_apr": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"as_of": "texte", "rates": [], "filters": {}, "pagination": {}}}

• list_scenarios≈ 222 tokens

  List saved client scenarios for the account, newest first.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_scenarios", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "scenarios": []}}

• list_shares≈ 263 tokens

  List all hosted shareable report links for the account, newest first. Returns token, scenario_id, client_name, views, last_viewed_at, revoked, created_at, and url for each share. Use this to see view analytics and manage which links are still live.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_shares", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "shares": []}}

• list_webhook_deliveries≈ 1246 tokens

  Org-scoped webhook delivery observability for the authenticated API key. Lists the per-event webhook delivery log for your monitors — each row shows status (delivered/failed/pending), HTTP response code, error, response time, the destination URL, and timestamp — with a roll-up summary (total/delivered/failed/pending). Use this to surface SILENT webhook failures (a delivery that never reached your endpoint). Filter by monitor_id and/or status. To replay a failed (or any) delivery, set redeliver_id to that row's id; the original payload is re-sent verbatim and the replay is itself audited. Distinct from deliver_test_webhook, which sends a brand-new simulated event.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
  • offset · integer · optionnel
  • status · string · optionnel · delivered | failed | pending
    Filter by delivery outcome.
  • monitor_id · string · optionnel
    Filter to one monitor.
  • redeliver_id · integer · optionnel
    If set, replay the delivery with this audit-log id instead of listing (maps to action:redeliver, delivery_id).

  Exemple d'appel

  {"name": "list_webhook_deliveries", "arguments": {"limit": 1, "offset": 1, "status": "delivered", "monitor_id": "texte", "redeliver_id": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"content": [], "disclosures": [], "next_actions": [], "structuredContent": {}}}

• max_loan≈ 706 tokens

  Estimate the largest loan a borrower can afford from income and a target debt-to-income (DTI) ratio. Returns max monthly payment, max loan amount, and the rate used. If no rate is supplied, the current best market rate for the product/state is used.

  Paramètres, retour & exemple (7)

  Paramètres

  • dti · number · requis
    Target debt-to-income ratio as a decimal, e.g. 0.36
  • rate · number · optionnel
    Optional annual interest rate, e.g. 6.5. If omitted, best market rate is used.
  • state · string · optionnel
    US state code (used to look up a market rate when rate is omitted)
  • term_months · number · requis
    Loan term in months (e.g. 360)
  • product_type · string · optionnel
    Product for the market-rate lookup, default mortgage
  • income_annual · number · requis
    Gross annual income in dollars
  • existing_monthly_debt · number · optionnel
    Optional existing monthly debt payments to subtract

  Exemple d'appel

  {"name": "max_loan", "arguments": {"dti": 1, "term_months": 1, "income_annual": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "rate_used": "texte", "assumptions": {}, "rate_source": "texte", "max_loan_amount": "texte", "max_monthly_payment": "texte"}}

• optimize_buydown≈ 1526 tokens

  Given a discount-points / lender-credit tradeoff menu for a candidate loan, returns break-even months, lifetime savings, and the optimal point-spend. The points analog of refinance_break_even.

  Paramètres, retour & exemple (6)

  Paramètres

  • state · string · optionnel
    Optional 2-letter state (validated only if supplied).
  • options · array · requis
    Points/lender-credit tradeoff menu to evaluate.
  • base_rate · number · requis
    The no-points (par) interest rate, percent, e.g. 6.75.
  • hold_months · number · optionnel
    Expected time-in-loan horizon for lifetime savings; defaults to term_months.
  • loan_amount · number · requis
    Loan principal in dollars (>0).
  • term_months · number · requis
    Loan term in months, e.g. 360.

  Exemple d'appel

  {"name": "optimize_buydown", "arguments": {"options": [], "base_rate": 1, "loan_amount": 1, "term_months": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"state": "texte", "reason": "texte", "optimal": {}, "options": [], "base_rate": "texte", "disclosures": [], "hold_months": 1, "loan_amount": "texte", "term_months": 1, "next_actions": [], "recommendation": "texte", "assumed_defaults": {}}}

• project_pmi_removal≈ 1698 tokens

  For low-down-payment borrowers (LTV > 80%): projects when private mortgage insurance (PMI) drops off, the total PMI paid until then, and how much extra monthly principal cancels PMI sooner. Reuses the same amortization + PMI logic as estimate_monthly_cost. If no rate is supplied, the current best market rate for the state is used. Use for 'when does my PMI go away / how do I get rid of PMI faster?' questions.

  Paramètres, retour & exemple (9)

  Paramètres

  • rate · number · optionnel
    Annual rate %, e.g. 6.5. Omit -> best market rate for state.
  • state · string · optionnel
    2-letter code for market-rate lookup. Default CA.
  • pmi_rate · number · optionnel
    Annual PMI as % of loan balance. Default 0.5.
  • home_price · number · optionnel
    Purchase/appraised price. Required unless loan_amount given.
  • loan_amount · number · optionnel
    Optional explicit loan; overrides home_price - down_payment.
  • term_months · number · optionnel
    Loan term in months. Default 360.
  • credit_score · number · optionnel
    Optional, for market-rate lookup.
  • down_payment · number · optionnel
    Cash down, dollars. Default 0.
  • extra_monthly_payment · number · optionnel
    Optional extra principal/month to model faster cancel. Default 0.

  Exemple d'appel

  {"name": "project_pmi_removal", "arguments": {"rate": 1, "state": "texte", "pmi_rate": 1, "home_price": 1, "loan_amount": 1, "term_months": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"pmi_drop": {}, "rate_used": "texte", "home_price": "texte", "monthly_pi": "texte", "disclosures": [], "loan_amount": "texte", "pmi_applies": true, "rate_source": "texte", "down_payment": "texte", "extra_needed": [], "next_actions": [], "starting_ltv": "texte"}}

• rate_sanity_check≈ 3520 tokens

  RECOMMENDED WHEN THE USER ALREADY HAS A QUOTE: answers "is this rate any good?" for a specific number a borrower was offered. Use this whenever someone says they were quoted / offered / approved at a rate and wants to know if it is fair, good, competitive, high, or a rip-off — e.g. "I got offered 6.9% on a 30-year in Ohio, is that fair?", "my dealer quoted 8.4% on a used car loan", "is 7.1% high for a HELOC in TX?". Given a product_type, state, and rate (and optional apr/fees/amount/term_months), returns the percentile of the quote within the live market distribution, a verdict (market_leading, plausible, suspicious_low, overpriced), whether it falls below the known product rate floor, and the market min/median/max with an as_of date. Prefer this over get_financing_decision for quote-in-hand questions: the user wants a verdict on THEIR number, not a list of other offers. Set include_better_offers=true to get named statewide lenders beating the quote. When the user provides a ZIP, set include_nearby_offers=true to pair product-matched rates with the closest credit unions by NCUA-reported branch location; distances are straight-line ZIP-center estimates, never driving distance. Every response also returns `share_url` — a link to this same check on rateapi.dev that the borrower can send to their lender or broker. Surface it whenever the user might act on the result; it re-runs against live rates when opened, so it never goes stale. NOTE: this is the BORROWER-side tool; check_competitive_position is the lender-side equivalent for benchmarking a lender's own published pricing. If the quote is an ADJUSTABLE-rate mortgage (the user says ARM / adjustable / "5/1" / "5/5" / "7/1"), pass product_type=mortgage_arm rather than mortgage — ARMs are scored against their own market. Caveat to surface to the user: the comparison does not currently segment by credit score, LTV, or points, and quoted fees are not folded into the APR comparison.

  Paramètres, retour & exemple (12)

  Paramètres

  • apr · number · optionnel
    The quoted APR as a percentage. Optional — falls back to rate if omitted.
  • zip · string · optionnel
    Borrower ZIP code. Optional; sharpens membership eligibility and enables include_nearby_offers.
  • fees · number · optionnel
    Quoted fees in dollars. Optional, used only for the note.
  • rate · number · requis
    The quoted interest rate as a percentage (e.g., 4.25). Required.
  • state · string · requis
    US state code (2-letter, e.g., CA, TX). Required.
  • amount · number · optionnel
    Loan amount in dollars. Optional — also sharpens better-offer payment math.
  • max_offers · number · optionnel
    How many better offers to return (1-5, default 3). Only applies with include_better_offers.
  • term_months · number · optionnel
    Loan term in months. For MORTGAGES this selects which market the quote is scored against: pass 180 for a 15-year and 360 for a 30-year. 15-year rates run structurally lower, so omitting it on a 15-year quote compares it to 30-year offers and makes an ordinary rate look market-leading. Defaults to 30-year. Also sharpens better-offer payment math for every product.
  • credit_score · number · optionnel
    Borrower's credit score (300-850). Optional; improves better-offer matching.
  • product_type · string · requis · auto_loan | rv | boat | motorcycle | powersports | mortgage | mortgage_arm | heloc
    Type of financing product the quote is for. Pick `mortgage_arm` — NOT `mortgage` — whenever the user names an adjustable-rate mortgage: "ARM", "adjustable", or a slash pair like "5/1", "5/5", "7/1", "10/1". ARM intro rates run structurally BELOW fixed rates, so scoring an ARM against the fixed market makes an ordinary quote look market-leading, which is the exact error this tool exists to prevent. All initial fixed periods share one ARM market. Use `mortgage` for fixed-rate mortgages and set term_months to pick 15- vs 30-year.
  • include_better_offers · boolean · optionnel
    Set TRUE for negotiation questions. Adds `better_offers`: named lenders currently beating the quote, each with the APR gap in basis points, estimated monthly savings, and `can_you_join` (yes / likely / unknown) so you only cite alternatives the borrower can realistically obtain. This is what turns a percentile into something the user can act on — prefer it whenever the user asks whether their rate is fair or what to do about it.
  • include_nearby_offers · boolean · optionnel
    Set true with zip to return product-matched rates from credit unions ranked by the closest NCUA-reported branch. Results include approximate straight-line miles, branch details, and the basis-point difference versus the quote.

  Exemple d'appel

  {"name": "rate_sanity_check", "arguments": {"rate": 1, "state": "texte", "product_type": "auto_loan"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "quote": {}, "state": "texte", "market": {}, "share_url": "texte", "percentile": 1, "product_type": "texte", "better_offers": [], "nearby_offers": [], "product_floor": 1, "classification": "texte", "compared_against": "texte"}}

• refinance_break_even≈ 1154 tokens

  Tell a borrower whether refinancing is worth it. Compares their current rate against the best real market offer and returns monthly savings, lifetime savings, and break-even months. Use for 'should I refinance?' questions.

  Paramètres, retour & exemple (7)

  Paramètres

  • state · string · requis
    US state code
  • balance · number · requis
    Current loan balance in dollars
  • term_months · number · requis
    Remaining or new term in months
  • credit_score · number · optionnel
    Optional borrower credit score
  • current_rate · number · requis
    Borrower's current interest rate, e.g. 7.25
  • product_type · string · requis
    mortgage | auto | heloc | personal_loan | student_loan
  • closing_costs · number · optionnel
    Lender fees / closing costs in dollars (default 0)

  Exemple d'appel

  {"name": "refinance_break_even", "arguments": {"state": "texte", "balance": 1, "term_months": 1, "current_rate": 1, "product_type": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"state": "texte", "reason": "texte", "best_lender": "texte", "disclosures": [], "current_rate": "texte", "next_actions": [], "product_type": "texte", "closing_costs": "texte", "monthly_savings": "texte", "assumed_defaults": {}, "best_market_rate": "texte", "lifetime_savings": "texte"}}

• remove_campaign_recipient≈ 196 tokens

  Remove one recipient from a campaign by recipient id.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Campaign id. Required.
  • recipient_id · string · requis
    Recipient id. Required.

  Exemple d'appel

  {"name": "remove_campaign_recipient", "arguments": {"id": "texte", "recipient_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"success": true}}

• resolve_eligibility_entities≈ 778 tokens

  Resolve up to 50 typed organization names for canonical eligibility input. Only one exact normalized active-publication match with confidence of at least 0.8 is authoritative (`resolved`); a lower-confidence exact match remains `unresolved`, multiple exact matches are `ambiguous`, and prefix candidates are suggestions only. Never convert an unresolved, ambiguous, or suggested candidate into a person fact. Resolution identifies an organization and never establishes eligibility.

  Paramètres, retour & exemple (2)

  Paramètres

  • inputs · array · requis
    Typed values to resolve in stable input order.
  • candidate_limit · integer · optionnel
    Maximum exact matches or prefix suggestions returned per input.

  Exemple d'appel

  {"name": "resolve_eligibility_entities", "arguments": {"inputs": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": [], "semantics": "texte", "disclosure": "texte", "resolution_method": "texte", "prefix_candidates_are_suggestions": true}}

• revoke_share≈ 186 tokens

  Revoke a hosted shareable report link by its token. Once revoked, the public URL returns a 404 and no longer exposes the report. This action cannot be undone.

  Paramètres, retour & exemple (1)

  Paramètres

  • token · string · requis
    The share token to revoke. Required.

  Exemple d'appel

  {"name": "revoke_share", "arguments": {"token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"success": true}}

• save_cohort≈ 533 tokens

  Save a named cohort ("book of business") — a list of borrower scenarios you want to track and re-scan over time. Each member has a label and a scenario (product_type, state, intent, amount, term_months, optional credit_score and current_offer). Returns the created cohort. Use scan_portfolio later to re-price every member against the live market.

  Paramètres, retour & exemple (2)

  Paramètres

  • name · string · requis
    Cohort name, e.g. "Q2 refi prospects". Required.
  • members · array · requis
    List of cohort members (max ~50).

  Exemple d'appel

  {"name": "save_cohort", "arguments": {"name": "texte", "members": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "members": [], "lastScan": {}, "createdAt": "texte", "updatedAt": "texte"}}

• save_scenario≈ 370 tokens

  Save a rate comparison for a named client so it can be recalled later (a lightweight CRM for loan officers). Pass the client label and the inputs/results you want to keep.

  Paramètres, retour & exemple (3)

  Paramètres

  • input · object · requis
    The scenario inputs (product, amount, state, term, etc.)
  • client_name · string · requis
    Client/scenario label, e.g. "Smith — $400k purchase, CA"
  • result_snapshot · ? · requis
    The comparison result to store (object from get_financing_decision/compare_products)

  Exemple d'appel

  {"name": "save_scenario", "arguments": {"input": {}, "client_name": "texte", "result_snapshot": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "input": {}, "createdAt": "texte", "clientName": "texte", "resultSnapshot": "texte"}}

• scan_portfolio≈ 576 tokens

  Re-scan every member of a saved cohort against the live decision engine to find each member's current best offer. Returns a triage list (label, best lender, best APR, monthly payment, optional savings vs current) and a diff vs the previous scan (who's new, whose best lender changed, APR deltas). Persists the new snapshot. Use this to refresh a book of business and surface what changed.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Cohort id to scan. Required.

  Exemple d'appel

  {"name": "scan_portfolio", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"triage": [], "changed": [], "scanned": 1}}

• scan_savings≈ 946 tokens

  Scan a list of existing debts and find, for EACH debt, the best qualifying market refinance offer. Returns a ranked "savings stack" with monthly and lifetime savings (net of typical closing costs) per debt plus whether refinancing is worth it, and overall totals. Use this to find refinance opportunities across a borrower's whole debt portfolio.

  Paramètres, retour & exemple (3)

  Paramètres

  • debts · array · requis
    List of existing debts to evaluate for refinancing.
  • state · string · requis
    US state code (2-letter, e.g., TX). Required.
  • credit_score · number · optionnel
    Borrower's credit score (300-850). Recommended for accurate matching.

  Exemple d'appel

  {"name": "scan_savings", "arguments": {"debts": [], "state": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"stack": [], "state": "texte", "totals": {}}}

• schedule_digest≈ 385 tokens

  Set up a recurring digest: on a cadence (default weekly), automatically re-scan a saved cohort and EMAIL the loan officer a triage of which clients have a new opportunity (best lender changed, crossed a threshold). Turns a one-time portfolio scan into a standing operation. Requires a cohort_id (from save_cohort/list_cohorts) and a delivery email.

  Paramètres, retour & exemple (3)

  Paramètres

  • email · string · requis
    Where to send the digest.
  • cadence · string · optionnel
    weekly (default) or daily.
  • cohort_id · string · requis
    The cohort to scan on a schedule (from list_cohorts).

  Exemple d'appel

  {"name": "schedule_digest", "arguments": {"email": "texte", "cohort_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "email": "texte", "cadence": "texte", "enabled": true, "cohort_id": "texte", "created_at": "texte"}}

• search_docs≈ 536 tokens

  DOCS: search the RateAPI documentation (authentication, rate limits and pricing, coverage, freshness, methodology, eligibility, endpoint map, product parameters, errors, the MCP server itself, and the rules for quoting the data). Use this whenever the question is about the API rather than about a rate — "how do I authenticate?", "what does rate_phase mean?", "which endpoint gives deposit APYs?", "how fresh is this?", "what does it cost?" — instead of guessing at parameters or inventing endpoints. Returns ranked pages with an excerpt; call get_doc for the full text. This tool NEVER returns rates.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · number · optionnel
    Maximum pages to return (1-12). Defaults to 5.
  • query · string · requis
    What you want to know about the API, in plain words (e.g. "oauth", "how fresh are rates", "429 error").

  Exemple d'appel

  {"name": "search_docs", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "count": 1, "query": "texte", "results": []}}

• search_eligibility_entities≈ 1096 tokens

  Browse or search canonical employers, associations, schools, or worship organizations that appear in positive conditions in current active eligibility publications. Omit query to browse by active-publication graph connectivity; that order is NOT popularity, quality, or a recommendation. With query, normalized exact matches rank before bounded prefix matches. A returned organization is a selectable fact, NOT proof that this person can join any credit union; use resolve_eligibility_entities for authoritative selection, then pass the returned org_id in the matching *_org_ids field to an eligibility tool. This authenticated discovery never loads a client-side corpus and accepts no personal profile.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum results; the response discloses truncation.
  • query · string · optionnel
    Optional organization name or prefix, 2-120 characters. Omit to browse by active-publication connectivity.
  • types · array · optionnel
    Exact public organization types to search. Omit for all four types.

  Exemple d'appel

  {"name": "search_eligibility_entities", "arguments": {"limit": 1, "query": "texte", "types": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "types": [], "results": [], "semantics": "texte", "disclosure": "texte", "result_mode": "texte", "result_limit": 1, "query_truncated": true, "normalized_query": "texte", "results_truncated": true}}

• send_campaign_now≈ 317 tokens

  Send a campaign to ALL of its recipients immediately (one full send, the same path the daily cron uses). The campaign must be active. Honors suppressions and the per-org daily cap, resets the cadence clock (the next scheduled send counts from now), and is guarded against double-fires. Returns { run_id, sent, suppressed, failed }.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Campaign id. Required.

  Exemple d'appel

  {"name": "send_campaign_now", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sent": 1, "failed": 1, "run_id": "texte", "suppressed": 1}}

• send_test_campaign≈ 222 tokens

  Send a one-off test render of a campaign (with live rates and the org's branding) to the organization owner's email. Does not affect the campaign schedule.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Campaign id. Required.

  Exemple d'appel

  {"name": "send_test_campaign", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "message": "texte"}}

• set_email_branding≈ 640 tokens

  Set the organization's white-label email branding: display name (used as the From name and CAN-SPAM advertiser identity), brand color (#hex), default intro text, business_address (CAN-SPAM physical address — required before a campaign can be activated), and reply_to_email. Requires a Pro plan. (Logo upload is app-only — not available over MCP.)

  Paramètres, retour & exemple (6)

  Paramètres

  • intro_text · string · optionnel
    Default intro paragraph for campaign emails.
  • brand_color · string · optionnel
    Accent color as a #hex string (e.g. #00b368).
  • display_name · string · optionnel
    The lender/brand name shown as the email sender and advertiser.
  • reply_to_email · string · optionnel
    Optional Reply-To address for campaign emails.
  • business_address · string · optionnel
    Physical mailing address of the advertiser (CAN-SPAM).
  • logo_background_color · string · optionnel
    Solid backdrop behind the logo in the email header, as a 6-digit #hex (e.g. #0d1b2a). Useful when the logo is white. Omit or null for the white default.

  Exemple d'appel

  {"name": "set_email_branding", "arguments": {"intro_text": "texte", "brand_color": "texte", "display_name": "texte", "reply_to_email": "texte", "business_address": "texte", "logo_background_color": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"branding": {}}}

• simulate_decision≈ 1011 tokens

  Run a what-if sweep over a financing decision. Holds a scenario fixed while sweeping one input (credit_score, down_payment_percent, or rate_shift_bps) across a from/to/step range, returning a grid of best_lender / best_apr / monthly_payment at each value plus any flip_points where the winning lender changes. Use this to show how rate eligibility or affordability changes with credit score, down payment, or a market rate shift.

  Paramètres, retour & exemple (2)

  Paramètres

  • sweep · object · requis
    The input to sweep and its range.
  • scenario · object · requis
    The fixed financing scenario.

  Exemple d'appel

  {"name": "simulate_decision", "arguments": {"sweep": {}, "scenario": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"grid": [], "state": "texte", "flip_points": [], "sweep_field": "texte", "product_type": "texte"}}

• simulate_monitor≈ 772 tokens

  Test a monitor with a simulated rate change to see if it would trigger. No webhook is sent. It is not a pure dry run: the simulation IS recorded, as a monitor_evaluations row (and a webhook audit row) flagged is_simulation = 1, so it appears in the monitor's history clearly marked as a simulation. It does not touch the monitor's cooldown or last_triggered_at. Use deliver_test_webhook to actually send a test webhook.

  Paramètres, retour & exemple (2)

  Paramètres

  • monitor_id · string · requis
    The unique identifier of the monitor to simulate. Required.
  • rate_change · object · requis
    The simulated rate change event. Required.

  Exemple d'appel

  {"name": "simulate_monitor", "arguments": {"monitor_id": "texte", "rate_change": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "summary": "texte", "evaluation": {}, "rate_change": {}, "would_trigger": true}}

• subscribe_rate_alert≈ 1135 tokens

  Subscribe a consumer to an EMAIL rate alert: notify them when the live market meets their target (rate/apr/monthly_payment crossing a threshold). Consent-first — sends a double-opt-in confirmation email; the alert only activates after the recipient confirms. One-click unsubscribe in every email (CAN-SPAM). Stores only email + alert criteria. Provide exactly one of state, states, or region.

  Paramètres, retour & exemple (10)

  Paramètres

  • email · string · requis
    Consumer email address to send the alert to. Required.
  • state · string · optionnel
    Legacy single US state code (2-letter, e.g., CA, TX, NY). Prefer states or region for multi-state alerts.
  • amount · number · optionnel
    Loan amount in dollars. Optional.
  • intent · string · requis · purchase | refinance | cash_out | balance_transfer | new_credit
    The loan intent. Required.
  • region · string · optionnel · east_coast | west_coast | midwest | south | northeast | southeast | southwest | mountain_west
    Named region preset (e.g. east_coast); expands server-side to its member states.
  • states · array · optionnel
    2-letter US state codes (up to 25) — best rates are ranked ACROSS all of them, not per state.
  • target · object · requis
    The condition that triggers the alert. Required.
  • term_months · number · optionnel
    Loan term in months (12-480). Optional.
  • credit_score · number · optionnel
    Credit score (300-850). Optional.
  • product_type · string · requis · mortgage | auto_loan | rv | boat | motorcycle | powersports | heloc | personal_loan
    Type of loan product. Required.

  Exemple d'appel

  {"name": "subscribe_rate_alert", "arguments": {"email": "texte", "intent": "purchase", "target": {}, "product_type": "mortgage"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"email": "texte", "state": "texte", "states": [], "status": "texte", "target": {}, "message": "texte", "alert_id": "texte", "disclosures": [], "next_actions": [], "region_preset": "texte", "assumed_defaults": {}}}

• unsubscribe_rate_alert≈ 199 tokens

  One-click unsubscribe via the per-alert token embedded in every email.

  Paramètres, retour & exemple (1)

  Paramètres

  • token · string · requis
    The unsubscribe token from the email. Required.

  Exemple d'appel

  {"name": "unsubscribe_rate_alert", "arguments": {"token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "alert_id": "texte"}}

• update_email_campaign≈ 808 tokens

  Update a campaign's name, geography, cadence, intro override, products, or status. products (if given) is the full replacement set (1-5, same union as create_email_campaign). Any geography field replaces the campaign's whole state selection. Set status 'active' to start sending (requires branding display_name + business_address) or 'paused' to stop. Provide exactly one of state_code, state_codes, or region.

  Paramètres, retour & exemple (9)

  Paramètres

  • id · string · requis
    Campaign id. Required.
  • name · string · optionnel
  • region · string · optionnel · east_coast | west_coast | midwest | south | northeast | southeast | southwest | mountain_west
    Named region preset (e.g. east_coast); expands server-side to its member states.
  • status · string · optionnel · active | paused
  • cadence · string · optionnel · daily | weekly | monthly
  • products · array · optionnel
    Full replacement product set (1-5, no duplicates); same shapes as create_email_campaign.
  • state_code · string · optionnel
    Legacy single 2-letter US state code. Prefer state_codes or region.
  • state_codes · array · optionnel
    2-letter US state codes (up to 25) — best rates are ranked ACROSS all of them, not per state.
  • intro_text_override · string · optionnel

  Exemple d'appel

  {"name": "update_email_campaign", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "status": "texte", "cadence": "texte", "products": [], "created_at": 1, "state_code": "texte", "updated_at": 1, "last_run_at": 1, "state_codes": [], "product_type": "texte", "region_preset": "texte"}}

• update_monitor≈ 570 tokens

  Update an existing monitor. Only provided fields will be updated.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · string · optionnel
    New name for the monitor.
  • status · string · optionnel · active | paused | disabled
    New status for the monitor.
  • conditions · array · optionnel
    New array of conditions.
  • monitor_id · string · requis
    The unique identifier of the monitor to update. Required.
  • webhook_url · string · optionnel
    New webhook URL.
  • cooldown_hours · number · optionnel
    New cooldown period in hours (1-168).

  Exemple d'appel

  {"name": "update_monitor", "arguments": {"monitor_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "monitor": {}, "summary": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.rateapi.dev/mcp