com.apievangelist/api-evangelist

Est-ce que com.apievangelist/api-evangelist est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.apievangelist/api-evangelist » 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 68 outils

• api_coverage≈ 244 tokens

  Measure how much of an API description your governance actually inspects — coverage by section, each rule's reach, and the rules that match nothing. Like test coverage, one altitude up.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "api_coverage", "arguments": {"document": {}}}

  Exemple de retour

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

• api_scorecard≈ 260 tokens

  Score an API's maturity 0-100 with a letter grade across design, governance coverage, documentation, and (from an apis.json) discoverability, agent-readiness, and operations. Pass your own `ruleset` — a score against rules you never adopted means little.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "api_scorecard", "arguments": {"document": {}}}

  Exemple de retour

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

• apply_overlay≈ 273 tokens

  Apply an OpenAPI Overlay to a document and report what each action matched. Use it for deprecation and migration choreography without forking the contract.

  Paramètres, retour & exemple (3)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • overlay · string|object · requis
    An OpenAPI Overlay document whose actions are applied to `document`.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "apply_overlay", "arguments": {"overlay": {}, "document": {}}}

  Exemple de retour

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

• audit_pipeline≈ 182 tokens

  Score a repository's Spectral CI setup against an 8-point maturity rubric and return a prioritized punch-list. Pass a public `repo` ("owner/name") or `files`.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "audit_pipeline", "arguments": {"context": "texte"}}

  Exemple de retour

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

• certify_api≈ 215 tokens

  Issue a tamper-evident governance certificate attesting an API passed a named ruleset at a profile threshold. A SHA-256 fingerprint lets anyone re-verify it.

  Paramètres, retour & exemple (2)

  Paramètres

  • api · string|object · requis
    The API description being attested or verified. String or parsed object.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "certify_api", "arguments": {"api": {}}}

  Exemple de retour

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

• classify_api_fields≈ 242 tokens

  Inventory the PII, secret, and sensitive fields an OpenAPI exposes, across parameters and request/response schemas. Run this before exposing an API to agents.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "classify_api_fields", "arguments": {"document": {}}}

  Exemple de retour

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

• code_snippets≈ 228 tokens

  Generate runnable curl, JavaScript, and Python samples for every operation, with path params filled in and a realistic body.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "code_snippets", "arguments": {"document": {}}}

  Exemple de retour

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

• company_dimensions≈ 242 tokens

  PRO — a company's investment dimensions, each read AGAINST the measured cohort: the cohort median, mean and max, this company's rank and percentile, and an index where 1.0 is exactly typical. A raw dimension score is unreadable on its own; these are the columns that make it mean something.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Company slug, as find_company_insights returns it, e.g. "jp-morgan-chase".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "company_dimensions", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• company_gaps≈ 183 tokens

  A company's weakest investment dimensions — where it is thin. Pro.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Company slug, as find_company_insights returns it, e.g. "jp-morgan-chase".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "company_gaps", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• company_peers≈ 245 tokens

  PRO — the companies most comparable to this one (same sub-sector where the data supports it, same industry otherwise), each with signal totals and top dimensions. The response says which basis it used.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Company slug, as find_company_insights returns it, e.g. "jp-morgan-chase".
  • limit · integer · optionnel
    How many peers to return, 1-100.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "company_peers", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• company_signals≈ 207 tokens

  PRO — the company's adopted stack entity by entity (services, tools, standards), each with how many companies across the cohort carry it and its radar ring.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Company slug, as find_company_insights returns it, e.g. "jp-morgan-chase".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "company_signals", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• company_whitespace≈ 236 tokens

  PRO — what this company's peers run that it does not, ranked by how many peers carry it. The opening list for a vendor selling into the account.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Company slug, as find_company_insights returns it, e.g. "jp-morgan-chase".
  • limit · integer · optionnel
    How many whitespace rows to return, 1-200.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "company_whitespace", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• deprecation_posture≈ 233 tokens

  Report every deprecated operation and whether it actually announces a sunset. The ones that go quiet are the ones that break consumers.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "deprecation_posture", "arguments": {"document": {}}}

  Exemple de retour

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

• diff_api_versions≈ 255 tokens

  Compare two OpenAPI versions and classify every change as breaking, non-breaking, or an addition — at path, operation, parameter, request-body, and response granularity.

  Paramètres, retour & exemple (3)

  Paramètres

  • new · string|object · requis
    The CANDIDATE version to compare against the baseline. Aliases: `to`, `revision`.
  • old · string|object · requis
    The BASELINE version of the document. Aliases: `from`, `base`.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "diff_api_versions", "arguments": {"new": {}, "old": {}}}

  Exemple de retour

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

• entity_demand≈ 369 tokens

  PRO — THE INVERSION. Every other insights tool runs company -> stack; this one runs stack -> companies: which companies show demand for a given service, tool or standard, broken down by industry. This is the prospecting query — "who should I be selling this to" — and it exists in no report, bundle or page. Returns BOTH the authoritative company count and the companies it can actually name, with the basis difference explained.

  Paramètres, retour & exemple (5)

  Paramètres

  • kind · string · requis · service | tool | standard
    Entity kind: "service", "tool" or "standard".
  • slug · string · requis
    Entity slug or display name — either resolves ("spark" and "Apache Spark" both work).
  • limit · integer · optionnel
    How many named companies to return, 1-500.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • industry · string · optionnel
    Restrict the named companies to one industry.

  Exemple d'appel

  {"name": "entity_demand", "arguments": {"kind": "service", "slug": "texte"}}

  Exemple de retour

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

• export_agent_rules≈ 242 tokens

  Turn a governance ruleset into agent-native guidance — an AGENTS.md block, a system-prompt set, a per-rule remediation pack, and a digest — so agents follow the rules while authoring, not after linting.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • ruleset · object · requis
    A Spectral ruleset to run instead of the catalog default. Score against rules you never adopted means little — pass your own.

  Exemple d'appel

  {"name": "export_agent_rules", "arguments": {"ruleset": {}}}

  Exemple de retour

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

• find_areas≈ 418 tokens

  The 77 focused topic areas of the network (agents, gateways, security, …), each a subsite with its own catalog.

  Paramètres, retour & exemple (8)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_areas", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• find_building_blocks≈ 520 tokens

  Search the governance building blocks by type: guidance (177), rules (617), policies (283), standards (432), strategies (75), schema (11), properties (790), experiences (46), lifecycle (29).

  Paramètres, retour & exemple (9)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • type · string · requis · guidance | rules | policies | standards | strategies | schema | properties | experiences
    Building-block type: guidance, rules, policies, standards, strategies, schema, properties, experiences or lifecycle.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_building_blocks", "arguments": {"type": "guidance"}}

  Exemple de retour

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

• find_company_insights≈ 256 tokens

  Browse profiled companies (Fortune 1000 + API providers) by name; ranked by technology-readiness signal. Free.

  Paramètres, retour & exemple (4)

  Paramètres

  • q · string · optionnel
    Free text matched against company name, e.g. "chase".
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_company_insights", "arguments": {"q": "texte", "page": 1, "limit": 1, "context": "texte"}}

  Exemple de retour

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

• find_conversations≈ 424 tokens

  API Evangelist Conversations — recorded discussions with API practitioners (guest, company, YouTube/SoundCloud links).

  Paramètres, retour & exemple (8)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_conversations", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• find_entities≈ 332 tokens

  Browse the demand-side entity catalog — every service, tool and standard companies are measured against, ranked by how many carry it. Free. This is the left-hand side of the inversion: pick an entity here, then call entity_demand to see WHO.

  Paramètres, retour & exemple (6)

  Paramètres

  • q · string · optionnel
    Substring match on the entity name.
  • kind · string · optionnel · service | tool | standard
    Entity kind: "service", "tool" or "standard".
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • min_companies · integer · optionnel
    Only entities carried by at least this many companies.

  Exemple d'appel

  {"name": "find_entities", "arguments": {"q": "texte", "kind": "service", "page": 1, "limit": 1, "context": "texte", "min_companies": 1}}

  Exemple de retour

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

• find_measured_standards≈ 246 tokens

  The standards bodies API Evangelist has actually MEASURED — repositories, maturity, governance, coalition. Distinct from find_standards, which searches 613 catalog entries describing what a standard IS. Free.

  Paramètres, retour & exemple (3)

  Paramètres

  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_measured_standards", "arguments": {"page": 1, "limit": 1, "context": "texte"}}

  Exemple de retour

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

• find_papers≈ 412 tokens

  API Evangelist papers — single-PDF deep dives on one practice or topic, with outlines.

  Paramètres, retour & exemple (8)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_papers", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• find_posts≈ 441 tokens

  Search or browse 5,100+ API Evangelist stories (2010–present); filter by year or tags.

  Paramètres, retour & exemple (9)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • year · string · optionnel
    Four-digit year; only posts whose date starts with it, e.g. "2024".
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_posts", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "year": "texte", "limit": 1}}

  Exemple de retour

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

• find_related≈ 360 tokens

  Given any doc (type + slug), the most related content across the whole network, ranked by shared-tag relevance (rare, specific tags weigh most). "More like this," across stories, areas, guidance, papers, conversations, and more.

  Paramètres, retour & exemple (5)

  Paramètres

  • slug · string · requis
    Slug of the item to find related content for, within `type`, e.g. "2026-09-29-you-cannot-see-your-own-api-from-the-outside".
  • type · string · requis
    Content type of the item `slug` names — the plural path name: posts, services, solutions, tools, areas, papers, videos, conversations, guidance…, e.g. "posts".
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • types · array · optionnel
    Only return related items of these types, e.g. ["papers","posts"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_related", "arguments": {"slug": "texte", "type": "texte"}}

  Exemple de retour

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

• find_services≈ 452 tokens

  The services API Evangelist offers teams and customers — API strategy, governance, discovery, and evangelism engagements by Kin Lane. The front door to working with API Evangelist. (For the third-party vendor registry, use find_solutions.)

  Paramètres, retour & exemple (8)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_services", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• find_solutions≈ 435 tokens

  The solutions registry — 740+ third-party API services and tools (gateways, portals, testing, monitoring, …) ranked by adoption across the companies API Evangelist tracks.

  Paramètres, retour & exemple (8)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_solutions", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• find_tags≈ 313 tokens

  Browse and rank the network tag taxonomy — every subject tag across 16k+ docs, by frequency or breadth (how many content types use it). Search with q. The map of what API Evangelist covers.

  Paramètres, retour & exemple (5)

  Paramètres

  • q · string · optionnel
    Free text matched against tag labels, e.g. "governance".
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · count | breadth
    "count" (default, most-used first) or "breadth" (spread across the most content types).
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_tags", "arguments": {"q": "texte", "page": 1, "sort": "count", "limit": 1, "context": "texte"}}

  Exemple de retour

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

• find_tools≈ 429 tokens

  The open-source tooling registry — 400+ tools in use across the companies API Evangelist tracks, each with adoption counts and technology-radar placement.

  Paramètres, retour & exemple (8)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_tools", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• find_videos≈ 420 tokens

  The API Evangelist video library — interviews and discussions from across the API space, searchable by transcript.

  Paramètres, retour & exemple (8)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "find_videos", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• find_vocabulary≈ 480 tokens

  The API vocabulary — thousands of resources, actions, personas, domains, schemas, and tags extracted from the API landscape. Filter by category.

  Paramètres, retour & exemple (9)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • category · string · optionnel · resources | actions | personas | domains | schemas | tags
    Vocabulary category: resources, actions, personas, domains, schemas or tags.

  Exemple d'appel

  {"name": "find_vocabulary", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• forge_mcp_tools≈ 236 tokens

  From an OpenAPI, forge an MCP server design, per-operation tools, Agent Skills, an enriched OpenAPI, a server.json, and apis.json properties.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "forge_mcp_tools", "arguments": {"document": {}}}

  Exemple de retour

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

• gate_agent_context≈ 182 tokens

  Choose which operations and fields an API exposes to agents and emit a governed Tyk OpenAPI, an MCP tool manifest, and a Spectral ruleset with PII and secret checks.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "gate_agent_context", "arguments": {"context": "texte"}}

  Exemple de retour

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

• generate_agent_descriptor≈ 183 tokens

  Generate an API's llms.txt and an AGENTS.md consumption contract — base URL, auth, the operation table, deprecated operations to avoid, and usage rules.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "generate_agent_descriptor", "arguments": {"context": "texte"}}

  Exemple de retour

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

• get_area≈ 179 tokens

  One topic area with its related-area graph resolved — walk the network from here.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Area slug, as find_areas returns it, e.g. "agents".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_area", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_building_block≈ 311 tokens

  One building block by type + slug; include=["content"] returns the full body.

  Paramètres, retour & exemple (4)

  Paramètres

  • slug · string · requis
    Building-block slug within `type`, as find_building_blocks returns it, e.g. "access" with type "guidance".
  • type · string · requis · guidance | rules | policies | standards | strategies | schema | properties | experiences
    Building-block type: guidance, rules, policies, standards, strategies, schema, properties, experiences or lifecycle.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • include · array · optionnel
    Pass ["content"] to inline the full body (Pro). Omitted, you get the summary.

  Exemple d'appel

  {"name": "get_building_block", "arguments": {"slug": "texte", "type": "guidance"}}

  Exemple de retour

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

• get_company_insight≈ 196 tokens

  Full demand-side profile for one company: 40-dimension readiness, adopted stack, per-quarter history. Pro.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Company slug, as find_company_insights returns it, e.g. "jp-morgan-chase".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_company_insight", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_contact≈ 158 tokens

  Every way to reach API Evangelist — email, contact form, newsletter, GitHub, social channels, and postal mail.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_contact", "arguments": {"context": "texte"}}

  Exemple de retour

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

• get_conversation≈ 239 tokens

  One conversation with guest detail and media links; include=["content"] returns the writeup.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Conversation slug — date-prefixed, as find_conversations returns it, e.g. "2026-09-01-lukasz-gornicki".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • include · array · optionnel
    Pass ["content"] to inline the full body (Pro). Omitted, you get the summary.

  Exemple d'appel

  {"name": "get_conversation", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_feeds≈ 160 tokens

  The static machine-readable feeds every network site publishes (JSON, APIs.json, zero-auth) — the no-key alternative to this API.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_feeds", "arguments": {"context": "texte"}}

  Exemple de retour

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

• get_guidance_section≈ 307 tokens

  One editorial guidance section as a list: history, technology, business, politics, governance, or evangelism — the six lenses API Evangelist organizes guidance through.

  Paramètres, retour & exemple (4)

  Paramètres

  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • section · string · requis · history | technology | business | politics | governance | evangelism
    Guidance section: history, technology, business, politics, governance or evangelism.

  Exemple d'appel

  {"name": "get_guidance_section", "arguments": {"section": "history"}}

  Exemple de retour

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

• get_overview≈ 214 tokens

  START HERE. What the API Evangelist network offers: sixteen years of API research as searchable stories, 77 topic areas, governance building blocks (guidance, rules, policies, standards, strategies), papers, conversations, and the consulting services Kin Lane offers teams. Returns counts, entry points, and how to engage.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_overview", "arguments": {"context": "texte"}}

  Exemple de retour

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

• get_paper≈ 179 tokens

  One paper with its full outline and purchase/landing URL.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Paper slug, as find_papers returns it, e.g. "change-on-the-agent-surface".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_paper", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_post≈ 238 tokens

  One story by slug (YYYY-MM-DD-slug); include=["content"] returns the full markdown body.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Post slug — date-prefixed, as find_posts returns it, e.g. "2026-09-29-you-cannot-see-your-own-api-from-the-outside".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • include · array · optionnel
    Pass ["content"] to inline the full body (Pro). Omitted, you get the summary.

  Exemple d'appel

  {"name": "get_post", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_service≈ 230 tokens

  Full detail for one service offering by slug; include=["content"] inlines the full pitch.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Service slug, as find_services returns it, e.g. "governance-agent-readiness".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • include · array · optionnel
    Pass ["content"] to inline the full body (Pro). Omitted, you get the summary.

  Exemple d'appel

  {"name": "get_service", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_solution≈ 186 tokens

  One solution from the vendor registry by slug, with its website and adoption count.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Solution (vendor) slug, as find_solutions returns it, e.g. "adobe".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_solution", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_stats≈ 157 tokens

  PRO — catalog intelligence: per-type counts, stories-per-year, and the top tags by reach across the network.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_stats", "arguments": {"context": "texte"}}

  Exemple de retour

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

• get_tag≈ 295 tokens

  One tag with its per-type counts and everything it labels across the whole network (stories, areas, guidance, papers, …). Filter with types.

  Paramètres, retour & exemple (5)

  Paramètres

  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • slug · string · requis
    Tag slug, as find_tags returns it, e.g. "apis".
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • types · array · optionnel
    Only return tagged items of these types, e.g. ["posts"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_tag", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_timeline≈ 315 tokens

  One of the four research timelines in chronological order: api (the moments that shaped web APIs), resources (which digital resources became APIs and when), industries (the industrial history framing API infrastructure), people (the people who made compute and APIs possible).

  Paramètres, retour & exemple (4)

  Paramètres

  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • timeline · string · requis · api | resources | industries | people
    Which timeline: api, resources, industries or people.

  Exemple d'appel

  {"name": "get_timeline", "arguments": {"timeline": "api"}}

  Exemple de retour

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

• get_tool≈ 181 tokens

  One tool from the tooling registry by slug, with its website, adoption count, and radar ring.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Tool slug, as find_tools returns it, e.g. "ajv".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "get_tool", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_video≈ 224 tokens

  One video by slug with its YouTube id; include=["content"] returns the full transcript.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Video slug, as find_videos returns it, e.g. "adam-duvander".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • include · array · optionnel
    Pass ["content"] to inline the full body (Pro). Omitted, you get the summary.

  Exemple d'appel

  {"name": "get_video", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• govern_estate≈ 273 tokens

  PRO — Run the core governance checks across a WHOLE SET of internal APIs and roll them up: per-API score/grade/errors/PII, plus estate aggregates (avg score, grade distribution, APIs with PII/secrets) and a worst-first punch-list of what to fix. Pass `apis` ([{id, document}]) and your own `ruleset`. detail:true adds per-API dimensions.

  Paramètres, retour & exemple (2)

  Paramètres

  • apis · array · requis
    The estate: one entry per API, [{ id, document }]. `document` alone is accepted for a single API.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "govern_estate", "arguments": {"apis": []}}

  Exemple de retour

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

• governance_report≈ 217 tokens

  Turn Spectral findings into a self-contained HTML governance report — severity summary, grouped by rule, framed toward progress.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • results · array|object · requis
    Spectral findings to render. An array, or the `{ results: [...] }` object a run returned.

  Exemple d'appel

  {"name": "governance_report", "arguments": {"results": []}}

  Exemple de retour

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

• guide_topic≈ 233 tokens

  PRO — Curated guide to one API topic (e.g. "gateways", "api governance", "discovery", "agents"). Bundles the matching topic area (with related areas), top guidance, rules, policies, and standards, relevant papers and recent stories, plus the API Evangelist services that can help a team with this topic.

  Paramètres, retour & exemple (2)

  Paramètres

  • topic · string · requis
    The topic to build a guide for.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "guide_topic", "arguments": {"topic": "texte"}}

  Exemple de retour

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

• insights_adoption≈ 272 tokens

  Services, tools, or standards ranked by how many companies adopt them. Free.

  Paramètres, retour & exemple (4)

  Paramètres

  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • type · string · optionnel · service | tool | standard
    What to rank by adoption across the companies: "service" (default), "tool" or "standard".
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "insights_adoption", "arguments": {"page": 1, "type": "service", "limit": 1, "context": "texte"}}

  Exemple de retour

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

• insights_dimensions≈ 232 tokens

  Cross-section ranking of the 40 tracked investment dimensions (AI, cloud, governance, …) by company signal. Free.

  Paramètres, retour & exemple (3)

  Paramètres

  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "insights_dimensions", "arguments": {"page": 1, "limit": 1, "context": "texte"}}

  Exemple de retour

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

• map_api_experience≈ 183 tokens

  Map each REST operation to its MCP tool and Agent Skill — the API -> MCP -> Agent-Skill chain — from an APIs.json, with a free/paid coverage scorecard and a flow map.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "map_api_experience", "arguments": {"context": "texte"}}

  Exemple de retour

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

• mock_payloads≈ 220 tokens

  Generate an example request and success-response payload for every operation from its schema.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "mock_payloads", "arguments": {"document": {}}}

  Exemple de retour

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

• reconcile_waivers≈ 272 tokens

  Reconcile a waivers file against lint output: suppress sanctioned violations and surface the expired, stale, and expiring ones. Returns the effective failing set a build should gate on.

  Paramètres, retour & exemple (3)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • waivers · string|object · requis
    The waivers file to reconcile — sanctioned violations, with expiry.
  • violations · array|object|string · requis
    Lint output to reconcile against the waivers. An array of findings, or the object a linter returned.

  Exemple d'appel

  {"name": "reconcile_waivers", "arguments": {"waivers": {}, "violations": []}}

  Exemple de retour

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

• score_reusability≈ 167 tokens

  Score how reusable a set of APIs is and detect duplication across them — the anti-sprawl view of an estate.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "score_reusability", "arguments": {"context": "texte"}}

  Exemple de retour

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

• search_api_evangelist≈ 562 tokens

  Unified search across the whole network: 5k+ stories, 77 topic areas, 2.5k governance building blocks, papers, conversations, videos, tools, timelines, services, and vocabulary. Filter with types (posts, areas, guidance, rules, policies, standards, strategies, schema, properties, experiences, lifecycle, conversations, videos, papers, services, solutions, tools, timelines, vocabulary).

  Paramètres, retour & exemple (9)

  Paramètres

  • q · string · optionnel
    Free text over title, summary, tags, and body.
  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • sort · string · optionnel · default | title | date
    Order when there is no `q`: "default" (dated content newest first, the rest A-Z), "title" (A-Z) or "date" (newest first). A `q` always orders by relevance.
  • tags · array · optionnel
    Tag slugs; match any by default.
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • match · string · optionnel · any | all
    How multiple `tags` combine: "any" (default, at least one) or "all" (every tag).
  • types · array · optionnel
    Content types to include — plural resource names: posts, services, solutions, tools, areas, papers, videos, conversations, guidance, rules, policies, standards, strategies…, e.g. ["posts","papers"].
  • fields · array · optionnel
    Return only these keys on each record, e.g. ["slug","title","url"].
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "search_api_evangelist", "arguments": {"q": "texte", "page": 1, "sort": "default", "tags": [], "limit": 1, "match": "any"}}

  Exemple de retour

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

• standard_adoption≈ 242 tokens

  How far a standards body actually got: repositories published, how many graduated past unclassified and the resulting share, release cadence, contributor count — with the provenance of every figure and an explicit list of what is NOT measured. Free, because a specification is a public good.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Standards body slug, as find_measured_standards returns it, e.g. "asyncapi".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "standard_adoption", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• standard_coalition≈ 232 tokens

  Who is actually behind a standard: the governing bodies and their membership, the working groups, the member companies, and the named people. Carries the caveats where our machine-readable source disagrees with the body's own published roster. Free.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Standards body slug, as find_measured_standards returns it, e.g. "asyncapi".
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "standard_coalition", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• standard_repositories≈ 258 tokens

  Every repository a standards body publishes, with maturity, stars, forks, open issues and archived status. Free.

  Paramètres, retour & exemple (4)

  Paramètres

  • page · integer · optionnel
    Page number, 1-based (default 1). Use with `limit` to walk a long list.
  • slug · string · requis
    Standards body slug, as find_measured_standards returns it, e.g. "asyncapi".
  • limit · integer · optionnel
    Results per page, 1-100 (default 25).
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.

  Exemple d'appel

  {"name": "standard_repositories", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• submit_api_evangelist_feedback≈ 396 tokens

  Report something wrong with a result: wrong data, a filter that did not filter, a ranking that put off-topic results first, a number you could not reproduce, or an answer that was useless for your task. Free, and the fastest way to get a defect fixed — the support sweep reads the log this lands in. Say what you expected as well as what you got.

  Paramètres, retour & exemple (6)

  Paramètres

  • tool · string · optionnel
    Optional name of the tool that produced it.
  • about · string · optionnel
    Optional slug, area, paper or story the report concerns.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • problem · string · requis
    What was wrong. Be specific — the tool you called, the arguments, and what came back.
  • expected · string · optionnel
    What you expected instead.
  • severity · string · optionnel · wrong | misleading | unhelpful
    wrong = factually incorrect; misleading = correct but reads as something else; unhelpful = right and useless.

  Exemple d'appel

  {"name": "submit_api_evangelist_feedback", "arguments": {"problem": "texte"}}

  Exemple de retour

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

• validate_api≈ 264 tokens

  Lint an OpenAPI, AsyncAPI, Arazzo, or JSON Schema document against the curated best-of-breed ruleset (Spectral) and return the findings. Pass your own `ruleset` to run rules you own instead of the catalog — which is what you should do before gating on anything.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • document · string|object · requis
    The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted.

  Exemple d'appel

  {"name": "validate_api", "arguments": {"document": {}}}

  Exemple de retour

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

• validate_onboarding≈ 217 tokens

  Validate an API Onboarding Descriptor (AID) against the api-commons schema and report which optional sections it fills in.

  Paramètres, retour & exemple (2)

  Paramètres

  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • descriptor · string|object · requis
    An API Onboarding Descriptor (AID) to validate. Aliases: `aid`, `document`.

  Exemple d'appel

  {"name": "validate_onboarding", "arguments": {"descriptor": {}}}

  Exemple de retour

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

• verify_certificate≈ 250 tokens

  Re-verify a governance certificate against the API it attests to. If the API drifted or the certificate was forged, verification fails.

  Paramètres, retour & exemple (3)

  Paramètres

  • api · string|object · requis
    The API description being attested or verified. String or parsed object.
  • context · string · optionnel
    Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
  • certificate · string|object · requis
    The governance certificate to re-verify. Alias: `cert`.

  Exemple d'appel

  {"name": "verify_certificate", "arguments": {"api": {}, "certificate": {}}}

  Exemple de retour

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

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.apievangelist.com/mcp