io.github.ariffazil/arifosmcp

Est-ce que io.github.ariffazil/arifosmcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.ariffazil/arifosmcp » 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 9 outils

• arif_forge≈ 1678 tokens

  KERNEL 777 · Governed execution: applies a mutation through A-FORGE only when carrying a sealed verdict id (seal_verdict_id) from arif_judge and a live session. The manifest/query defines exactly what changes; mode=dry_run previews the plan without applying it. This is the only verb that executes general mutations — kernel memory writes go to arif_memory and permanent records to arif_seal.Auth: requires session_id + session_token from arif_init plus a sealed verdict id (seal_verdict_id) from arif_judge. Returns: the applied mutation receipt — one of the two committal verbs (with arif_seal).

  Paramètres, retour & exemple (15)

  Paramètres

  • mode · string · optionnel · engineer | query | write | generate | commit | recall | dry_run
    'engineer' (default) — plan and apply the work; 'dry_run' — preview what would happen, nothing is applied; 'query' — read-only questions about the workspace; 'write' — write files; 'generate' — generate code or content; 'commit' — commit prepared work; 'recall' — retrieve past forge artifacts.
  • query · ? · optionnel
    The task in plain language when no manifest is supplied, e.g. 'restart the gateway service'.
  • plan_id · ? · optionnel
    Plan id from arif_think's plan mode, when executing an approved plan.
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log.
  • manifest · string · optionnel
    Required for engineer (the default mode), write, and generate: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=dry_run accepts the manifest or a plain-language query; mode=query uses query instead.
  • session_id · ? · optionnel
    Session id returned by arif_init; scopes this execution to your governed session.
  • arif_ack_id · ? · optionnel
    Acknowledgment id from a prior step, for multi-step execution chains.
  • artifact_id · ? · optionnel
    Id of an existing artifact (from an earlier forge or judge response) that this call operates on.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) returned by arif_init — proves the session is yours.
  • vault_entry_id · ? · optionnel
    Id of the permanent-ledger entry linked to this execution, when one already exists.
  • seal_verdict_id · ? · optionnel
    The SEAL verdict id arif_judge returned — without it, nothing is executed.
  • ack_irreversible · boolean · optionnel
    Set true to confirm you accept this execution cannot be undone, when the judged action was irreversible.
  • judge_state_hash · ? · optionnel
    Hash string from the arif_judge SEAL response — proves the verdict has not been tampered with.
  • approved_action_hash · ? · optionnel
    Hash of the exact action that was judged — execution is refused if what you submit differs from it.
  • constitutional_chain_id · ? · optionnel
    Id of the evidence chain (observe→think→judge) that led to the SEAL — copy it from the judge response.

  Exemple d'appel

  {"name": "arif_forge", "arguments": {"mode": "engineer", "query": "texte", "plan_id": "texte", "actor_id": "texte", "manifest": "texte", "session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "texte"}}

• arif_init≈ 2482 tokens

  KERNEL 000 · Ignite a governed kernel session: binds actor identity, constitutional floors F1–F13, and the audit chain. Returns the session_id + session_token that every other arif_* verb requires. Use mode=preflight to inspect an existing session without re-igniting, mode=resume to continue one. Modes: init, preflight, resume, validate, canary, triage, epoch_open, epoch_seal, light, opt_out.Auth: the only verb needing no session — it mints the session_id + session_token every other verb requires. Returns: session_id, session_token, constitution_hash, allowed_next_tools.

  Paramètres, retour & exemple (28)

  Paramètres

  • mode · string · optionnel · init | light | resume | validate | canary | preflight | triage | epoch_open
    What to do: 'init' (default) starts a new governed session; 'preflight' checks an existing session's state without creating one; 'resume' re-attaches to the session in session_id; 'validate' re-checks credentials; 'canary' is a transport probe; 'triage' reads session state; 'epoch_open'/'epoch_seal' bracket a long working window; 'light' is a minimal session; 'opt_out' records a privacy opt-out.
  • nonce · ? · optionnel
    One-time random string (e.g. a UUID) making this request unique; protects against replay of the same call.
  • intent · string · requis
    Required. Plain-language statement of what this session is for, e.g. 'repair the failing MCP tests'. A session without a stated purpose is refused (F1 Amanah). Recorded for audit.
  • context · ? · optionnel
    JSON object of background facts to bind into the session, e.g. {"repo": "arifOS", "task": "fix-tests"}.
  • payload · ? · optionnel
    Extra mode-specific data as a JSON object; the mode's response tells you which fields it expects.
  • tooling · ? · optionnel
    JSON list of the tools you can use, e.g. ["Bash", "Read"] — lets the kernel scope what it will permit you. Also accepts an object like {"requested_capabilities": [...]}.
  • verbose · ? · optionnel
    Legacy on/off verbosity ('true'/'false'); prefer verbosity.
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
  • epoch_id · ? · optionnel
    Optional id grouping related sessions into one long-running epoch, e.g. '2026-H2-ops'.
  • evidence · ? · optionnel
    JSON list of facts you have already verified, e.g. [{"fact": "pytest 299 passed", "source": "CI run"}] — carried into the session record. Also accepts a single object.
  • trace_id · ? · optionnel
    Correlation id of your choosing (e.g. 'req-8f3a') — lets you find this call later across kernel logs and organ systems.
  • verbosity · string · optionnel · minimal | standard | full
    How detailed responses should be: 'minimal' (default), 'standard', or 'full'.
  • session_id · ? · optionnel
    Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
  • agent_policy · ? · optionnel
    JSON constraints on your own behavior, e.g. {"autonomy": "reversible_only", "forbidden": ["git push"]}.
  • auth_context · ? · optionnel
    JSON carrying external authentication material, e.g. {"token_class": "bearer", "issuer": "github"} — used for gating.
  • counterparty · ? · optionnel
    JSON describing the other party in a two-agent exchange, e.g. {"agent_id": "hermes/1", "role": "verifier"}.
  • sovereign_id · ? · optionnel
    Identifier of the human principal you act for, when acting under their explicit delegation.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated.
  • actor_signature · ? · optionnel
    Cryptographic signature over the request, if your agent holds a key — proves the call genuinely came from actor_id. Omit if you have no key.
  • caller_actor_id · ? · optionnel
    If you are calling on behalf of another agent, that agent's id — builds a delegation chain for the audit log.
  • delegation_mode · ? · optionnel
    Contract governing delegated calls, e.g. 'read_only' or 'governed'.
  • idempotency_key · ? · optionnel
    Client-chosen key (e.g. 'job-42-attempt-1'). Retrying with the same key will not repeat the effect — safe retries on flaky networks.
  • ack_irreversible · boolean · optionnel
    Set true to acknowledge that session records are permanent audit artifacts and cannot be deleted afterwards.
  • executor_actor_id · ? · optionnel
    Id of the agent that will actually carry out work under this session's permissions, if different from actor_id.
  • declared_model_key · ? · optionnel
    The model you run on, e.g. 'zai-coding-plan/glm-5.3'. Informational only — the kernel records but never trusts it.
  • client_capabilities · ? · optionnel
    JSON declaring what your client supports, e.g. {"transports": ["http"], "protocol": "2025-11-25"}.
  • requested_authority · string · optionnel
    The highest class of action you may take: 'OBSERVE_ONLY' (read-only, default) or a higher governed class granted by your policy.
  • previous_session_hash · ? · optionnel
    Hash string returned when your previous session closed; supplying it chains this session to that one, proving continuity.

  Exemple d'appel

  {"name": "arif_init", "arguments": {"intent": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "texte"}}

• arif_judge≈ 2542 tokens

  KERNEL 666 · Binding constitutional arbitration: evaluates a candidate action or claim and returns SEAL / HOLD / SABAR / VOID with the full reason chain. Weighs action class, blast radius, reversibility, entropy pathway, and cooling state; a SEAL verdict here is what arif_forge requires before it will execute anything. Judge arbitrates — it does not gather (evidence comes via arif_observe, reasoning via arif_think) and it does not mutate (execution is arif_forge, permanence is arif_seal). Modes: judge, intercept, validate, hold, escalate.Auth: requires session_id + session_token from arif_init. Returns: verdict (SEAL/HOLD/SABAR/VOID) with the full reason chain — arbitration only, it does not mutate.

  Paramètres, retour & exemple (31)

  Paramètres

  • mode · string · optionnel · intercept | judge | validate | hold | escalate
    'judge' (default) — render a verdict on candidate; 'intercept' — pre-flight gate before an action runs; 'validate' — re-check a prior verdict; 'hold' — place an action into a cooling period; 'escalate' — refer the decision to the human owner.
  • nonce · ? · optionnel
    One-time random string (e.g. a UUID) making this request unique; protects against replay of the same call.
  • domain · ? · optionnel
    Subject area for claim evaluation, e.g. 'geoscience' or 'finance'.
  • key_id · ? · optionnel
    Which of your registered keys produced actor_signature, e.g. 'key-1'.
  • actor_B · ? · optionnel
    Your calibrated confidence for a prediction, 0.0–1.0 (Brier-style score component).
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
  • evidence · ? · optionnel
    The facts the verdict should rest on — a JSON list like [{"fact": "tests pass", "source": "CI"}], or an object.
  • actor_Phi · ? · optionnel
    JSON map of supporting signals about you, e.g. {"consistency": 0.9, "track_record": 0.7}.
  • candidate · ? · optionnel
    The action or claim being judged, stated plainly, e.g. 'delete table users in prod'.
  • claim_text · ? · optionnel
    The exact claim sentence under judgment, e.g. 'uptime exceeded 99% in August'.
  • session_id · ? · optionnel
    Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
  • action_tier · string · optionnel
    How risky the action is: 'standard', 'high', or 'critical' — higher tiers demand stronger evidence.
  • claim_class · ? · optionnel
    Epistemic strength of the claim: 'OBS' (directly observed), 'DER' (derived from observations), 'INT' (interpreted), 'SPEC' (speculative), 'UNKNOWN' (cannot witness — honest null; maps to TruthClass.UNK, weight 0.30, cannot authorize mutation). RULE absence-null: 'not in my knowledge' is NOT evidence a claim is false — label UNKNOWN, never FALSE.
  • niat_params · ? · optionnel
    JSON intent-calibration settings, e.g. {"sincerity": 0.8, "stated_goal": "verify the claim"}.
  • action_class · ? · optionnel
    Kind of action under judgment: 'OBSERVE' (read-only), 'DRAFT' (compose text), 'MUTATE' (change state), 'IRREVERSIBLE' (permanent).
  • blast_radius · ? · optionnel
    Who or what the action can affect: 'self', 'session', 'organ', or 'federation'.
  • seal_purpose · ? · optionnel
    One sentence saying why this verdict/record must exist, e.g. 'closing deployment D-17'. Stored permanently alongside the record.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated.
  • context_source · ? · optionnel
    Where the candidate came from: 'session', 'file', or 'memory'.
  • heart_critique · ? · optionnel
    JSON result of an ethics/dignity check, e.g. {"coercion": false, "dignity": 0.9} — feeds the verdict.
  • vault_entry_id · ? · optionnel
    Id of the permanent-ledger entry this verdict should attach to (from an earlier arif_seal response).
  • actor_signature · ? · optionnel
    Cryptographic signature over the request, if your agent holds a key — proves the call genuinely came from actor_id. Omit if you have no key.
  • authority_token · ? · optionnel
    Authority credential CLAIMED for this proposal (payload field, not proof). The judge records the claim and still verifies identity separately — an unverified token never upgrades an OBSERVE_ONLY session, and verdicts remain binding regardless of what the token asserts.
  • entropy_pathway · ? · optionnel
    How the action changes system order: 'reduces', 'neutral', or 'increases' complexity.
  • entropy_receipt · ? · optionnel
    JSON receipt from an entropy computation, bound to this judgment.
  • authority_effect · ? · optionnel
    What permission a SEAL verdict would grant, e.g. 'execute forge plan P-9'.
  • cooldown_entry_id · ? · optionnel
    Id of an existing cooling-period record to consult before this action may proceed.
  • sovereign_receipt · ? · optionnel
    Reference to the human owner's explicit approval, for the rare case where they have already decided directly.
  • reversibility_level · ? · optionnel
    How hard the action would be to undo: 'reversible', 'hard', or 'irreversible'.
  • requested_capability · ? · optionnel
    The specific capability being requested, e.g. 'forge.execute' — checked against the capability registry.
  • constitutional_chain_id · ? · optionnel
    Id of the evidence chain this call belongs to (observe→think→judge→seal). Copy it from the earlier step's response to link the steps together.

  Exemple d'appel

  {"name": "arif_judge", "arguments": {"mode": "intercept", "nonce": "texte", "domain": "texte", "key_id": "texte", "actor_B": "texte", "actor_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "texte"}}

• arif_memory≈ 1446 tokens

  KERNEL 555 · Governed memory of the kernel itself: six tiers (L1–L6) with per-mode gating. recall, inspect, and audit are read paths; remember, revise, promote, and forget mutate tiers — promote and forget additionally require human_approval=true. Use for cross-session lessons, canon, and memory audit; external evidence belongs to arif_observe and reasoning artifacts to arif_think. Modes: recall, inspect, attest, remember, promote, revise, forget, audit, metabolize.Auth: requires session_id + session_token from arif_init. Returns: memory entries by tier (L1–L6); promote and forget gates require explicit human approval.

  Paramètres, retour & exemple (15)

  Paramètres

  • mode · string · optionnel · recall | inspect | attest | remember | promote | revise | forget | audit
    'recall' (default) — semantic search of stored memories; 'inspect' — read one memory in full; 'attest' — vouch for a memory's accuracy; 'remember' — store new text; 'promote' — move a memory up a tier; 'revise' — replace a memory's text; 'forget' — remove a memory (gated); 'audit' — integrity scan; 'metabolize' — compact and consolidate tiers.
  • tier · ? · optionnel
    Which memory tier to target, 'L1'–'L6' (L1 = hot working memory, L6 = sealed canon).
  • query · ? · optionnel
    What to search for, in plain language (mode=recall/audit), e.g. 'past deploy rollback steps'.
  • content · ? · optionnel
    The text to store (mode=remember) — write it as a self-contained lesson or fact.
  • payload · ? · optionnel
    Extra mode-specific fields as JSON — e.g. {"truth_class": "DERIVED", "provenance": "CI log"} for remember.
  • to_tier · ? · optionnel
    Destination tier when promoting, e.g. 'L4'.
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log.
  • lease_id · ? · optionnel
    Id of a short-lived permission grant (lease) authorizing this write, when one was issued to you.
  • trace_id · ? · optionnel
    Correlation id of your choosing (e.g. 'req-8f3a') to find this call later in the logs.
  • memory_id · ? · optionnel
    UUID of the memory entry to inspect/revise/forget — it was returned when the memory was created or last listed.
  • session_id · ? · optionnel
    Session id returned by arif_init; attributes this call to your governed session.
  • new_content · ? · optionnel
    Replacement text for the memory (mode=revise) — must refer to the same memory_id.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) returned by arif_init — proves the session is yours.
  • human_approval · boolean · optionnel
    Set true ONLY when the human owner explicitly approved this promote/forget — the gate refuses without it.
  • idempotency_key · ? · optionnel
    Client-chosen key (e.g. 'memo-42'); retries with the same key will not store duplicates.

  Exemple d'appel

  {"name": "arif_memory", "arguments": {"mode": "recall", "tier": "texte", "query": "texte", "content": "texte", "payload": "texte", "to_tier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "texte"}}

• arif_observe≈ 1274 tokens

  KERNEL 111 · Collect evidence — facts and sources with epistemic tags (OBS) and uncertainty bounds, never conclusions. mode=search queries the open web/literature; mode=fetch retrieves a URL and records its provenance; mode=vitals reads kernel machine telemetry. Reason over what you gathered with arif_think; delegate domain analysis to an organ with arif_route. Modes: search, fetch, hybrid_discovery, ingest, compass, atlas, entropy_dS, vitals.Auth: requires session_id + session_token from arif_init. Returns: evidence items with epistemic tags (OBS) and uncertainty bounds — facts, never conclusions.

  Paramètres, retour & exemple (8)

  Paramètres

  • url · ? · optionnel
    Exact URL to retrieve when mode=fetch, e.g. 'https://example.com/report.pdf'.
  • mode · string · optionnel · search | fetch | hybrid_discovery | ingest | compass | atlas | entropy_dS | vitals
    'search' (default) — web/literature query; 'fetch' — retrieve one URL with provenance; 'hybrid_discovery' — combine sources; 'ingest' — absorb a document; 'compass'/'atlas' — guided navigation; 'entropy_dS' — measure system change; 'vitals' — kernel machine telemetry.
  • query · ? · optionnel
    What to look for, in plain language, e.g. 'TDQS scoring rubric MCP'.
  • layers · ? · optionnel
    Restrict where to look, e.g. ["web"] or ["canon", "memory"]; omit to search everything available.
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
  • session_id · ? · optionnel
    Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
  • result_limit · integer · optionnel
    Maximum number of results to return in search modes; default 10.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated.

  Exemple d'appel

  {"name": "arif_observe", "arguments": {"url": "texte", "mode": "search", "query": "texte", "layers": "texte", "actor_id": "texte", "session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "texte"}}

• arif_report≈ 485 tokens

  AGENT REPORT LANE · File or read reports between agents without involving the human. Use when your work is done, when you are blocked by another agent, or when you need to tell peers a fact. modes: report (file), inbox (read peers), ack, flush, stats. kind=fyi|peer|done|claim stay in the peer lane; ONLY kind=decision or kind=blocked reach the sovereign, and only in one coalesced message. Reports are SELF_REPORTED — probe before relying on one.

  Paramètres, retour & exemple (19)

  Paramètres

  • body · ? · optionnel
  • kind · string · optionnel
  • mode · string · optionnel
  • force · boolean · optionnel
  • limit · integer · optionnel
  • since · ? · optionnel
  • sender · ? · optionnel
  • dry_run · boolean · optionnel
  • subject · ? · optionnel
  • actor_id · ? · optionnel
  • evidence · ? · optionnel
  • platform · ? · optionnel
  • _envelope · ? · optionnel
  • mark_read · boolean · optionnel
  • report_id · ? · optionnel
  • thread_id · ? · optionnel
  • session_id · ? · optionnel
  • needs_human · ? · optionnel
  • session_token · ? · optionnel

  Exemple d'appel

  {"name": "arif_report", "arguments": {"body": "texte", "kind": "texte", "mode": "texte", "force": true, "limit": 1, "since": "texte"}}

  Exemple de retour

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

• arif_route≈ 1339 tokens

  KERNEL 444 · Intent→organ router: classifies a natural-language intent and dispatches it to the specialist organ (GEOX geoscience, WEALTH capital, WELL vitality, A-FORGE execution). Returns the routing decision only — no organ call — unless organ_tool names the target tool and arguments carries its inputs. Prefer this over guessing organs yourself; use arif_think for reasoning you keep in-kernel.Auth: requires session_id + session_token from arif_init. Returns: the routing decision (organ + tool) only — the organ call itself is a separate step.

  Paramètres, retour & exemple (11)

  Paramètres

  • mode · ? · optionnel
    'route' (default) — classify intent and recommend the target organ; 'triage' — rank a batch of intents; 'delegate' — prepare an A2A handoff; 'status' — surface organ state; 'kernel' — kernel-level status; 'metabolize' — feed routing outcomes to arifFlow. Routing only recommends — execution is arif_forge after a SEAL verdict.
  • task · ? · optionnel
    Alias for intent (backward compat).
  • organ · ? · optionnel
    Optional explicit organ override. If provided, intent matching is skipped and this organ is used directly.
  • intent · ? · optionnel
    Natural-language description of what the user wants. e.g. "interpret this seismic section", "assess portfolio risk"
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
  • arguments · ? · optionnel
    Arguments to pass to organ_tool.
  • mission_id · ? · optionnel
    Explicit human-cockpit mission binding (investigate|interpret| decide|build|monitor|remember). When set, skips keyword classification and binds the six-mission plan. Preferred over free-text when the agent already knows the mission.
  • organ_tool · ? · optionnel
    The tool name on the target organ to call. If absent, returns routing decision only (no bridge call).
  • session_id · ? · optionnel
    Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated.
  • contract_c_kwargs · ? · optionnel
    Extra keyword arguments passed through to the organ tool call, as a JSON object.

  Exemple d'appel

  {"name": "arif_route", "arguments": {"mode": "texte", "task": "texte", "organ": "texte", "intent": "texte", "actor_id": "texte", "arguments": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "texte"}}

• arif_seal≈ 1705 tokens

  KERNEL 999 · Append an entry to VAULT999, the immutable ledger — accepted entries can never be edited or removed; there is no unseal. Use for permanent records of verified outcomes, lessons, and session closure once a verdict exists. ack_irreversible=true is the explicit acknowledgment of permanence, and judge_state_hash binds the entry to the verdict that authorized it. Reversible changes belong in arif_forge under a SEAL. Modes: seal, verify, ledger, changelog, audit, session_close.Commit projection: seven of the eight verbs are reversible or informational and project their outcomes onto the two committal verbs — arif_forge (governed mutation) and arif_seal (permanence). Auth: requires session_id + session_token from arif_init. Returns: the immutable ledger entry id — append-only, there is no unseal.

  Paramètres, retour & exemple (14)

  Paramètres

  • mode · string · optionnel · seal | verify | ledger | changelog | audit | session_close
    'seal' (default) — append a permanent entry; 'verify' — check one entry; 'ledger' — read the ledger head; 'changelog' — recent appends; 'audit' — integrity check; 'session_close' — close out a session into the ledger.
  • nonce · ? · optionnel
    One-time random string (e.g. a UUID) making this request unique; protects against replay of the same call.
  • payload · string · requis
    The content to store forever, as a string (usually JSON-serialized) — the outcome, lesson, or record itself. Required for the write modes (seal, session_close); pure reads (verify, ledger, changelog, audit) may omit it.
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
  • session_id · ? · optionnel
    Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
  • drift_events · ? · optionnel
    JSON list of deviations observed, e.g. [{"what": "schema drift", "where": "tools/list"}] — stored with the record.
  • seal_purpose · ? · optionnel
    One sentence saying why this verdict/record must exist, e.g. 'closing deployment D-17'. Stored permanently alongside the record.
  • witness_type · string · optionnel
    Who witnessed the sealed fact: 'ai', 'human', or 'external' system.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated.
  • constitutional · ? · optionnel
    JSON block of governance metadata (floors consulted, chain references) — normally built by the kernel, not by callers.
  • actor_signature · ? · optionnel
    Cryptographic signature over the request, if your agent holds a key — proves the call genuinely came from actor_id. Omit if you have no key.
  • ack_irreversible · boolean · optionnel
    Set true to confirm you understand sealed entries are PERMANENT — they can never be edited or removed.
  • judge_state_hash · ? · optionnel
    Hash string from the arif_judge SEAL response — ties this entry to the verdict that authorized it.
  • constitutional_chain_id · ? · optionnel
    Id of the evidence chain this call belongs to (observe→think→judge→seal). Copy it from the earlier step's response to link the steps together.

  Exemple d'appel

  {"name": "arif_seal", "arguments": {"payload": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "texte"}}

• arif_think≈ 1264 tokens

  KERNEL 333 · Structured reasoning pass: decomposes a query and returns reasoning steps labeled OBS (observed), DER (derived), INT (interpretation), SPEC (specification) under truth floors. Produces reasoning records only — no verdicts (those come from arif_judge) and no state changes. The plan-family modes draft/review/approve execution plans; simulate and wonder explore counterfactuals. Modes: reason, reflect, verify, axioms, plan, plan_review, plan_approve, refactor_plan, metabolize, simulate, wonder, atlas.Auth: requires session_id + session_token from arif_init. Returns: reasoning steps labelled OBS/DER/INT/SPEC — records only; verdicts belong to arif_judge.

  Paramètres, retour & exemple (8)

  Paramètres

  • mode · string · optionnel · reason | reflect | verify | axioms | plan | plan_review | plan_approve | refactor_plan
    'reason' (default) — decompose a question; 'reflect' — self-review of prior reasoning; 'verify' — check a derivation; 'axioms' — surface hidden assumptions; 'plan'/'plan_review'/'plan_approve'/'refactor_plan' — execution-plan lifecycle; 'metabolize' — consolidate past reasoning; 'simulate' — what-if; 'wonder' — open exploration; 'atlas' — map the problem space.
  • query · ? · optionnel
    The question, claim, or problem to reason about, in plain language.
  • context · ? · optionnel
  • plan_id · ? · optionnel
    Plan reference from an earlier plan-mode response — needed for the review/approve/refactor steps.
  • actor_id · ? · optionnel
    Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
  • session_id · ? · optionnel
    Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
  • witness_type · string · optionnel
    Who vouches for the reasoning record: 'ai' (default), 'human', or 'external' system.
  • session_token · ? · optionnel
    Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated.

  Exemple d'appel

  {"name": "arif_think", "arguments": {"mode": "reason", "query": "texte", "context": "texte", "plan_id": "texte", "actor_id": "texte", "session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": {}, "tool": "texte", "result": {}, "status": "texte", "delta_S": "texte", "reasons": [], "actor_id": "texte", "timestamp": "texte", "session_id": "texte", "nine_signal": {}, "output_policy": "texte", "stage_progression": "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://arifosmcp.arif-fazil.com/mcp