Mnemom Reputation API

Per-agent reputation scores.

GitHub OpenAPI

Operations 10

POST /reputation/batch Batch reputation lookup (auth required) #
GET /reputation/benchmarks Aggregate reputation benchmarks #
GET /reputation/compare Compare 2–10 agents' reputation scores #
GET /reputation/search Search the public reputation directory #
GET /reputation/{agent_id} Get reputation score for an agent #
GET /reputation/{agent_id}/badge.svg Embeddable SVG reputation badge #
GET /reputation/{agent_id}/events List recent reputation events #
GET /reputation/{agent_id}/history Get weekly reputation snapshots #
GET /reputation/{agent_id}/og-image Open Graph share-card image for an agent #
GET /reputation/{agent_id}/verify Cryptographic verification bundle for an agent's reputation #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/mnemom-ai:mnemom-ai-reputation-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

mnemom-ai-reputation-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Mnemom Reputation API
  description: Trust infrastructure for AI agents. Transparent alignment verification, behavioral drift detection, and accountability primitives.
  version: 1.0.0
  contact:
    name: Mnemom
    url: https://mnemom.ai
    email: support@mnemom.ai
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://api.mnemom.ai/v1
  description: Production
security:
- BearerAuth: []
- ApiKeyAuth: []
tags:
- name: Reputation
  description: Per-agent reputation scores.
paths:
  /reputation/batch:
    post:
      operationId: batchReputation
      x-proxied: REPUTATION_SERVICE
      summary: Batch reputation lookup (auth required)
      description: 'Returns reputation rows for up to 50 agent ids. Requires API key or bearer JWT (rate-limited as `search_batch` — 30/min per auth principal). Private-visibility agents return a stub row with `score: null`.'
      tags:
      - Reputation
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - agent_ids
              properties:
                agent_ids:
                  type: array
                  items:
                    type: string
                  maxItems: 50
                  minItems: 0
      responses:
        '200':
          description: Scores (private rows return stubs).
          content:
            application/json:
              schema:
                type: object
                required:
                - scores
                properties:
                  scores:
                    type: array
                    items:
                      oneOf:
                      - $ref: '#/components/schemas/ReputationScore'
                      - type: object
                        properties:
                          agent_id:
                            type: string
                          visibility:
                            type: string
                            enum:
                            - private
                          score:
                            type: 'null'
                          grade:
                            type: 'null'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/CrossOriginRejected'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/benchmarks:
    get:
      operationId: getReputationBenchmarks
      x-proxied: REPUTATION_SERVICE
      summary: Aggregate reputation benchmarks
      description: Returns mean/median/p25/p75/p90 score and a grade-distribution histogram across every eligible agent. Cached. Public, rate-limited (`benchmarks` bucket).
      tags:
      - Reputation
      security: []
      responses:
        '200':
          description: Benchmark stats.
          content:
            application/json:
              schema:
                type: object
                required:
                - total_eligible
                - mean_score
                - median_score
                - p25_score
                - p75_score
                - p90_score
                - grade_distribution
                properties:
                  total_eligible:
                    type: integer
                  mean_score:
                    type: number
                  median_score:
                    type: number
                  p25_score:
                    type: number
                  p75_score:
                    type: number
                  p90_score:
                    type: number
                  grade_distribution:
                    type: object
                    additionalProperties:
                      type: integer
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/compare:
    get:
      operationId: compareReputation
      x-proxied: REPUTATION_SERVICE
      summary: Compare 2–10 agents' reputation scores
      description: Returns the reputation rows for the given agent ids (comma-separated, 2–10). Private-visibility agents are silently filtered out. Public endpoint, cached 5 min.
      tags:
      - Reputation
      security: []
      parameters:
      - name: ids
        in: query
        required: true
        schema:
          type: string
        description: Comma-separated list of 2–10 agent ids.
      responses:
        '200':
          description: Comparison result.
          content:
            application/json:
              schema:
                type: object
                required:
                - agents
                properties:
                  agents:
                    type: array
                    items:
                      $ref: '#/components/schemas/ReputationScore'
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/search:
    get:
      operationId: searchReputationDirectory
      x-proxied: REPUTATION_SERVICE
      summary: Search the public reputation directory
      description: Lists agents whose reputation visibility is `public`, with optional filters. `q` matches on agent name (or `smolt-`/`mnm-` ID prefix). Unclaimed, not-rated (NR) agents appear at the bottom when the filters permit. Page-based pagination.
      tags:
      - Reputation
      security: []
      parameters:
      - name: q
        in: query
        required: false
        schema:
          type: string
        description: Name search (ilike) or agent-id prefix match.
      - name: grade
        in: query
        required: false
        schema:
          type: string
        description: Filter to one grade (e.g. `AAA`, `B`, `NR`).
      - name: confidence
        in: query
        required: false
        description: Filter to agents at a given reputation-confidence level (driven by how much evidence backs the score).
        schema:
          type: string
          enum:
          - high
          - medium
          - low
          - insufficient
      - name: sort
        in: query
        required: false
        description: Result ordering. Default "score" (highest-rated first); other supported keys order by recency or name.
        schema:
          type: string
          default: score
      - name: page
        in: query
        required: false
        description: 1-based page number for pagination. Default 1.
        schema:
          type: integer
          minimum: 1
          default: 1
      - name: per_page
        in: query
        required: false
        description: Number of results per page. 1–100, default 20.
        schema:
          type: integer
          minimum: 1
          maximum: 100
          default: 20
      responses:
        '200':
          description: Directory page.
          content:
            application/json:
              schema:
                type: object
                required:
                - agents
                - total
                - page
                - per_page
                properties:
                  agents:
                    type: array
                    items:
                      $ref: '#/components/schemas/ReputationScore'
                  total:
                    type: integer
                  page:
                    type: integer
                  per_page:
                    type: integer
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/{agent_id}:
    get:
      operationId: getReputation
      x-proxied: REPUTATION_SERVICE
      summary: Get reputation score for an agent
      description: 'Returns the agent''s current reputation: numeric score (0–1000), letter grade (AAA–D, NR for not-rated), tier, five-component breakdown, 30-day trend, and an A2A trust extension block for interop. Private-visibility agents return 403 to non-owners. Public endpoint, IP-rate-limited (lookup bucket).'
      tags:
      - Reputation
      security: []
      parameters:
      - $ref: '#/components/parameters/AgentId'
      responses:
        '200':
          description: Reputation score with A2A trust extension.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ReputationScore'
        '400':
          $ref: '#/components/responses/BadRequest'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/{agent_id}/badge.svg:
    get:
      operationId: getReputationBadge
      x-proxied: REPUTATION_SERVICE
      summary: Embeddable SVG reputation badge
      description: Returns an SVG image (image/svg+xml) showing the agent's grade + score, suitable for embedding in GitHub README files, docs, or dashboards. Public, rate-limited (`badge` bucket).
      tags:
      - Reputation
      security: []
      parameters:
      - $ref: '#/components/parameters/AgentId'
      responses:
        '200':
          description: SVG badge.
          content:
            image/svg+xml:
              schema:
                type: string
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/{agent_id}/events:
    get:
      operationId: getReputationEvents
      x-proxied: REPUTATION_SERVICE
      summary: List recent reputation events
      description: Returns up to 50 most-recent reputation events (violation detected, card amendment, reclassification applied, etc). Public endpoint.
      tags:
      - Reputation
      security: []
      parameters:
      - $ref: '#/components/parameters/AgentId'
      responses:
        '200':
          description: Recent events.
          content:
            application/json:
              schema:
                type: object
                required:
                - events
                properties:
                  events:
                    type: array
                    items:
                      type: object
                      additionalProperties: true
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/{agent_id}/history:
    get:
      operationId: getReputationHistory
      x-proxied: REPUTATION_SERVICE
      summary: Get weekly reputation snapshots
      description: Returns up to 52 weekly snapshots of the agent's reputation (most recent first). Public endpoint.
      tags:
      - Reputation
      security: []
      parameters:
      - $ref: '#/components/parameters/AgentId'
      responses:
        '200':
          description: Weekly snapshots.
          content:
            application/json:
              schema:
                type: object
                required:
                - snapshots
                properties:
                  snapshots:
                    type: array
                    items:
                      type: object
                      additionalProperties: true
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/{agent_id}/og-image:
    get:
      operationId: getReputationOgImage
      x-proxied: REPUTATION_SERVICE
      summary: Open Graph share-card image for an agent
      description: Returns a 1200×630 PNG (or rendered HTML fallback) suitable for `og:image` link previews when the agent's profile is shared.
      tags:
      - Reputation
      security: []
      parameters:
      - $ref: '#/components/parameters/AgentId'
      responses:
        '200':
          description: Share-card image.
          content:
            image/png:
              schema:
                type: string
                format: binary
            text/html:
              schema:
                type: string
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
  /reputation/{agent_id}/verify:
    get:
      operationId: verifyReputation
      x-proxied: REPUTATION_SERVICE
      summary: Cryptographic verification bundle for an agent's reputation
      description: 'Returns the score plus a `verification` block containing: the latest certificate hash, the agent''s Merkle root, checkpoint count, first/last checkpoint timestamps, and a `hash_chain_valid` flag. Response is Cache-Control 3600s. Public endpoint.'
      tags:
      - Reputation
      security: []
      parameters:
      - $ref: '#/components/parameters/AgentId'
      responses:
        '200':
          description: Verification bundle.
          headers:
            Cache-Control:
              schema:
                type: string
                example: public, max-age=3600, s-maxage=3600
          content:
            application/json:
              schema:
                type: object
                required:
                - agent_id
                - score
                - grade
                - computed_at
                - verification
                properties:
                  agent_id:
                    type: string
                  score:
                    type: number
                  grade:
                    type: string
                  computed_at:
                    type: string
                    format: date-time
                  verification:
                    type:
                    - object
                    - 'null'
                    properties:
                      latest_certificate_hash:
                        type:
                        - string
                        - 'null'
                      merkle_root:
                        type:
                        - string
                        - 'null'
                      checkpoint_count:
                        type: integer
                      first_checkpoint:
                        type:
                        - string
                        - 'null'
                        format: date-time
                      last_checkpoint:
                        type:
                        - string
                        - 'null'
                        format: date-time
                      hash_chain_valid:
                        type: boolean
                      certificate_url:
                        type:
                        - string
                        - 'null'
        '400':
          $ref: '#/components/responses/BadRequest'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
components:
  responses:
    Unauthorized:
      description: Authentication required
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    InternalServerError:
      description: Server error — request was well-formed but the server failed to fulfill it. Typically a downstream dependency (DB / RPC / external API) returned an unexpected error.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    TooManyRequests:
      description: Rate-limit exceeded. The global per-IP limiter (100 requests/minute, applied to every `/v1/*` route) rejected this request. Back off until the window resets — `Retry-After` carries the cooldown in seconds and `X-RateLimit-Reset` the absolute reset time.
      headers:
        Retry-After:
          description: Seconds to wait before retrying.
          schema:
            type: integer
            minimum: 1
        X-RateLimit-Limit:
          description: Requests permitted per window.
          schema:
            type: integer
        X-RateLimit-Remaining:
          description: Requests remaining in the current window (0 on a 429).
          schema:
            type: integer
            minimum: 0
        X-RateLimit-Reset:
          description: Unix epoch seconds at which the current window resets.
          schema:
            type: integer
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    CrossOriginRejected:
      description: Cross-origin write refused (`cross_origin_rejected`). A state-changing request that carries the browser session cookie must come from a first-party origin (`Origin`, or failing that `Referer`) and must not send a form-style body (text/plain, urlencoded, multipart) the operation does not declare. Bearer and API-key callers are never subject to this check.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Forbidden:
      description: Forbidden
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    BadRequest:
      description: Bad request
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    NotFound:
      description: Resource not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    ReputationScore:
      type: object
      description: 'Agent reputation row computed by the reputation worker''s 6-hour cron. Grade alphabet: `AAA AA+ AA A+ A B+ B C+ C D NR` (NR = not-rated, insufficient data). Score is an integer 0–1000.'
      required:
      - agent_id
      - score
      - grade
      - is_eligible
      - checkpoint_count
      - confidence
      - components
      - visibility
      properties:
        agent_id:
          type: string
        score:
          type:
          - integer
          - 'null'
          minimum: 0
          maximum: 1000
        grade:
          type:
          - string
          - 'null'
          description: AAA–D or NR.
        tier:
          type:
          - string
          - 'null'
        is_eligible:
          type: boolean
        checkpoint_count:
          type: integer
        checkpoint_accounting:
          type:
          - object
          - 'null'
          description: Structured breakdown of how checkpoints were counted toward the score. `analyzed` is the scoring population; `excluded` buckets are mutually exclusive and `analyzed + synthetic + insufficient_thinking + quarantined + analysis_failed + integrity_off = total` (`analysis_failed` is absent, i.e. 0, on scores computed before MNE-9696; `integrity_off` is absent, i.e. 0, on scores computed before MNE-9763, and on those scores integrity-off turns are counted in `insufficient_thinking`). Null for legacy rows computed before this field existed.
          required:
          - total
          - analyzed
          - excluded
          properties:
            total:
              type: integer
              description: All checkpoints recorded for the agent.
            analyzed:
              type: integer
              description: Checkpoints that counted toward the score (drives the X/50 eligibility gauge).
            excluded:
              type: object
              required:
              - synthetic
              - insufficient_thinking
              - quarantined
              properties:
                synthetic:
                  type: integer
                  description: Synthetic (`ic-synthetic-*`) checkpoints.
                insufficient_thinking:
                  type: integer
                  description: 'Zero-analysis checkpoints (no extraction confidence, thinking tokens, or analysis duration) that were attempted: not integrity-off turns, which are counted in `integrity_off`.'
                quarantined:
                  type: integer
                  description: Checkpoints referenced by a non-expired enforce advisory; excluded from scoring entirely.
                analysis_failed:
                  type: integer
                  description: 'Checkpoints whose integrity analysis was attempted but failed (verdict `unverified`: parse error, timeout, analyser unavailable) and that are not already counted in `insufficient_thinking`. Shown as not checked; never evidence, never toward the 50-checkpoint gate.'
                integrity_off:
                  type: integer
                  description: Checkpoints written while integrity analysis was off for the agent (verdict `unanalyzed`). No analysis was attempted, so they are neither a failure nor insufficient thinking. Never evidence, never toward the 50-checkpoint gate. Absent (treat as 0) on scores computed before MNE-9763.
            re_evaluated:
              type: object
              description: How many of the agent's checkpoints carry each kind of re-evaluation annotation (counted over `total`, not the analyzed subset). Observability only — these are not an exclusion bucket and do not enter the score arithmetic. Absent on scores computed before this breakdown existed.
              required:
              - corrected_clear
              - corrected_non_clear
              - resolved_no_correction
              properties:
                corrected_clear:
                  type: integer
                  description: Checkpoints explicitly corrected to `clear` (`re_evaluation_metadata.corrected_verdict = 'clear'`).
                corrected_non_clear:
                  type: integer
                  description: Checkpoints corrected to a NON-clear verdict — a cross-turn escalation or a reviewer reclassification to `review_needed`/`boundary_violation`. These count against the score per the correction, not as exonerations; a non-zero value is why this agent's score differs from the pre-MNE-2156 calculation.
                resolved_no_correction:
                  type: integer
                  description: Checkpoints re-evaluated with NO recorded correction — the trust-recovery convention, scored as `clear`.
        confidence:
          type: string
          enum:
          - insufficient
          - low
          - medium
          - high
        components:
          type: array
          items:
            type: object
            required:
            - key
            - score
            - weight
            - weighted_score
            properties:
              key:
                type: string
                enum:
                - integrity_ratio
                - compliance
                - drift_stability
                - trace_completeness
                - coherence_compatibility
              label:
                type: string
              score:
                type: number
              weight:
                type: number
              weighted_score:
                type: number
              factors:
                type: array
        computed_at:
          type:
          - string
          - 'null'
          format: date-time
        next_compute_at:
          type:
          - string
          - 'null'
          format: date-time
          description: Next scheduled recompute — the 00/06/12/18 UTC cron slot strictly after `computed_at` (`floor(computed_at/6h)*6h + 6h`). Null when `computed_at` is null.
        trend_30d:
          type:
          - number
          - 'null'
        visibility:
          type: string
          enum:
          - public
          - private
          description: Reputation-publication axis — whether this agent's Trust Rating is published. Every registered agent's reputation is `public` by accountability standard (the default; that is the whole point of a portable, verifiable rating); `private` is a rare owner opt-out that 403s the read to non-owners. This is DISTINCT from `Agent.public` (the identity-record visibility axis) — they share the word "public" but govern different things.
        claimed:
          type: boolean
        agent_name:
          type:
          - string
          - 'null'
        a2a_trust_extension:
          type: object
          description: A2A trust extension for interop. Only present on `GET /reputation/{agent_id}` (not on batch/compare rows).
          properties:
            extension_uri:
              type: string
            provider:
              type: string
            score:
              type: number
            grade:
              type: string
            confidence:
              type: string
            verified_url:
              type: string
              format: uri
            badge_url:
              type: string
              format: uri
            methodology_url:
              type: string
              format: uri
            last_updated:
              type: string
              format: date-time
    Error:
      type: object
      description: Canonical error envelope (ADR-API-001 conv 1). `error` is always an object — never a bare string. Every 4xx/5xx response across the API conforms to this shape; the runtime helper is `src/http-errors.ts::buildErrorBody`.
      required:
      - error
      properties:
        error:
          type: object
          required:
          - code
          - message
          properties:
            code:
              type: string
              pattern: ^[a-z][a-z0-9_]*$
              description: 'Stable, machine-matchable failure identifier (lowercase snake_case). Clients may branch on this; the string is part of the contract.


                **Status-class defaults** — emitted when no caller code is supplied (`errorCodeForStatus(status)`): `bad_request` (400), `unauthorized` (401), `forbidden` (403), `not_found` (404), `method_not_allowed` (405), `conflict` (409), `gone` (410), `precondition_failed` (412), `payload_too_large` (413), `unsupported_media_type` (415), `unprocessable_entity` (422), `precondition_required` (428), `rate_limited` (429), `internal_error` (500), `not_implemented` (501), `bad_gateway` (502), `service_unavailable` (503), `gateway_timeout` (504). Fallback `error` for unmapped statuses.


                **Caller-supplied codes** — handlers may pass an explicit `code` for a specific failure class. Examples: `agent_not_found`, `invalid_hash_proof`, `already_linked`, `idempotency_conflict`, `feature_gated`, `schema_validation_failed`, `no_token`, `bad_canonical_payload`.


                **Care-framed sub-resource codes** — the cards-as-primitive surface passes its stable care code-string straight through as `error.code`. Examples: `if_match_absent`, `if_match_stale`, `if_match_malformed`, `primitive_validation_failed`.'
            message:
              type: string
              description: Human-readable, care-framed explanation of the failure.
            details:
              description: 'Optional structured context for the failure (any JSON value: object, array, or primitive). Common shapes: validation findings list, idempotency-conflict diff, `{presented_etag, current_etag}` on a stale `If-Match`, etc. Mirrors the helper''s `details?: unknown`.'
  parameters:
    AgentId:
      name: agent_id
      in: path
      required: true
      schema:
        type: string
      description: Agent identifier (e.g. smolt-abc123)
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: 'Supabase JWT token in Authorization: Bearer header'
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-Mnemom-Api-Key
      description: Mnemom API key (mnm_... format)
    ServiceRole:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Supabase service role bearer JWT. Used by /blog admin operations that talk directly to Supabase. NOT used by /internal/* or /v1/arena/internal/* — those use the custom-header schemes below.
    InternalKeyAuth:
      type: apiKey
      in: header
      name: X-Internal-Key
      description: Internal service-to-service shared secret, timing-safe compared against INTERNAL_API_KEY. Used by /internal/* gateway routes (compose, agents, webhooks emit).
    ServiceKeyAuth:
      type: apiKey
      in: header
      name: X-Service-Key
      description: Service-to-service shared secret, timing-safe compared against MNEMOM_SERVICE_KEY. Used by /v1/arena/internal/*, /v1/on-chain/*, and the /v1/internal/* readers consumed by the reputation cron.
    CoherenceTokenAuth:
      type: http
      scheme: bearer
      description: Per-cell coherence bearer token. Provisioned in 1Password vault `mnemom-coherence` (one item per receiver). Value compared against COHERENCE_<NAME>_SERVICE_TOKEN_EXPECTED. Used by /v1/internal/coherence/* and /v1/internal/governance/dispatch.
    ArenaCandidateTokenAuth:
      type: http
      scheme: bearer
      description: Dedicated arena writer token (ADR-004 §"Arena dedicated writer token"). Compared against ARENA_RECIPE_CANDIDATE_TOKEN. The token's only capability is writing recipe candidates with writer_identity='arena-bypass' (stamped server-side). Used by POST /v1/internal/recipe-candidates.
    CustomerVoiceTokenAuth:
      type: http
      scheme: bearer
      description: Customer Voice API bearer token. Timing-safe compared against CUSTOMER_VOICE_API_TOKEN. Grants access to all /v1/internal/feedback/* endpoints (MNE-1876). No customer-facing or reporter-read capability.
    CookieAuth:
      type: apiKey
      in: cookie
      name: mnemom_session
      description: 'HttpOnly, Secure, SameSite=Lax cookie issued by /v1/auth/sign-in (or the SSO / email-callback flows). The value is an AES-256-GCM-encrypted blob of {access_token, refresh_token, issued_at, auth_method}. Browser clients include this automatically with `credentials: "include"`.'
    LicenseJwtAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: License JWT (HS256, HMAC-signed with LICENSE_SIGNING_SECRET). Used by self-hosted deployment instances to authenticate `/v1/deployments/heartbeat`. Not interchangeable with the Supabase user JWT.
    AgentAuth:
      type: apiKey
      in: header
      name: X-Mnemom-Agent-Proof
      description: 'Agent possession proof: the full SHA-256 hex digest of `${apiKey}|${agentName}` (or `${apiKey}` for an unnamed singleton agent) — the same `hash_proof` primitive used by POST /v1/agents claim, link-agent, and verify-binding. The server resolves the agent by `agent_hash = proof[:16]`. The agent''s *own* identity (ADR-API-001 third auth class) — distinct from ApiKeyAuth (`X-Mnemom-Api-Key`, which resolves a user/account, not an agent).'