Agent Health Monitor

AHM Verify API

Post-transaction output-quality scoring: register a job specification (POST /v1/specs, free), submit an agent's delivered output for evaluation by a six-role adversarial Claude panel (POST /v1/outputs, $0.50 USDC per verdict via x402 — a live 402 was observed), and poll the verdict (GET /v1/verdicts/{verdict_id}) for ALLOW / HOLD / REJECT with confidence and findings. Published as OpenAPI 3.1.0 (v0.1.0) at https://verify.agenthealthmonitor.xyz/openapi.json with Swagger UI at /docs and a /health endpoint; separate from the AHS composite.

Documentation GitHub OpenAPI

Operations 4

POST /v1/specs Create Spec #

POST /v1/outputs Submit Output #

GET /v1/verdicts/{verdict_id} Get Verdict #

GET /health Health #

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/ahm-verify-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

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. See our Privacy Policy and Terms.

GitHub Google LinkedIn

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

OpenAPI Specification

openapi: 3.1.0
info:
  title: AHM Verify
  description: Post-transaction output quality scoring via a six-role Claude adjudication panel (D4)
  version: 0.1.0
servers:
- url: https://verify.agenthealthmonitor.xyz
  description: Production
  x-apievangelist-note: 'Added by API Evangelist. The provider-served openapi.json at https://verify.agenthealthmonitor.xyz/openapi.json
    declares no servers[]; the host is the one that serves the spec and its Swagger UI (/docs) and is named as "Live at: verify.agenthealthmonitor.xyz"
    on docs.agenthealthmonitor.xyz. Everything else in this file is the provider spec verbatim, converted from JSON to YAML.'
paths:
  /v1/specs:
    post:
      summary: Create Spec
      description: Register a job specification. Returns spec_id and spec_hash.
      operationId: create_spec_v1_specs_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SpecRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SpecResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/outputs:
    post:
      summary: Submit Output
      description: Submit an agent's output for evaluation. Triggers async panel pipeline.
      operationId: submit_output_v1_outputs_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/OutputRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OutputResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/verdicts/{verdict_id}:
    get:
      summary: Get Verdict
      description: Poll for verdict result. Returns status + full result when completed.
      operationId: get_verdict_v1_verdicts__verdict_id__get
      parameters:
      - name: verdict_id
        in: path
        required: true
        schema:
          type: string
          title: Verdict Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VerdictResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /health:
    get:
      summary: Health
      operationId: health_health_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
components:
  schemas:
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    OutputRequest:
      properties:
        spec_id:
          type: string
          title: Spec Id
          description: UUID of the pre-registered spec
        output_text:
          type: string
          minLength: 1
          title: Output Text
          description: The agent's delivered output text
        submitted_by:
          type: string
          title: Submitted By
          description: 'Who submitted: client, agent, or protocol'
          default: client
        submitter_addr:
          type: string
          title: Submitter Addr
          description: Wallet address of the submitter
        provider_addr:
          type: string
          title: Provider Addr
          description: Wallet address of the agent/provider
        mode:
          type: string
          title: Mode
          description: Evaluation mode. Only 'standard' is implemented — every verdict runs the standard pipeline at $0.50.
          default: standard
      type: object
      required:
      - spec_id
      - output_text
      - submitter_addr
      - provider_addr
      title: OutputRequest
    OutputResponse:
      properties:
        verdict_id:
          type: string
          title: Verdict Id
        status:
          type: string
          title: Status
      type: object
      required:
      - verdict_id
      - status
      title: OutputResponse
    SpecRequest:
      properties:
        client_addr:
          type: string
          title: Client Addr
          description: Wallet address of the client registering the spec
        provider_addr:
          anyOf:
          - type: string
          - type: 'null'
          title: Provider Addr
          description: Intended provider address, if known
        spec_text:
          type: string
          minLength: 1
          title: Spec Text
          description: Task specification / job description
        acceptance_criteria:
          anyOf:
          - type: string
          - type: 'null'
          title: Acceptance Criteria
          description: Pre-registered acceptance criteria
        domain:
          type: string
          title: Domain
          description: Evaluation domain key
          default: default
        erc8183_job_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Erc8183 Job Id
          description: Optional on-chain job ID (hex)
      type: object
      required:
      - client_addr
      - spec_text
      title: SpecRequest
    SpecResponse:
      properties:
        spec_id:
          type: string
          title: Spec Id
        spec_hash:
          type: string
          title: Spec Hash
      type: object
      required:
      - spec_id
      - spec_hash
      title: SpecResponse
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    VerdictResponse:
      properties:
        verdict_id:
          type: string
          title: Verdict Id
        status:
          type: string
          title: Status
        final_verdict:
          anyOf:
          - type: string
          - type: 'null'
          title: Final Verdict
        final_score:
          anyOf:
          - type: integer
          - type: 'null'
          title: Final Score
        confidence:
          anyOf:
          - type: number
          - type: 'null'
          title: Confidence
        mdi:
          anyOf:
          - type: number
          - type: 'null'
          title: Mdi
        on_chain_action:
          anyOf:
          - type: string
          - type: 'null'
          title: On Chain Action
        domain:
          anyOf:
          - type: string
          - type: 'null'
          title: Domain
        met_criteria:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Met Criteria
        unmet_criteria:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Unmet Criteria
        key_objections:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Key Objections
        reasoning:
          anyOf:
          - type: string
          - type: 'null'
          title: Reasoning
        strongest_dissent:
          anyOf:
          - type: string
          - type: 'null'
          title: Strongest Dissent
        generator_majority:
          anyOf:
          - type: string
          - type: 'null'
          title: Generator Majority
        critic_override_applied:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Critic Override Applied
        zero_history_adjustment_applied:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Zero History Adjustment Applied
        rejection_asymmetry_applied:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Rejection Asymmetry Applied
        latency_ms:
          anyOf:
          - type: integer
          - type: 'null'
          title: Latency Ms
        evaluated_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Evaluated At
        error_message:
          anyOf:
          - type: string
          - type: 'null'
          title: Error Message
      type: object
      required:
      - verdict_id
      - status
      title: VerdictResponse