Anchord AI Guard API

The Guard API from Anchord AI — 2 operation(s) for guard.

Operations 2

POST /v1/guard/write Decide whether a proposed write is allowed #
POST /v1/guard/write:batch Batch guard checks (max 200) #

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/anchord-ai:anchord-ai-guard-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.

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

OpenAPI Specification

anchord-ai-guard-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: AnchorID Guard API
  version: 1.0.0
  description: 'Anchord''s multi-tenant identity resolution + safe-write gate (v1). Read-only — never writes back to external systems. Guard/write endpoints are evaluation-only: they return a decision, the caller executes.'
servers:
- url: https://api.anchord.ai/api
  description: Production
- url: https://staging.api.anchord.ai/api
  description: Staging (testing environment)
security:
- bearerAuth: []
tags:
- name: Guard
paths:
  /v1/guard/write:
    post:
      tags:
      - Guard
      summary: Decide whether a proposed write is allowed
      description: 'Evaluation-only. Pass an entity_id; the guard checks link confidence, conflict state, and merge status. Returns allowed: true/false with block codes. Never writes to external systems.'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - entity_id
              properties:
                entity_id:
                  type: string
                  format: uuid
                min_confidence:
                  type: number
                  minimum: 0
                  maximum: 1
                  default: 0.7
                  description: Minimum link confidence required (default 0.70).
                require_no_conflicts:
                  type: boolean
                  default: true
                  description: Block if unresolved conflicts exist (default true).
            examples:
              basic:
                summary: Check if a write is safe
                value:
                  entity_id: 9b1deb4d-3b7d-4bad-9bdd-2b0d7b3dcb6d
              with_threshold:
                summary: Lower confidence threshold
                value:
                  entity_id: 9b1deb4d-3b7d-4bad-9bdd-2b0d7b3dcb6d
                  min_confidence: 0.5
                  require_no_conflicts: false
      responses:
        '200':
          description: Guard decision.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GuardWriteResponse'
        '400':
          description: Bad request.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      operationId: postV1GuardWrite
      x-operation-id-source: derived
  /v1/guard/write:batch:
    post:
      tags:
      - Guard
      summary: Batch guard checks (max 200)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - items
              properties:
                items:
                  type: array
                  maxItems: 200
                  items:
                    type: object
                    required:
                    - client_ref
                    - entity_id
                    properties:
                      client_ref:
                        type: string
                        maxLength: 255
                      entity_id:
                        type: string
                        format: uuid
                      min_confidence:
                        type: number
                        minimum: 0
                        maximum: 1
                      require_no_conflicts:
                        type: boolean
      responses:
        '200':
          description: Batch guard decisions.
          content:
            application/json:
              schema:
                type: object
                required:
                - results
                - request_id
                properties:
                  results:
                    type: array
                    items:
                      $ref: '#/components/schemas/GuardBatchResult'
                  request_id:
                    type: string
        '400':
          description: Bad request.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Batch too large (max 200).
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      operationId: postV1GuardWrite:batch
      x-operation-id-source: derived
components:
  schemas:
    EntityRef:
      type: object
      required:
      - id
      - kind
      properties:
        id:
          type: string
          format: uuid
        kind:
          $ref: '#/components/schemas/EntityKind'
    GuardBatchResult:
      type: object
      required:
      - client_ref
      - allowed
      - blocks
      properties:
        client_ref:
          type: string
        allowed:
          type: boolean
        entity_id:
          type: string
          format: uuid
        entity:
          anyOf:
          - $ref: '#/components/schemas/EntityRef'
          - type: 'null'
        blocks:
          type: array
          items:
            type: string
        confidence:
          type: number
          minimum: 0
          maximum: 1
          nullable: true
        active_links:
          type: integer
        audit_id:
          type: string
          format: uuid
        redirect:
          type: object
          properties:
            code:
              type: string
            requested_entity_id:
              type: string
              format: uuid
            canonical_entity_id:
              type: string
              format: uuid
    EntityKind:
      type: string
      enum:
      - company
      - person
    GuardWriteResponse:
      type: object
      required:
      - audit_id
      - allowed
      - blocks
      - request_id
      properties:
        audit_id:
          type: string
          format: uuid
        allowed:
          type: boolean
        entity_id:
          type: string
          format: uuid
          nullable: true
          description: The entity that was evaluated.
        entity:
          anyOf:
          - $ref: '#/components/schemas/EntityRef'
          - type: 'null'
        blocks:
          type: array
          items:
            type: string
          description: 'Block codes when allowed is false. Possible values: ENTITY_NOT_FOUND, NO_CANONICAL_LINK, CONFIDENCE_BELOW_THRESHOLD, UNRESOLVED_CONFLICTS.

            '
        confidence:
          type: number
          minimum: 0
          maximum: 1
          nullable: true
        active_links:
          type: integer
          description: Count of active entity links at evaluation time.
        redirect:
          description: Present when the requested entity has been merged. Evaluation was performed against the canonical entity.
          type: object
          properties:
            code:
              type: string
              enum:
              - ENTITY_REDIRECTED_TO_CANONICAL
            requested_entity_id:
              type: string
              format: uuid
            canonical_entity_id:
              type: string
              format: uuid
        request_id:
          type: string
    ErrorResponse:
      type: object
      required:
      - error
      - request_id
      properties:
        error:
          type: object
          required:
          - code
          - message
          properties:
            code:
              type: string
            message:
              type: string
            details:
              type: object
              additionalProperties: true
        request_id:
          type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer