AutoGPT Search API

The search API from AutoGPT — 1 operation(s) for search.

Operations 1

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/autogpt-search-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

autogpt-search-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: AutoGPT Agent Server Search API
  summary: AutoGPT Agent Server
  description: This server is used to execute agents that are created by the AutoGPT system.
  version: '0.1'
tags:
- name: Search
paths:
  /api/search/global:
    get:
      tags:
      - Search
      summary: Global search
      operationId: getSearchGlobal search
      security:
      - HTTPBearerJWT: []
      parameters:
      - name: q
        in: query
        required: false
        schema:
          type: string
          maxLength: 512
          description: Free-form search query (semantic + lexical). When empty or omitted, the endpoint returns the most-recently-updated items per bucket instead.
          default: ''
          title: Q
        description: Free-form search query (semantic + lexical). When empty or omitted, the endpoint returns the most-recently-updated items per bucket instead.
      - name: per_type_limit
        in: query
        required: false
        schema:
          type: integer
          maximum: 10
          minimum: 1
          description: Maximum items returned per bucket. The response contains *at most* this many agents, files, and chats — fewer when the bucket has no/few matches.
          default: 4
          title: Per Type Limit
        description: Maximum items returned per bucket. The response contains *at most* this many agents, files, and chats — fewer when the bucket has no/few matches.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GlobalSearchResponse'
        '401':
          $ref: '#/components/responses/HTTP401NotAuthenticatedError'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  responses:
    HTTP401NotAuthenticatedError:
      description: Authentication required
      content:
        application/json:
          schema:
            type: object
            properties:
              detail:
                type: string
  schemas:
    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
    SearchResultItem:
      properties:
        id:
          type: string
          title: Id
        type:
          type: string
          enum:
          - library_agent
          - store_agent
          - workspace_file
          - chat_session
          title: Type
        title:
          type: string
          title: Title
        subtitle:
          anyOf:
          - type: string
          - type: 'null'
          title: Subtitle
        metadata:
          additionalProperties: true
          type: object
          title: Metadata
        score:
          anyOf:
          - type: number
          - type: 'null'
          title: Score
        updated_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Updated At
      type: object
      required:
      - id
      - type
      - title
      title: SearchResultItem
      description: 'One row in a /search/global bucket.


        Kept intentionally generic so the frontend can render all three

        buckets through a single component. Type-specific details live in

        ``metadata`` (e.g. mime_type for files, creator for store agents).'
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    GlobalSearchResponse:
      properties:
        agents:
          items:
            $ref: '#/components/schemas/SearchResultItem'
          type: array
          title: Agents
        files:
          items:
            $ref: '#/components/schemas/SearchResultItem'
          type: array
          title: Files
        chats:
          items:
            $ref: '#/components/schemas/SearchResultItem'
          type: array
          title: Chats
      type: object
      title: GlobalSearchResponse
      description: 'Top-N hits bucketed by item type.


        For a non-empty query this contains hybrid-search results.

        For an empty query this contains the most-recently-updated items

        per bucket (cached per-user with a short TTL).'
  securitySchemes:
    APIKeyAuthenticator-X-Postmark-Webhook-Token:
      type: apiKey
      in: header
      name: X-Postmark-Webhook-Token
    HTTPBearer:
      type: http
      scheme: bearer
    HTTPBearerJWT:
      type: http
      scheme: bearer
      bearerFormat: jwt