kapa.ai Retrieval API

Semantic retrieval and keyword search.

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/kapa-ai-retrieval-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 email required.

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

OpenAPI Specification

kapa-ai-retrieval-api-openapi.yml Raw ↑
openapi: 3.0.1
info:
  title: kapa.ai Query Analytics Retrieval API
  description: REST API for the kapa.ai answer platform. Ask a project's kapa.ai instance questions and receive retrieval-augmented answers with sources, run threaded multi-turn conversations (standard and streamed), perform semantic retrieval and keyword search against ingested knowledge sources, submit feedback, and read project, integration, source, and analytics data. All requests are authenticated with an X-API-KEY header.
  termsOfService: https://www.kapa.ai/content/terms-of-service
  contact:
    name: kapa.ai Support
    url: https://docs.kapa.ai
  version: '1.0'
servers:
- url: https://api.kapa.ai
  description: kapa.ai production API
security:
- ApiKeyAuth: []
tags:
- name: Retrieval
  description: Semantic retrieval and keyword search.
paths:
  /query/v1/projects/{project_id}/retrieval:
    post:
      operationId: retrieval
      tags:
      - Retrieval
      summary: Retrieval
      description: Semantic retrieval against the project's ingested knowledge sources without LLM generation. Returns the most relevant chunks in descending order of relevance, for use as context for external LLMs and agents.
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RetrievalRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RetrievalResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /query/v1/projects/{project_id}/search:
    get:
      operationId: search
      tags:
      - Retrieval
      summary: Search (deprecated)
      description: Deprecated fast keyword-based search across the project's knowledge sources. Use the retrieval endpoint for semantic search.
      deprecated: true
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      - name: query
        in: query
        required: true
        schema:
          type: string
        description: The search query string.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RetrievalResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
components:
  parameters:
    ProjectId:
      name: project_id
      in: path
      required: true
      description: The kapa.ai project (instance) identifier.
      schema:
        type: string
        format: uuid
  schemas:
    RetrievedChunk:
      type: object
      properties:
        content:
          type: string
        source_url:
          type: string
          format: uri
        title:
          type: string
        score:
          type: number
          format: float
          description: Relevance score in descending order.
    Error:
      type: object
      properties:
        detail:
          type: string
    RetrievalResponse:
      type: object
      properties:
        relevant_sources:
          type: array
          items:
            $ref: '#/components/schemas/RetrievedChunk'
    RetrievalRequest:
      type: object
      required:
      - query
      properties:
        query:
          type: string
          description: The retrieval query.
        num_results:
          type: integer
          description: Maximum number of chunks to return.
  responses:
    Unauthorized:
      description: Missing or invalid X-API-KEY.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-KEY
      description: kapa.ai project API key, created in the API Keys tab of the platform.