Klu

Klu Actions API

Run Actions to generate completions.

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/klu-ai-actions-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

klu-ai-actions-api-openapi.yml Raw ↑
openapi: 3.0.1
info:
  title: Klu Actions API
  description: 'REST API for the Klu (klu.ai) LLM app platform. The Klu Engine runs Actions - each encapsulating a prompt template, model config, context (RAG), and output parsing - against input variables to generate completions, and manages the data, feedback, sessions, models, apps, and workspaces around them. Authentication is via a Bearer API key obtained from the workspace API Keys settings.

    NOTE - Endpoints under the Actions, Context, and Apps/Workspaces paths reflect the publicly documented Klu API reference and SDK surface. Where the public docs document a capability via the SDK but do not publish the exact REST path, this spec models the conventional resource path used by the Klu Engine; see review.yml for which operations are documented verbatim versus inferred from the SDK.'
  termsOfService: https://klu.ai/terms
  contact:
    name: Klu Support
    url: https://help.klu.ai/
  version: '1.0'
servers:
- url: https://api.klu.ai/v1
  description: Klu Engine production API
security:
- bearerAuth: []
tags:
- name: Actions
  description: Run Actions to generate completions.
paths:
  /actions:
    post:
      operationId: runAction
      tags:
      - Actions
      summary: Run an Action
      description: Executes a Klu Action by GUID against the provided input, returning the generated completion and a feedback URL containing the data point GUID. Supports streaming, async execution, response caching, session memory, context metadata filtering, and experiments.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RunActionRequest'
      responses:
        '200':
          description: Generation result.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RunActionResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
components:
  responses:
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    RateLimited:
      description: Too many requests.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    RunActionResponse:
      type: object
      properties:
        msg:
          type: string
          description: The generated completion text.
        feedback_url:
          type: string
          description: URL containing the data point GUID for submitting feedback on this generation.
        stream_url:
          type: string
          description: Token streaming endpoint, present when streaming is enabled.
        data_guid:
          type: string
          description: GUID of the data point recorded for this generation.
    RunActionRequest:
      type: object
      required:
      - action
      - input
      properties:
        action:
          type: string
          description: GUID of the Action to run.
        input:
          description: Input string, or an object of key-value variable pairs for the prompt template.
          oneOf:
          - type: string
          - type: object
            additionalProperties: true
        streaming:
          type: boolean
          description: Stream the response token by token.
          default: false
        async_mode:
          type: boolean
          description: Execute asynchronously and return a generation GUID to retrieve results later.
          default: false
        cache:
          type: boolean
          description: Return a cached response when an equivalent generation is available.
          default: false
        session:
          type: string
          description: Session GUID to use for conversational context.
        metadata_filter:
          type: object
          additionalProperties: true
          description: Filter Context documents by metadata attributes.
        experiment:
          type: string
          description: Experiment GUID for A/B testing.
    Error:
      type: object
      properties:
        error:
          type: string
        message:
          type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Klu API key passed as a Bearer token in the Authorization header.