JitAPI

Provides dynamic LLM-driven API discovery and workflow execution across multiple APIs via OpenAPI specifications.
  • python

3

GitHub Stars

python

Language

2 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "nk3750-jitapi": {
      "command": "uvx",
      "args": [
        "jitapi"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "JITAPI_LOG_FILE": "/var/log/jitapi.log",
        "JITAPI_LOG_LEVEL": "INFO",
        "JITAPI_STORAGE_DIR": "~/.jitapi"
      }
    }
  }
}

JitAPI is an MCP server that lets large language models interact with any API by dynamically discovering relevant endpoints from OpenAPI specifications. It uses semantic search and dependency graphs to fetch only the endpoints needed for each task, enabling efficient, multi-step workflows across multiple APIs.

How to use

You will use an MCP client to connect to the JitAPI server and run tools that register APIs, plan workflows, and execute them. After setup, you can ask the assistant to register an API, plan a multi-step workflow, and execute the workflow with automatic parameter passing between steps.

How to install

Prerequisites include Python and a compatible MCP client (such as Claude Code or Claude Desktop). You also need an OpenAI API key for embeddings and workflow planning.

# Install JitAPI via pip
pip install jitapi

# Or run with UV environment manager
uvx jitapi

Configuration and usage notes

Use the following MCP configurations to run JitAPI locally. The configurations assume you will provide your own OpenAI API key.

{
  "mcpServers": {
    "jitapi": {
      "command": "uvx",
      "args": ["jitapi"],
      "env": {
        "OPENAI_API_KEY": "sk-REPLACE_WITH_YOUR_KEY"
      }
    }
  }
}

Environment variables

The following environment variables are recognized. Provide them in your MCP config or your shell/.env as needed.

  • OPENAI_API_KEY
  • JITAPI_STORAGE_DIR
  • JITAPI_LOG_LEVEL
  • JITAPI_LOG_FILE

Available tools

JitAPI exposes a set of tools to manage APIs, search endpoints, plan workflows, and execute them.

Available tools

register_api

Register an OpenAPI specification from a URL to make its endpoints available for discovery and workflow planning.

list_apis

List all APIs registered with JitAPI along with their basic metadata.

search_endpoints

Perform a semantic search to locate endpoints relevant to a natural language query.

get_workflow

Plan a multi-step workflow by extracting parameters and mapping data flow between endpoints.

execute_workflow

Execute a previously planned workflow, handling parameter passing between steps.

get_endpoint_schema

Retrieve detailed schema information for a specific endpoint.

call_api

Execute a single API call directly within a workflow context.

set_api_auth

Configure authentication methods for registered APIs.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational