Skip to main content
Glama

JitAPI

PyPI PyPI Downloads License: MIT Python 3.10+

Point Claude at any API. JitAPI figures out which endpoints to call and in what order — automatically.

JitAPI is an MCP server that lets Claude interact with any API from its OpenAPI spec. Instead of dumping hundreds of endpoints into context, JitAPI uses semantic search and a dependency graph to surface only what's needed — then Claude plans and executes the calls.

https://github.com/user-attachments/assets/53f72f89-a41a-4a9c-a688-ec876ea05fbd


The Problem

Stripe has 300+ endpoints. GitHub has 800+. Loading the full spec into Claude's context wastes tokens and causes hallucinations. Writing a custom MCP server for every API you use doesn't scale.

JitAPI solves this: register any OpenAPI spec once, then ask for what you need in plain English. It finds the right endpoints, resolves dependencies between them, and lets Claude execute the calls.

Related MCP server: OpenAPI to MCP

Quick Start

pip install jitapi

Add to your Claude Code config (.mcp.json):

{
  "mcpServers": {
    "jitapi": {
      "command": "uvx",
      "args": ["jitapi"]
    }
  }
}

That's it. No API keys required — JitAPI uses local embeddings out of the box.

Then in Claude:

You: Register the GitHub API from https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json

Claude: ✓ Registered GitHub v3 REST API — 1,107 endpoints indexed

You: List my repos

Claude: [searches for "list repositories for authenticated user" → finds GET /user/repos → executes]
Here are your repositories: ...

Multi-API Orchestration

The killer feature: register multiple APIs and ask questions that span them. JitAPI searches across all registered APIs and Claude chains the calls.

You: Register the TMDB API and OpenWeatherMap API
Claude: ✓ Registered both APIs

You: Find the top popular movie on TMDB, then get the weather where it was filmed

Claude: [searches TMDB → GET /movie/popular → GET /movie/{id} for production locations
         → searches OpenWeather → GET /data/2.5/weather with the city]

The #1 popular movie is "Inception", filmed in Los Angeles.
Current weather in LA: 72°F, partly cloudy.

How It Works

Register API                          Ask a question
     │                                      │
     ▼                                      ▼
Parse OpenAPI spec               Embed query → vector search
     │                                      │
     ▼                                      ▼
Build dependency graph           Find relevant endpoints
     │                                      │
     ▼                                      ▼
Embed all endpoints              Expand with dependencies
     │                                      │
     ▼                                      ▼
Store in vector DB               Return schemas → Claude executes
  1. Register — Parse an OpenAPI spec, build a dependency graph (which endpoints need data from which other endpoints), and create searchable embeddings for all endpoints

  2. Search — When you ask a question, JitAPI embeds your query and finds the most relevant endpoints via cosine similarity

  3. Expand — The dependency graph adds any prerequisite endpoints (e.g., "you need to call GET /users first to get the user_id for POST /orders")

  4. Execute — Claude gets the endpoint schemas and makes the API calls, passing data between steps

MCP Tools

Tool

Description

register_api

Register an API from an OpenAPI spec URL

list_apis

List all registered APIs and their endpoint counts

search_endpoints

Semantic search across endpoints using natural language

get_workflow

Find relevant endpoints with dependency resolution and full schemas

get_endpoint_schema

Get the complete schema for a specific endpoint

call_api

Execute a single API call with auth, path params, query params, and body

set_api_auth

Configure authentication (API key header, API key query param, or bearer token)

delete_api

Remove a registered API and all its data

Setup

Claude Code

Create .mcp.json in your project directory (or ~/.claude.json for global access):

{
  "mcpServers": {
    "jitapi": {
      "command": "uvx",
      "args": ["jitapi"]
    }
  }
}

Claude Desktop

Add to your Claude Desktop config:

OS

Config path

macOS

~/Library/Application Support/Claude/claude_desktop_config.json

Windows

%APPDATA%\Claude\claude_desktop_config.json

Linux

~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "jitapi": {
      "command": "uvx",
      "args": ["jitapi"]
    }
  }
}

Embedding Providers

JitAPI works out of the box with local embeddings (fastembed) — no API keys needed. For better search quality on large APIs, you can add a cloud embedding provider:

Provider

Quality

Setup

Local (default)

Good

Nothing — works immediately

Voyage AI (recommended)

Excellent

pip install jitapi[voyage] + set VOYAGE_API_KEY

OpenAI

Excellent

pip install jitapi[openai] + set OPENAI_API_KEY

Cohere

Very good

pip install jitapi[cohere] + set COHERE_API_KEY

Set the API key in your MCP config's env block:

{
  "mcpServers": {
    "jitapi": {
      "command": "uvx",
      "args": ["jitapi"],
      "env": {
        "VOYAGE_API_KEY": "your-key-here"
      }
    }
  }
}

Provider is auto-detected from available environment variables. Priority: Voyage AI > OpenAI > Cohere > local.

Authentication

Configure API authentication after registering. Supported auth types: bearer, api_key (custom header), and api_key_query (query parameter). The recommended approach uses environment variables so secrets are never written to disk:

{
  "mcpServers": {
    "jitapi": {
      "command": "uvx",
      "args": ["jitapi"],
      "env": {
        "GITHUB_TOKEN": "ghp_...",
        "OPENWEATHER_API_KEY": "your-key-here"
      }
    }
  }
}

Then tell Claude to use the env var:

You: Set bearer auth for GitHub using env var GITHUB_TOKEN
Claude: [calls set_api_auth with auth_type="bearer", env_var="GITHUB_TOKEN"]
✓ Auth configured for github (from env var $GITHUB_TOKEN)

With env_var, JitAPI reads the secret from the environment at request time — only the env var name is persisted, never the credential itself.

You can also pass credentials directly (they'll be stored in ~/.jitapi/auth.json with 0600 permissions):

You: Set API key auth for OpenWeather with param name "appid"
Claude: [calls set_api_auth with auth_type="api_key_query", credential="...", param_name="appid"]
✓ Auth configured for openweather

Supported auth types: bearer, api_key (custom header, default X-API-Key), api_key_query (query parameter).

Security note: When using env_var, credentials are resolved at runtime and never touch the filesystem. When passing credential directly, secrets are stored as plaintext JSON at ~/.jitapi/auth.json (file permissions 0600, directory 0700). For production use, prefer the env_var approach.

Environment Variables

Variable

Required

Description

VOYAGE_API_KEY

No

Voyage AI API key (recommended cloud provider)

OPENAI_API_KEY

No

OpenAI API key (alternative cloud provider)

COHERE_API_KEY

No

Cohere API key (alternative cloud provider)

JITAPI_STORAGE_DIR

No

Data directory (default: ~/.jitapi)

JITAPI_LOG_LEVEL

No

DEBUG, INFO, WARNING, ERROR (default: INFO)

Development

git clone https://github.com/nk3750/jitapi.git
cd jitapi
pip install -e ".[dev]"
pytest
ruff check src/

License

MIT


Built by Neelabh Kumar — AI engineer and builder.

Available Tools

8 tools
call_apiB

Execute an API call. Make sure authentication is configured first.

Inputs: api_id (required), endpoint_id (required), path_params, query_params, +1 more.

delete_apiA

Delete a registered API and all its data including endpoints, embeddings, dependency graph, and authentication credentials.

Inputs: api_id (required).

get_endpoint_schemaB

Get the full schema for a specific endpoint. Use this to get detailed parameter and response information.

Inputs: api_id (required), endpoint_id (required).

get_workflowA

Get relevant endpoints with dependency resolution and full schemas for accomplishing a task. Returns search results expanded with their dependencies so you can plan and execute the right API calls in the right order. After reviewing the results, use call_api to execute each step.

Inputs: query (required), api_id (required), max_steps.

list_apisB

List all registered APIs with their basic information.

Inputs: no named parameters.

register_apiA

Register a new API by ingesting its OpenAPI specification. This parses the spec, builds a dependency graph, and creates searchable embeddings.

Inputs: api_id (required), spec_url (required).

search_endpointsA

Search for API endpoints using natural language. Returns semantically similar endpoints based on the query.

Inputs: query (required), api_id, top_k.

set_api_authA

Configure authentication for an API. Supports API key (header or query param) and bearer token auth. Use env_var to reference a secret from an environment variable — the credential is then resolved at request time and never stored on disk.

Inputs: api_id (required), auth_type (required), credential, env_var, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: register/delete/list for API lifecycle management, search_endpoints for discovery, get_endpoint_schema for detailed inspection, get_workflow for task planning with dependencies, set_api_auth for configuration, and call_api for execution. No overlapping functionality.

    Naming Consistency5/5

    Consistent snake_case throughout with verb_noun pattern (call_api, delete_api, list_apis, register_api, search_endpoints, get_workflow, get_endpoint_schema, set_api_auth). All use standard CRUD-style verbs (get, list, search, call, set, register, delete).

    Tool Count5/5

    8 tools is well-scoped for an API management server covering the full lifecycle: registration, listing, deletion, authentication, discovery (search), inspection (schema), planning (workflow), and execution. Each tool earns its place without redundancy.

    Completeness4/5

    Covers the core API lifecycle well (register, list, delete, auth, search, call) with helpful additions like workflow planning. Minor gaps: no get_api for specific API details (only list_apis), no update_api for refreshing specs without full deletion, and no way to remove auth without deleting the entire API.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A standalone proxy that transforms any OpenAPI or Swagger-described REST API into an MCP server by mapping API operations to executable MCP tools. It enables AI clients to interact with existing web services through automated HTTP requests based on their official documentation.
      16
      MIT
    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Universal AI API Orchestrator. 850 tools across 53 services under a single MCP interface. Connect Claude, GPT, or Gemini to Stripe, Slack, GitHub, LinkedIn, Cloudflare, Shopify, Twilio, and 46 more via natural language. $0.10/execution, no subscription. Patent Pending.
      274 npm
      5
      -
    • A
      license
      A
      quality
      C
      maintenance
      Turn any OpenAPI spec into MCP tools for Claude — instantly. Point mcp-openapi at any OpenAPI 3.x spec and Claude can call every endpoint through natural language. No custom integration code. No manual tool definitions. One line of config.
      2
      40 npm
      1
      MIT