Jitapi

Created By
nk37502 months ago
Point Claude at any API. JitAPI figures out which endpoints to call and in what order — automatically. Register any OpenAPI spec, search endpoints in plain English, and orchestrate multi-step workflows across multiple APIs. No API keys required — works out of the box with local embeddings.
Overview

What is JitAPI?

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

The Problem

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

How It Works

  1. Register any OpenAPI spec URL
  2. Search endpoints in plain English
  3. Execute — Claude chains the right API calls automatically

JitAPI builds a dependency graph that knows "you need to call GET /users first to get the user_id for POST /orders" — and resolves this
automatically.

Key Features

  • Zero-config: Works out of the box with local embeddings. No API keys required.
  • Multi-API orchestration: Register multiple APIs, ask questions that span them
  • Dependency graphs: Automatically resolves endpoint dependencies
  • Semantic search: Find endpoints using natural language, not exact paths
  • Pluggable embeddings: Local (default), Voyage AI, OpenAI, or Cohere

Quick Start

pip install jitapi

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

Links

- https://github.com/nk3750/jitapi                                                                                                         
- https://pypi.org/project/jitapi/

Server Config

{
  "mcpServers": {
    "jitapi": {
      "command": "uvx",
      "args": [
        "jitapi"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
nk3750
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

37 minutes ago