⚡️ mcpo

Created By
ericsantosa year ago
A simple, secure MCP-to-OpenAPI proxy server
Overview

What is mcpo?

mcpo is a simple and secure proxy server that exposes any MCP tool as an OpenAPI-compatible HTTP server, allowing seamless integration with LLM agents and applications that expect OpenAPI servers.

How to use mcpo?

To use mcpo, you can run it via command line with a specified MCP server command. For example:

uvx mcpo --port 8000 --api-key "top-secret" -- your_mcp_server_command

You can also use Python or Docker to run mcpo without installation.

Key features of mcpo?

  • Instantly exposes MCP tools as OpenAPI-compatible servers.
  • Enhances security, stability, and scalability using web standards.
  • Auto-generates interactive documentation for every tool.
  • Uses pure HTTP, eliminating the need for custom protocols or glue code.

Use cases of mcpo?

  1. Making legacy MCP tools accessible via modern web APIs.
  2. Integrating various AI tools with OpenAPI specifications.
  3. Simplifying the deployment of multiple MCP tools through a single config file.

FAQ from mcpo?

  • What is an MCP tool?

MCP stands for Model Context Protocol, which allows various tools to communicate in a standardized way.

  • Is mcpo secure?

Yes! mcpo adds security features to ensure safe communication between tools.

  • Can I run mcpo in a Docker container?

Absolutely! You can run mcpo via Docker without needing to install it on your machine.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
ericsantos
Star
0
Language
Python
License
MIT license

Recommend Servers

View All
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.

11 hours ago
Voyei

an hour ago