MCP-connect

MCP Connect bridges the gap between cloud AI services and local Stdio-based MCP servers by translating HTTP/HTTPS requests, enabling cloud integration with local resources. MCP Connect bridges the gap between

198
13

MCP Connect

License: MIT

MCP Connect is a tool designed to bridge the gap between cloud-based AI services and local Model Context Protocol (MCP) servers that use Stdio transport. It enables cloud AI tools to interact with local MCP servers by translating HTTP/HTTPS requests to Stdio communication.

Key features:

  • Cloud Integration, Protocol Translation, Security, and Flexibility.
  • Built-in support for Ngrok tunnel.

How it works:

MCP Connect acts as a bridge between cloud AI tools and local MCP servers, using tunnels to facilitate communication.

Quick Start:

  1. Clone the repository and configure the .env file.
  2. Install dependencies using npm install.
  3. Run MCP Connect using npm run build and npm run start or npm run dev.

API Endpoints:

  • GET /health: Health check endpoint.
  • POST /bridge: Main bridge endpoint for receiving requests.

MCP Connect uses token-based authentication and requires environment variables such as AUTH_TOKEN, PORT, LOG_LEVEL, and NGROK_AUTH_TOKEN. It can be used with ConsoleX AI to access local MCP Servers.

Repository

EV
EvalsOne

EvalsOne/MCP-connect

Created

December 21, 2024

Updated

March 28, 2025

Language

TypeScript

Category

Developer Tools