{"type":"mcp_server","name":"MCP-connect","description":"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","category":"Developer Tools","language":"TypeScript","stars":238,"forks":13,"owner":"EvalsOne","github_url":"https://github.com/EvalsOne/MCP-connect","homepage":null,"setup":"## Setup\n\n1. Clone the repository: `git clone https://github.com/EvalsOne/MCP-connect.git` and enter the directory: `cd MCP-connect`\n2. Copy `.env.example` to `.env` and configure the port and auth_token: `cp .env.example .env`\n3. Install dependencies: `npm install`\n4. Run MCP Connect: `npm run build`, `npm run start` (or `npm run dev` for dev mode).\n5.  (Optional) Get your Ngrok auth token from https://dashboard.ngrok.com/authtokens and add it to your .env file as `NGROK_AUTH_TOKEN=your_ngrok_auth_token`.\n6. (Optional) Run with tunnel: `npm run start:tunnel` (or `npm run dev:tunnel` for dev mode).","tools":"## Available Tools\n\n1. Cloud Integration (Enables cloud-based AI services to interact with local Stdio based MCP servers)\n2. Protocol Translation (Converts HTTP/HTTPS requests to Stdio communication)\n3. Security (Provides secure access to local resources while maintaining control)\n4. Flexibility (Supports various MCP servers without modifying their implementation)\n5. Easy to use (Just run MCP Connect locally, zero modification to the MCP server)\n6. Tunnel (Built-in support for Ngrok tunnel)\n7. `/health` endpoint (Health check endpoint)\n8. `/bridge` endpoint (Main bridge endpoint for receiving requests from the cloud)\n","faq":null,"created_at":"2024-12-21T03:45:33+00:00","updated_at":"2025-03-28T20:34:26+00:00","source_url":"https://model-context-protocol.com/servers/cloud-ai-local-mcp-server-access","related_articles":[]}