Typingmind MCP

🚀 MCP Connector

The MCP Connector is a lightweight server that can run and manage multiple Model Context Protocol (MCP) servers. It is specifically designed for integration with TypingMind. It offers an easy way to run MCP servers on a local computer or a remote server, allowing you to connect custom AI models or tools to TypingMind via a simple REST API.

🚀 Quick Start

Run on Local Device

You can quickly start the MCP Connector using npx (no installation required):

npx @typingmind/mcp <auth-token>

• Replace <auth-token> with the authentication token you obtained from TypingMind.

Keep this terminal window open to use the MCP Connector while using TypingMind.

HTTPS Support

To enable HTTPS, set the following environment variables:

CERTFILE=./path/to/certificate.crt KEYFILE=./path/to/privatekey.key npx @typingmind/mcp <auth-token>

• CERTFILE: Path to the SSL certificate file.
• KEYFILE: Path to the private key file.

When both variables are set, the server will use HTTPS instead of HTTP.

Run on Server

If you prefer to run the MCP Connector on a remote server:

1. Install Node.js (version 14 or higher).
2. Run the server using npx:

npx @typingmind/mcp <auth-token>

When enabling HTTPS:

CERTFILE=./path/to/certificate.crt KEYFILE=./path/to/privatekey.key npx @typingmind/mcp <auth-token>

Alternatively, for persistent operation (e.g., after closing the SSH session), you can use a process manager like pm2 or screen/tmux:

pm2 start npx -- @typingmind/mcp <auth-token>

💻 Usage Examples

Connect to TypingMind

To connect the MCP Connector to TypingMind:

1. Visit www.typingmind.com/mcp and follow the instructions.
2. Paste your MCP Connector server address (http://localhost:<port> or your server IP address and port) and the authentication token on the MCP integration page of TypingMind.

📚 Documentation

REST API Endpoints

All API endpoints require authentication via a Bearer token, which is provided when starting the server.

⚠️ Important Note

• All requests require the Authorization: Bearer <auth-token> header.
• Available ports: The server will choose port 50880 or 50881. Please ensure these ports are available. You can also specify a different port via the PORT environment variable.

📄 License

MIT