MCP Server Template for Cursor IDE

What is MCP Server Template for Cursor IDE?

A simple template for creating custom tools for Cursor IDE using Model Context Protocol (MCP). Users create their own repository from this template, modify the tools, and connect them to Cursor IDE.

How to use MCP Server Template for Cursor IDE?

Use the "Deploy to Heroku" button for quick deployment, or set up locally via Docker (docker compose up --build -d) or traditional Python setup with uv (uv run mcp-simple-tool). Connect to Cursor IDE by adding an MCP server in Settings → Features, using either SSE or stdio transport.

Key features of MCP Server Template for Cursor IDE

• Template for building custom Cursor IDE tools
• Supports both stdio and SSE transport protocols
• One-click deploy to Heroku
• Docker and traditional Python setup options
• Configurable via environment variables (.env)
• Integration with Smithery for Claude Desktop

Use cases of MCP Server Template for Cursor IDE

• Create personalized MCP tools for Cursor IDE
• Quickly prototype and serve custom tools via Heroku
• Experiment with MCP server development locally
• Deploy a mood-checking example tool for testing
• Use as a starting point for more complex MCP servers

FAQ from MCP Server Template for Cursor IDE

What transport protocols does the server support?

The server supports both stdio (default) and SSE transport, configurable via command-line options.

How can I deploy the server quickly?

You can deploy to Heroku with a single click using the provided button, or run locally with Docker or Python.

How do I connect the server to Cursor IDE?

In Cursor Settings → Features, add a new MCP server with Type set to "sse" (for Heroku/Docker) or "stdio" (for local run) and the appropriate URL or command path.

What are the environment variables I can set?

Available variables include MCP_SERVER_PORT, MCP_SERVER_HOST, DEBUG, and MCP_USER_AGENT.

Is there a dependency on Python or Docker?

The traditional setup requires Python and the uv package manager; Docker is optional but provides containerized deployment.