My MCP Server

What is My MCP Server?

My MCP Server is a custom implementation of the Model Context Protocol (MCP), an open protocol that standardizes how applications provide context to large language models. It is designed to be used with Claude Desktop, enabling Claude to access real-time weather forecast data via the MCP standard.

How to use My MCP Server?

Install Node.js and npm, then clone the repository and run npm install followed by npm run build. Configure the server in Claude Desktop by editing ~/Library/Application Support/Claude/claude_desktop_config.json (on macOS) to specify the node command and the full path to build/main.js. Restart Claude Desktop and verify the server is registered; then ask a question like “What’s the weather in San Francisco?” to see the integrated forecast.

Key features of My MCP Server

• Implements the Model Context Protocol for structured AI context.
• Integrates directly with Claude Desktop for real-time data.
• Provides weather forecast information via MCP tools.
• Built with Node.js and easily configurable.
• Includes a quick-start build and setup process.
• Compares MCP with Function Calling for clarity.

Use cases of My MCP Server

• Getting live weather forecasts inside Claude Desktop conversations.
• Demonstrating how MCP connects AI models to external data sources.
• Testing and developing custom MCP servers for other data types.

FAQ from My MCP Server

What is the Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to LLMs, acting like a USB-C port for AI applications to connect with data sources and tools.

How does MCP differ from OpenAI’s Function Calling?

Function Calling is a proprietary API pattern from OpenAI, while MCP is an open, standardized protocol that works across different hosts and clients like Claude Desktop.

What are the prerequisites to run My MCP Server?

You need Node.js and npm installed, plus Claude Desktop (downloadable from claude.ai/download).

How do I configure the server in Claude Desktop?

Edit the claude_desktop_config.json file (on macOS at ~/Library/Application Support/Claude/claude_desktop_config.json) to add the server’s command (node) and path to the built main.js.

How do I test if the server is working?

After restarting Claude Desktop, ask a weather question (e.g., “What’s the weather in San Francisco?”). If the server is registered correctly, Claude will include forecast data in its response.