MCP Analytics Middleware

🚀 MCP Analytics Middleware

A simple way to track and visualize the usage of your MCP server. Discover which tools are most popular, detect errors early, and monitor server performance.

• Supporting Blog Post

✨ Features

• 🔍 Track all tool calls and resource requests.
• 📊 View performance metrics and error rates.
• 🌐 Web dashboard with real-time analytics.
• 💾 Persistent storage using SQLite database.

🚀 Quick Start

📦 Installation

Install the package:

yarn add mcp-analytics-middleware

💻 Usage

Add it to your MCP server:

import { McpAnalytics } from 'mcp-analytics-middleware';

let server = new McpServer({ 
name: 'Sample MCP Server with Analytics',
version: '1.0.0'
});

const analytics = new McpAnalytics('analytics.db');

server = analytics.enhance(server); // Override tool and resource function implementations to record usage in SQLite

💻 Usage Examples

Real - Time Analytics

Want to directly provide a real - time dashboard for a TypeScript SDK MCP server (using this middleware)? Use the following command:

npx -p mcp-analytics-middleware web-viewer --db-path analytics.db

The web dashboard will open at http://localhost:8080 and display real - time analytics! You'll see:

• Total number of tool calls and resource requests.
• Error rates and performance metrics.
• Most used tools and slowest operations.

Example Implementations

You can find the following example implementations:

1. Example of a Dummy Calculator Server with analytics middleware src/server.ts
2. Ethereum RPC MCP server with analytics middleware server/index.ts
3. Google Maps MCP server version with analytics middleware added src/google-maps/index.ts

Running with Inspector

If you're using MCP Inspector, simply add the analytics flag:

yarn inspector --analytics --db-path analytics.db

📄 License

MIT