What does the middleware actually do?
It overrides tool and resource function implementations to record usage in an SQLite database.
@Phillip-Kemper
基本情報
A lightweight TypeScript middleware for MCP SDK servers that delivers analytics. Captures request metrics, performance data, and usage patterns with minimal overhead. Features real-time monitoring, configurable data collection, and detailed reporting - all with full type safety.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-analytics-middleware": {
"command": "npx",
"args": [
"-p",
"mcp-analytics-middleware",
"web-viewer",
"--db-path",
"analytics.db"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
MCP Analytics Middleware is a simple way to track and visualize how your MCP server is being used. It records tool calls and resource requests, tracks performance metrics and error rates, and provides a web dashboard for live analytics. It is for developers who want to understand which tools are most popular, catch errors early, and monitor server performance.
Install via yarn add mcp-analytics-middleware, then import McpAnalytics and wrap your McpServer instance with analytics.enhance(server). You can launch the live web dashboard with npx -p mcp-analytics-middleware web-viewer --db-path analytics.db, or use the MCP Inspector flag --analytics --db-path analytics.db.
It overrides tool and resource function implementations to record usage in an SQLite database.
Run `npx -p mcp-analytics-middleware web-viewer --db-path analytics.db` and open http://localhost:8080.
Total tool calls and resource requests, error rates, performance metrics, most used tools, and slowest operations.
Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.
Check whether ChatGPT, Claude, Perplexity and Gemini recommend a business, right from your AI agent. Get a 0 to 100 AI visibility score with a per-engine breakdown, the competitor named in your place, a full site audit,

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can
Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl
Pay-as-you-go data APIs for AI agents. Search providers, inspect endpoint prices, and run company enrichment, email verification, SEO, web search, and other data tasks through one hosted MCP server.
コメント