Model Context Protocol (MCP) Server Directory

MCPShark is a VS Code and Cursor extension that captures every MCP tool call — request, response, latency, payload — and renders it as an interactive timeline. This guide builds an MCPShark-powered monitoring server that exposes tool call telemetry as structured MCP resources for real-time agent debugging.

Atomic is a local-first, AI-augmented personal knowledge base that uses SQLite FTS5 and BM25 ranking for embedding-free semantic search. This guide builds an Atomic MCP Server that exposes note creation, semantic retrieval, and context merging as MCP tools — giving AI agents persistent, queryable memory with an 18MB memory footprint.

Build DearAgent Email MCP Server: self-hosted email inbox API for AI agents using Cloudflare Workers and FastMCP. Open-source alternative to AgentMail.

Build a Google SEO & GEO MCP server with Search Console, GA4, PageSpeed Insights, and structured data validation tools for AI agents. Full FastMCP tutorial.

Build a Remote MCP Servers Hub with FastMCP: curated directory, automated health checks, and MCP client integration for discovering 200+ remote AI agent tools.

BankMCP is an open-source self-hosted MCP server that gives AI agents read-only access to bank accounts via Open Banking APIs. With 199 GitHub stars, it solves the critical gap of standardized financial data access for AI agents without sharing credentials.

Build Geiger MCP Scanner -- a read-only MCP server that inventories every AI agent, MCP server, plugin, and AI extension on your machine. Full Python/ FastMCP tutorial.

PaperGraph MCP turns academic math papers into evidence-grounded reading maps for AI agents -- parsing LaTeX source into theorem dependency graphs.

Build a Golf Scanner MCP server that discovers and audits every MCP server running on your machine. Scan processes for MCP endpoints, inspect registered tools, check security posture, detect exposed configuration files, and identify vulnerable or outdated server versions.

Build an MCP analytics server that provides product analytics and evaluation metrics for AI agent sessions. Track every tool call, measure latency and success rates, compute aggregate performance metrics, and enable data-driven agent optimization — all through MCP tools.

Build a Tiptap AI Agent MCP server that adds AI-powered content workflows to any text editor. Generate, summarize, rewrite, translate, and optimize content through structured MCP tool calls — no more context switching to ChatGPT.

Build a Mnemosyne hierarchical memory MCP server that gives AI agents persistent, organized memory. Store conversations as structured memory nodes, retrieve by recency and relevance, and organize memories with automatic clustering.