ベスト＆人気の MCP サーバー
カテゴリ、インストールガイド、ソースで比較できます。
MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
A MCP (Model Control Protocol) SEO tool service based on Ahrefs data. Includes features such as backlink analysis, keyword research, traffic estimation, and more.
MCP server for AutoCAD LT automation and headless DXF generation.
A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.
An unofficial, opinionated MCP server for Bear Notes — built around relevance-ranked search instead of substring matching.
Index your codebase. AI searches instead of re-reading files. 94% token savings, reproducibly benchmarked.
An MCP server to use with AI agents such as OpenCode, Mai, VSCode, Claude, CLION, ...
Most AI agents still explore documentation the expensive way:
Stop exporting CSVs. Start asking your AI agent questions.
If you find this repo useful, please also star our ⭐
AI-driven semantic code search as an MCP tool — powered by Windsurf's reverse-engineered SWE-grep protocol.
An MCP server that connects your AI assistant to HackerOne. It pulls your bug bounty history, program scopes, and report details into a local SQLite database, then exposes tools that let any...
llamacloud-mcp is a tool that allows you to use LlamaCloud as an MCP server. It can be used to query LlamaCloud indexes and extract data from files.
This project provides an MCP server acting as an interface to the Meta Ads, enabling programmatic access to Meta Ads data and management features.
A Nix-based configuration framework for Model Control Protocol (MCP) servers with ready-to-use packages.
ServiceNow MCP server: 450+ tools and 26 AI capabilities for any AI (Claude, ChatGPT, Gemini, Cursor, Copilot).
File cache with diff tracking for AI coding agents. Powered by Turso, a high-performance embedded database.
Supercharge AI Agents, Safely
Give any AI agent eyes and hands inside any running app. 10 platforms. Zero test code. One MCP server.
This project leverages Playwright for automated browser testing and integrates with Cloudflare Workers, Browser Rendering and @cloudflare/playwright for deployment.
The package provides two ways to connect AI applications to MCP servers on AWS:
Claude Code memory that learns from corrections. The only MCP server that measures whether your agent actually stops repeating a mistake.
MCP Server for running code snippet and show the result.
Reqable MCP Server exposes local Reqable capture traffic to MCP clients (Windsurf/Cursor/Claude/Codex).