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。
一款全面的、便捷的cocos creator AI MCP服务插件，适用于3.8.0以上cocos版本，一键安装，一键启动。A comprehensive and convenient cocos creator AI MCP service plug-in, suitable for cocos versions above 3.8.
Command-line interface for any Model Context Protocol (MCP) server.
Multi-AI MCP Server - Connect ChatGPT, Claude, Gemini & Perplexity to your coding tools without any API
This tool generates from OpenAPI specifications, creating Python packages that can be used by AI assistants to interact with APIs.
Canvas MCP Client is an built around an infinite, zoomable, and pannable canvas. It provides a unified interface for interacting with multiple MCP (Model Context Protocol) servers through a flexible,...
把 Burp Suite 33 个插件（26 核心 + 7 Phase 3 高级工具）通过 MCP 协议桥接到 AI 客户端
Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
CodeGraph transforms your entire codebase into a semantically searchable knowledge graph that AI agents can actually reason about—not just grep through.
High-quality parsing 257 languages/grammars through tree-sitter AST analysis, in-process resolvers, enhanced with compiler-grade resolution for Python, TypeScript / JavaScript, PHP, C#, Go, C, C++,...
JSReverser-MCP 是一个面向 JavaScript 逆向分析的 MCP 工具，专门用于帮助开发者在真实浏览器环境中高效定位前端核心逻辑。它 将脚本检索、断点调试、函数 Hook、网络请求追踪、调用链分析、混淆还原和风险评估整合为统一能力，可直接接入 Claude、 Codex、Cursor 等支持 MCP 的客户端。
Citra — PDF answers with page-level proof. Local-first structured text, tables, OCR, visual evidence, and citations via MCP, CLI, and SDK.
AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.
Connect ClickHouse to your AI assistants.
📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.
Vibetest MCP - automated QA testing using Browser-Use agents
Token-efficient MCP adapter for Pi coding agent
Not a path. Not a URL. A handoff that answers back.
🦉 Augur — 本地优先的投资研究记忆系统：18 位投资大师独立分析 + 加权共识，证据带时间语义、每次运行可复查，CLI / Dashboard / MCP。A local-first research memory system with 18 investor personas.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro,...
An MCP server for interacting with Sentry via LLMs.
LLDB MCP Integration + other helpful commands
MCP Server for Turkish & American Stock Exchange and Fund Data
Every LLM starts every conversation from zero. Stash gives your agent persistent memory — it remembers, recalls, consolidates, and learns across sessions. No more explaining yourself from scratch.
MCP server for Docker