热门好用的 MCP Server 推荐
按分类、安装方式和来源搜索比较 MCP Server。
MCP server for Web3 protocol documentation — EIPs, ERCs, BIPs, SIMDs, Cosmos ADRs, Polkadot RFCs, contract registry
Wot UI 的 AI 能力工具集：Skills、MCP 协议与 CLI 工具等
OrcaSlicer MCP — drive OrcaSlicer from Claude or any MCP client: load models, tune settings, slice, analyze
mcp-vision-server is an MCP stdio server that lets MCP clients analyze images and run OCR through an existing OpenAI-compatible vision Chat Completions API.
Structured reasoning for LLMs. Decompose, track confidence, visualize, approve.
✅ octagon-agent orchestrates broad market intelligence analysis
面试鸭 的题目搜索API现已兼容MCP协议，是国内首家兼容MCP协议的面试刷题网站。关于MCP协议，详见MCP官方文档。
MCP server for build123d to improve AI cognition when creating 3D CAD models
Email for AI agents — read, search, send and triage Gmail / QQ / 163 / any IMAP from the CLI or MCP. Part of the *-use family.
Your AI conversation history, queryable from any MCP-aware LLM, stored entirely on your machine.
Your AI agent doesn't know what's broken in production. This fixes that.
This document will guide you through setting up and running the Tasker MCP integration, including instructions for installing dependencies, preparing servers, and updating tasks.
Quickstart · Configure your client · Comfy Cloud MCP · Tools · Contributing
Maybe the headless Ghidra MCP you are looking for.
VV knowledge layer for AI agents — MCP server exposing Visualize Value frameworks, voice, and content
VoidMob MCP server for mobile proxies, non-VoIP SMS verifications, dedicated private numbers and global eSIMs.
An MCP server implementation for retrieving information from Pinecone Assistant.
Agents should not start every session with amnesia — but they shouldn't get to write whatever they want either.
An opinionated Jira MCP server built from years of real-world software development experience.
n2-QLN: Intelligent Tool Router & Semantic Search Layer for MCP. Connect 1,000+ tools through 1 interface. Prevent AI model confusion and maximize context window efficiency
Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB.
A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats and learn from past errors through a lesson system.
Guide AI to systematically complete software development through a structured workflow, ensuring code implementation stays aligned with business needs.
A Model-Context-Protocol (MCP) server that lets Claude (or any MCP-compatible LLM) interact with your Obsidian vault through the community plugin – written in and runnable with .