Claude Desktop 安装指南

支持本地 MCP 配置的桌面客户端。

12488个结果

MCP Servers

6054 个结果
KL
kenneth-liao/mcp-intro
开发工具

This tutorial demonstrates how to integrate Model Context Protocol (MCP) servers with Langgraph agents to create powerful, tool-enabled AI applications.

21 060
GG
gerritcodereview/gerrit-mcp-server
开发工具

MCP server for interacting with the Gerrit code review system - (mirror of https://gerrit.googlesource.com/gerrit-mcp-server)

20 060
ZM
zanetworker/mcp-playground
开发工具

Simple MCP Client for remote MCP Servers 🌐

25 060
BR
brightdata/real-estate-ai-agent
开发工具

Real Estate AI Agent System is a Python-based solution that leverages AI agents and Bright Data's Model Context Protocol (MCP) server to extract, process, and deliver structured real estate property...

151 060
DC
daxianlee/cocos-mcp-server
开发工具

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.

1156 060
LG
libreearth/gimp-mcp
开发工具

is an initiative to integrate the into the GNU Image Manipulation Program (GIMP), enabling seamless interaction between GIMP and AI models.

114 060
CO
cloudbadal007/ontology-mcp-self-healing
数据库管理

Self-healing multi-agent system using ontologies and MCP to automatically adapt when database schemas change

21 060
SF
sausheong/felix
开发工具

Felix — single-binary AI agent gateway. Multi-provider LLM, persistent memory, MCP client, runs entirely on your hardware

47 060
CC
coroslab/coros-mcp
开发工具

Official COROS MCP server and Agent skills for integrating sports and health data into AI clients.

42 060
DA
darknoah/aime-chat
开发工具

A cross-platform AI desktop chat cowork app supporting 10+ LLM providers, RAG knowledge base, and MCP tools. Built with Electron + React + Mastra.

45 060
GM
goplus/mcp
部署与 DevOps

A XGo implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

50 060
JO
jhacksman/openscad-mcp-server
开发工具

A Model Context Protocol (MCP) server that enables users to generate 3D models from text descriptions or images, with a focus on creating parametric 3D models using multi-view reconstruction and...

172 060

Agent Skills

6434 个结果
YR
ypares/rigup.nix
开发工具

rigup is a Nix-based system for packaging knowledge, instructions and skills for your AI agent with the tools and configuration needed to execute them.

8670
SA
simota/agent-skills
开发工具

90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy).

7770
FA
flaqai/awesome_seo_writing_skill
开发工具

Share the awesome skills for SEO Writing. All the skills are developed by Flaq AI Team

7770
LA
learnprompt/afu-llm-todo
效率工作流

LLM Todo for Obsidian agents Inbox -> Wiki -> Todo Card -> Calendar

8470
LQ
levi-qiao/longgraph-skill
开发工具

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates.

7670
SM
social-media-skills/skills
开发工具

106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.

7870
SA
shopify/agent-skills
开发工具

Shopify skills for agent collaboration

7970
AS
andrewnggirl/skilllens
开发工具

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

7570
ZG
zlbigger/google-seos.skill
开发工具

基于 Google 官方 SEO 文档构建的专业 SEO 诊断和优化技能。支持 OpenClaw / Claude 等 AI 助手,即问即用。 A professional SEO diagnostic and optimization skill built on 207 official Google SEO documents.

7670
LF
lubusin/frappe-skills
开发工具

Frappe Agent Skills gives AI coding assistants structured Frappe knowledge for DocTypes, APIs, Desk customization, frontend apps, reports, testing, and production patterns.

6070
SS
sarvamai/skills
开发工具

A curated set of practical skills and examples for building AI applications using Sarvam APIs.

7170
VE
vannyben7/edict-agent
开发工具

Edict Agent is a Codex skill for complex, ambiguous, high-risk, cross-module, or parallelizable tasks.

9570