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
MM
mats2208/mcp-packet-tracer
开发工具

61 MCP Tools 5 MCP Resources 74 Device Models 151 Modules 15 Cable Types

125 070
OP
openclaw/peekaboo
开发工具

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI...

4839 070
PC
permacommons/chabeau
开发工具

OpenAI-API compatible terminal chatbot and MCP client in Rust

40 070
OW
open-webui/mcpo
开发工具

A simple, secure MCP-to-OpenAPI proxy server

4283 070
CC
codegraphcontext/codegraphcontext
开发工具

An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

3890 070
HM
hdresearch/mcp-shell
开发工具

A Node.js implementation of the Model Context Protocol (MCP) that provides secure shell command execution capabilities.

41 070
VB
vanto/beanquery-mcp
开发工具

The Beancount MCP Server is an experimental implementation of the Model Context Protocol (MCP) designed to interface with Beancount ledger files.

51 070
SA
supadata-ai/mcp
开发工具

Official Supadata MCP Server - Adds powerful video & web scraping to Cursor, Claude and any other LLM clients.

57 070
MS
modsetter/surfsense
效率工作流

SurfSense is the , an open web research platform with live data connectors. Your agents research the live web with structured data from , through one or .

1.5万 070
RD
repowise-dev/repowise
开发工具

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

3327 070
FC
florianbruniaux/claude-code-ultimate-guide
部署与 DevOps

The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.

5373 070
DG
developzir/gepa-mcp
开发工具

I'm not quite sure this works as is 😂 You may need to ask the model you're working with to clean it up:

51 070

Agent Skills

6434 个结果
ZA
zhaoxuya520/ai-fullstack-delivery-workflow
代码审查

AI 全栈交付工作流总控系统 — 17 个岗位工作流 + 100+ Skills + 自举脚本,AI 读一遍 README 就能自动配置环境并执行完整软件项目交付。覆盖产品/设计/前端/后端/测试/DevOps/SRE/安全/数据/AI集成/逆向渗透。

4940
BO
besoeasy/open-skills
开发工具

Battle-tested execution playbooks that give any AI agent the exact commands, APIs, and patterns it needs — cutting token usage by and making local models as capable as GPT-4.

12740
LA
lingyichen-ai/workflow-skill
API 开发

Describe your workflow in one sentence, and get a complete workflow definition file ready to import into Coze, Dify, or ComfyUI — including node configuration, edges, layout, and all...

14440
WS
workos/skills
开发工具

WorkOS skills for AI coding agents. Two skills and 40 reference files covering AuthKit, SSO, Directory Sync, RBAC, Vault, Migrations, backend SDKs, and more.

4540
EV
exponential-view-co/autoresearch-autobeta
开发工具

This repository contains two for autonomous iterative research — a pattern inspired by Andrej Karpathy's observation (March 2026; URL correct at time of writing) that any domain with a scalar oracle...

4840
EA
elisaterumi-ai/agent-skills-in-practice
开发工具

From prompts to systems — learn how to build reusable AI skills.

12640
CO
chenkuansun/openclaw-world
开发工具

3D virtual room where AI agents walk, chat, and collaborate as animated lobster avatars

4840
GJ
grandcamel/jira-assistant-skills
开发工具

Claude Code Skills for JIRA automation - modular skills for issue management, workflows, search, and collaboration

4840
AU
abhinavbwj/urban-design-skills-claude
开发工具

18 interconnected skills covering urban design theory, quantitative standards, and computational tools.

11840
TA
tariux/ai-skills-not-awesome
开发工具

A curated collection of operational system prompts and behavioral patterns for AI assistants, LLM agents, and prompt engineers. Each `.skill.

4740
CG
cyanluna-git/cyanluna.skills
开发工具

cyanluna.skills AI-powered kanban pipeline for Claude Code and Codex — seven autonomous agents, one board.

16940
MY
mn-youssef/security-skills
开发工具

A portable set of for testing and hardening an application . They apply attacker thinking (red team) to find vulnerabilities, then guide you to fix them (blue team).

4640