Claude Desktop 安装指南

支持本地 MCP 配置的桌面客户端。

10039个结果

MCP Servers

5255 个结果
FL
ftshare-lab/ftshare-mcp
开发工具

FTShare MCP 是面向 AI Agent 的金融数据 MCP 服务,让 Claude Code、Codex、WorkBuddy、OpenClaw、Hermes 等支持 MCP 的客户端,可以通过自然语言调用 FTShare 的行情、财务、宏观、基金、期货、债券、美股和港股数据。

107 045
KM
kevinwatt/mcp-server-searxng
开发工具

An MCP server implementation that integrates with SearXNG, providing privacy-focused meta search capabilities.

36 045
AL
anton15k/llm_wiki_agent
效率工作流

MCP server that turns raw sources into an interlinked Obsidian wiki with Claude Code.

34 045
VL
virtuslab/llm-tools-mcp
部署与 DevOps

Connect to MCP servers right from your shell. Plugin for simonw/llm.

38 045
AA
agency-ai-solutions/openai-codex-mcp
开发工具

An MCP server to wrap the OpenAI Codex CLI tool for use with Claude Code.

51 045
BM
bitteprotocol/mcp
分析与监控

This monorepo contains MCP (Model Control Protocol) servers for different services.

14 045
PG
philschmid/gemini-api-docs-mcp
开发工具

A remote HTTP MCP server that provides tools to search and retrieve Google Gemini API documentation. The server exposes the MCP protocol at the /mcp endpoint and can be deployed to Cloud Run or other...

101 045
AM
alexai-mcp/opencrab
开发工具

OpenCrab is the public integration repository for the LocalCrab ontology factory and the OpenCrab hosted ecosystem at opencrab.sh.

99 045
PB
patrykiti/blender-ai-mcp
开发工具

blender-ai-mcp lets Claude, ChatGPT, Codex, and other MCP clients control Blender through a stable tool API instead of ad-hoc Python generation.

54 045
BO
benseverndev-oss/goldenmatch
开发工具

Zero-config matching that , in an engine verified from a laptop CSV to a . The identities it produces live in a — stable entity_ids, per-field provenance, merge/split, and a tamper-evident audit log...

128 045
UT
unmodeled-tyler/vessel-browser
分析与监控

Vessel is a simple, clean web browser with an AI assistant built in. Browse the web normally, then ask Vessel to help research, navigate pages, summarize what you are reading, fill forms, or keep...

126 045
HS
hnking-star/flysecagent
API 开发

这是一个基于大语言模型和MCP(Model-Controller-Plugin)和Rag架构的网络安全智能助手项目。它旨在通过自然语言交互,帮助用户执行渗透测试任务、查询安全信息、分析流量包等。

122 045

Agent Skills

4784 个结果
AA
atomflow-ai/molecode
开发工具

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly. Instead of making language models reconstruct molecular structure from cryptic strings, MoleCode lets...

29686
DA
disler/agent-sandbox-skill
开发工具

An agent skill for managing isolated execution environments

37886
CS
coleam00/skills
开发工具

The skills I actually use to build software with coding agents. Straight out of my .claude/skills/ folder.

23186
LK
lukasniessen/kubernetes-skill
开发工具

The #1 Kubernetes skill for Claude Code and Codex, measured by GitHub stars.

31586
GP
gokulrajaram/productspec
开发工具

ProductSpec is the open standard for product intent. It acts as a Product Harness for AI-native software work: what to build, what not to build, how to prove completion, and when intent changes.

26386
PA
paralleldrive/aidd
开发工具

AI agents like Claude Code ship features fast. AIDD Framework keeps them working, secure, and maintainable.

37686
LT
luoling8192/technical-writing
开发工具

中文内部技术写作的 agent skill。约束设计文档、评审稿、postmortem、分享稿等场景的语气、句法、结构,让产出贴近技术汇报,避开营销稿和散文气质。

21086
RM
reinamaccredy/maestro
开发工具

Local-first harness for agent-built codebases. Humans steer, agents execute, maestro is the substrate.

22686
WF
wbh604/fund-guy-skill
浏览器自动化

一句话:输入一个基金代码,Agent 把基金经理 8 年的每一笔买卖翻出来,拿 12 个月后的真实走势逐笔验对错,最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测,全都有。

20286
BW
bitget-wallet-ai-lab/bitget-wallet-skill
开发工具

An AI Agent skill that wraps the Bitget Wallet API, enabling natural-language-driven on-chain data queries and swap operations.

23386
GR
googlecloudplatform/race-condition
开发工具

A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...

21786
SD
shenli/distributed-system-testing
开发工具

Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.

22786