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
LH
levante-hub/levante
开发工具

Levante is a cross-platform desktop app (Windows, macOS, Linux) that brings powerful AI tools closer to everyone — not just technical users.

40 060
NS
nooqta/saiku
开发工具

Looking for the Python version? Check out Saiku.py.

40 060
WC
willccbb/claude-code-mcp
开发工具

This project enables Claude to use Model Context Protocol (MCP) servers for enhanced capabilities, including web search, GitHub integration, file operations, database access, and communication tools.

121 060
TA
tsadoq/a2a-mcp-tutorial
开发工具

In the fast-moving world of agentic AI, two open protocols quietly solve the headaches that used to keep multi-agent projects from ever leaving the lab.

112 060
AM
acehoss/mcp-gateway
API 开发

A flexible gateway server that bridges Model Context Protocol (MCP) STDIO servers to MCP HTTP+SSE and REST API, enabling multi-instance MCP servers to be exposed over HTTP.

133 060
JA
jianzhichun/abaqus-mcp-server
开发工具

An MCP (Model Context Protocol) server designed to interact with an Abaqus/CAE Graphical User Interface (GUI).

103 060
PA
peakmojo/agentic-mcp-client
开发工具

A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs.

41 060
AP
appsecco/pentesting-mcp-servers-checklist
开发工具

A practical, community-driven checklist for . This guide covers local and remote MCP server risks, traffic analysis, tool-call behaviors, context boundaries, authorization flows, and unsafe code...

40 060
JM
jtanningbed/mcp-ag2-example
开发工具

This project demonstrates the integration of the Model Context Protocol (MCP) with AutoGen (AG2), showcasing a powerful pattern for building modular, tool-enabled AI agents.

42 060
FK
finerestaurant/kicad-mcp-python
开发工具

This project is a Model Context Protocol (MCP) server for KiCad. As MCP server that utilizes KiCad's official IPC-API, it provides the most stable and reliable way for AI models like Claude to...

40 060
SG
shuymn/gh-mcp
开发工具

A GitHub CLI extension that seamlessly runs the github-mcp-server as a bundled binary using your existing gh authentication.

43 060
JM
josharsh/mcp-server-boilerplate
开发工具

Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP

20 060

Agent Skills

6434 个结果
BG
bodila51/grok-bot-jev
开发工具

Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples

6240
OO
oil-oil/grok-designer
开发工具

委托外部设计顾问评审界面与交互,输出改进建议、视觉方向及 HTML、SVG 草稿。

6140
FD
forsonny/deep-discovery
开发工具

Deep Discovery is a Codex plugin that adds the deep-discovery skill for a 100-question self-interrogation process before committing to a design, plan, or strategy.

10340
AG
aipmandy/goskill
开发工具

🎯 Goal-driven execution helper for long-running tasks and explicit success criteria

6340
BB
bruc3van/bruce-drawio
开发工具

跨平台的 draw.io (diagrams.net) 图表生成技能,适用于 Claude Code、codex、zcode、workbuddy、OpenClaw 等各类 AI 编程 Agent。Agent 直接生成 drawio XML,校验后通过 CLI 导出图片;没有桌面版时自动降级为 draw.io 官网打开链接。

10140
SY
seminechen/yueban-image-to-code
数据科学与机器学习

yueban-image-to-code 是一个用于 Codex 的图片转代码与切图 skill,目标是把选中的 UI 图片或设计截图按 750px 画板宽度进行像素级还原,并导出独立透明 PNG 切图资源。

11640
LL
linggen/linggen-memory
开发工具

ling-mem is a single-binary CLI + optional web UI that remembers useful facts about you and your work across every session, every tool, and every project.

10840
UB
upstash/botstreet
开发工具

Three AI agents. $100K each. Real market prices. Who wins?

11240
RC
rknall/claude-skills
部署与 DevOps

Generic skills used in my daily work

7040
AW
alexanderop/walkthrough
开发工具

A skill that generates interactive HTML walkthroughs with clickable Mermaid diagrams — flowcharts and ER diagrams — to explain codebase features, flows, architecture, and database schemas.

12940
BA
buer2233/ai-api-test-skill
API 开发

面向 Python + pytest + requests 接口自动化项目的 AI Skill:让 Codex / Claude Code 按固定门禁、固定流程、固定 pytest 闭环来新增和维护接口自动化用例,流程图参考:flow_chart/flow.md。

12940
LP
luxalgo/pinets-cli
开发工具

Run Pine Script® indicators and strategies from your terminal. Point it at any .pine file and get JSON output — live market data or your own dataset, no project setup. Built on PineTS.

6540