Claude Desktop インストールガイド

ローカル MCP 設定に対応するデスクトップクライアント。

11766件

MCP Servers

5533 件
PM
patrup/mcp-libre
Developer tools

A comprehensive Model Context Protocol (MCP) server that provides tools and resources for interacting with LibreOffice documents.

94 070
CA
codealive-ai/codealive-mcp
Developer tools

This MCP (Model Context Protocol) server enables AI clients like Claude Code, Cursor, Claude Desktop, Continue, VS Code (GitHub Copilot), Cline, Codex, OpenCode, SourceCraft Code Assistant,...

87 070
DM
dollhousemcp/mcp-server
Developer tools

- a starter element from your portfolio — your AI immediately changes - any element type (persona, skill, template, agent, memory, ensemble) by describing what you want in plain English - any...

41 070
AT
aquasecurity/trivy-mcp
Security testing

https://github.com/user-attachments/assets/125791b0-3164-4dcc-8fb3-e45481a9cbf7

47 070
LM
linkedinlearning/model-context-protocol-mcp-hands-on-with-agentic-ai-2034200
Developer tools

This is the repository for the LinkedIn Learning course Model Context Protocol (MCP): Hands-On with Agentic AI. The full course is available from LinkedIn Learning.

114 070
SA
seuros/action_mcp
Developer tools

is a Ruby gem focused on providing Model Context Protocol (MCP) capability to Ruby on Rails applications, specifically as a server.

117 070
CC
codegraphcontext/codegraphcontext
Developer tools

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

3890 070
IM
inanna-malick/popup-mcp
Productivity workflow

- Display interactive popup windows from AI assistants through the Model Context Protocol.

75 070
TP
tathagat22/plumb-mcp
Developer tools

⭐ If Plumb saves you tokens — or designs you a page — star it on GitHub so others can find it.

71 070
JC
jamf-concepts/mcp-hub
Developer tools

Jamf's open source mcp for Jamf Pro, Jamf Protect and Jamf Security

30 070
AT
atlassian/trello-mcp-server
Developer tools

Official remote MCP server for Trello.

52 070
AR
azer/react-analyzer-mcp
Developer tools

MCP server for analyzing & generating docs for React code locally

58 070

Agent Skills

6233 件
FS
flornkm/skills
Developer tools

There are plenty of skills out there. This library avoids slop and only ships skills that:

10340
HL
hardness1020/leeway
Developer tools

Human-defined workflows. AI-powered execution. YAML decision trees with scheduling, hooks, MCP, and 21 built-in tools.

11340
JV
jasonbitsmith/vps-first-steps
Deployment & DevOps

A single, readable bash script that takes a fresh Ubuntu/Debian VPS from default install to a hardened, ready-to-use server.

4140
GI
guopenglin/image2ppt
Developer tools

DeckWeaver 可以把 GPT、Gemini等输出的图片重建为可编辑的 PowerPoint 文件。它可以作为Agent的Skill使用,或者直接作为一个无大模型介入的命令行工具。

6140
AD
allenloves/de-ai-tone
Research

去 AI 味:繁體中文寫作與翻譯的風格規範(Claude Code skill)

6240
RB
ripemangobox/bite
Developer tools

Semi-automated research assistant and local knowledge base for paper analysis, ideation, coding, experiments, writing, and publication workflows.

6140
NA
norahe0304-art/30x-video
Browser automation

One URL in, an agency-grade launch video out. A Claude Code skill (Remotion + React) with a 16-law taste codex — 12 brands, 12 worlds, zero templates.

6240
YU
yuanpingsong/ultracodex
Developer tools

Run Claude Code workflow scripts, unmodified, on the OpenAI Codex CLI — fable plans, codex executes, fable verifies. Parallel agent fleets, builder–verifier loops, token budgets, full-screen TUI.

6540
SA
sunyifeisb-art/legalwork
Developer tools

LegalWork - legal AI workbench

6240
CI
cyber-immortal/cyber-figures
Research

赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation

6640
SE
syy12335/environment-runtime
Developer tools

Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。随着 OpenClaw 在企业工程流程中的关注度持续提升,一个现实需求也逐渐显现:面向通用场景的 agent runtime 设计未必能直接覆盖所有工程落地形态。这个项目把视角收窄到高确定性工程流程,希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。

12740
DC
doraemonkeys/claude-code-debug-mode
Developer tools

A hypothesis-driven debugging skill for Claude Code, Codex, and Gemini CLI. Instead of blindly guessing fixes, it instruments your code with runtime logs, generates multiple hypotheses, and...

11140