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。

11526件

MCP Servers

5493 件
SN
sanbuphy/nanomcp
Developer tools

"The question is not what you look at, but what you see." — Henry David Thoreau

74 060
AC
amidabuddha/console-chat-gpt
Developer tools

For new installs, use tellm instead. It is a small Rust Telegram assistant for Claude, GPT/Grok, Gemini, compatible endpoints, and local Ollama, with per-room model selection and keychain-backed...

158 060
KM
kuanhoong/mcp
Developer tools

This project demonstrates the implementation of Model Context Protocol (MCP) for both local and remote server configurations using stdio and HTTP protocols.

12 060
OM
ory/mcp
Developer tools

This repository contains TypeScript packages for integrating Ory authentication and access control with the Model Context Protocol (MCP).

11 060
JY
jiangusheng/yuns-desktop-pet
Developer tools

- - DeepSeek-V3 Chat、DeepSeek-R1 推理模型 - - Gemini 3 Pro/Flash、Gemini 2.5 系列(最新) - - GPT-4o、o1/o3 推理系列 - - Claude Sonnet 4、Claude 3.5 系列 - - Llama 3.3 70B(免费高速推理)

141 060
MC
mcpgod/cli
Developer tools

Fine-grained control over model context protocol (MCP) clients, servers, and tools. Context is God.

116 060
JS
jagan-shanmugam/mattermost-mcp-host
Developer tools

A Mattermost integration that connects to Model Context Protocol (MCP) servers, leveraging a LangGraph-based AI agent to provide an intelligent interface for interacting with users and executing...

34 060
HM
hyper-mcp-rs/hyper-mcp
Developer tools

📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.

880 059
NH
noone-hub/jsreverser-mcp
Developer tools

JSReverser-MCP 是一个面向 JavaScript 逆向分析的 MCP 工具,专门用于帮助开发者在真实浏览器环境中高效定位前端核心逻辑。它 将脚本检索、断点调试、函数 Hook、网络请求追踪、调用链分析、混淆还原和风险评估整合为统一能力,可直接接入 Claude、 Codex、Cursor 等支持 MCP 的客户端。

901 059
SM
saik0s/mcp-browser-use
Browser automation

MCP server that gives AI assistants the power to control a web browser.

950 059
JC
jakedismo/codegraph-rust
Developer tools

CodeGraph transforms your entire codebase into a semantically searchable knowledge graph that AI agents can actually reason about—not just grep through.

843 059
SC
sylphxai/citra
Developer tools

Citra — PDF answers with page-level proof. Local-first structured text, tables, OCR, visual evidence, and citations via MCP, CLI, and SDK.

936 059

Agent Skills

6033 件
PA
papadopouloskyriakos/agentic-chatops
Deployment & DevOps

AI agents that triage infrastructure alerts, investigate root causes, and propose fixes — while a solo operator sleeps.

10740
AR
anjos2/recursive-research
Developer tools

Claude Code skill for recursive research up to PhD level across any domain. Source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction.

4740
AA
aziz0x00/agent.sh
Developer tools

minimalist/toy terminal agent harness written in bash

4640
GG
goodniuniu/github-kb
Developer tools

GitHub Knowledge Base Manager - A Claude Code skill for managing local GitHub projects

4540
MP
mutonby/pleng
Analytics & monitoring

Your AI Platform Engineer. Self-hosted cloud built for AI agents — deploy, monitor, and operate your infrastructure through natural language. One VPS. One command.

4640
JE
just-every/plugin-ultracode
Developer tools

Ultracode Codex plugin

4740
PJ
pixelhawk4328-jvtdg/sprint-planning-agenda
Research

Sprint planning agenda: capacity, ready backlog, commit bar — no overfill.

4740
AC
arturitu/comfyui-scene-camera-action
Developer tools

Playable 3D previz for AI video. Stage environments, act with keyboard controls (WASD), cut dynamic cameras, and feed exact motion into generative video models.

4540
GG
gadievron/greenlight
Security testing

Refusal handling skill for vulnerability research evals

4640
BB
benchjack/benchjack
Developer tools

AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results

4740
DH
dhasson04/human-harness
API development

Harness for humans with ADHD

4740
RE
reorx/envops
Developer tools

A single-file CLI to inspect and manipulate .env files, designed to be safe by default: values that look like secrets are in all output unless you explicitly ask otherwise.

4540