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。

12488件

MCP Servers

6054 件
MI
merozemory/ida-multi-mcp
Developer tools

Multi-instance IDA Pro MCP server — analyze multiple binaries simultaneously through a single MCP endpoint.

324 056
EM
evalstate/mcp-hfspace
Developer tools

MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.

387 056
AG
assafelovic/gptr-mcp
Developer tools

MCP server for enabling LLM applications to perform deep research via the MCP protocol

354 056
DN
disler/nano-agent
Developer tools

Watched how we used GPT-5 and Claude Code with nano-agents here.

205 056
EB
eyalzh/browser-control-mcp
Developer tools

MCP server paired with a browser extension that enables AI agents to control the user's browser.

304 056
ER
elonjask/reqable-mcp
Developer tools

Reqable MCP Server exposes local Reqable capture traffic to MCP clients (Windsurf/Cursor/Claude/Codex).

235 056
JJ
jgravelle/jdocmunch-mcp
Developer tools

Most AI agents still explore documentation the expensive way:

201 056
KM
kerlenton/mcpsnoop
Developer tools

A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.

324 056
CS
cnych/seo-mcp
Developer tools

A MCP (Model Control Protocol) SEO tool service based on Ahrefs data. Includes features such as backlink analysis, keyword research, traffic estimation, and more.

253 056
SS
silung/scholar-search-mcp
Developer tools

An MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and retrieve academic paper metadata.

235 056
VC
veelenga/claude-mermaid
Developer tools

MCP server for rendering Mermaid diagrams in Claude Code with functionality and a built-in skill for expert guidance.

200 056
AM
aws/mcp-proxy-for-aws
Developer tools

The package provides two ways to connect AI applications to MCP servers on AWS:

323 056

Agent Skills

6434 件
QN
quillai-network/quillshield_skills
Developer tools

AI agent skills for advanced smart contract security auditing. These skills teach AI agents (Claude, Cursor) the QuillShield methodology for detecting vulnerabilities that traditional static analysis...

11570
GA
gokapso/agent-skills
Developer tools

: These skills are in active development and subject to rapid change.

14370
MY
mapleshaw/yt-dlp-downloader-skill
Developer tools

A Cursor Agent Skill for downloading videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp.

19270
DS
dabit3/skill-audit
Developer tools

Audit agent skill definitions for security, completeness, and compatibility across Codex, Claude Code, OpenClaw, and more

4770
WW
wenziai/wenzi-xhs-agent-skills
Code review

文子的小红书 Agent Skills:从账号定位、选题标题、真人化改稿、图文规划到排期复盘的一套可安装工作流。

15470
AB
agihunt/blurt
Developer tools

Show it. Say it. Your AI gets it. Record your screen and talk — your coding agent turns it into bugs, ideas and to-dos, with the exact frames marked. 口喷鸡:边看边喷,AI 全懂。

4170
BI
blacktop/ipsw-skill
Developer tools

An AI agent skill for Apple firmware and binary reverse engineering using the ipsw CLI tool.

6970
AS
alexbybye/scut_cs
API development

:计算机类、计算机科学与技术、网络工程、信息安全等。 :SCUT, 华南理工大学, 计院, 历年卷, 期末复习, 实验报告, 课设, 华为智能基座。

9970
JQ
joeseesun/qiaomu-skill-publisher
Developer tools

Publish agent skills to GitHub with attractive README checks, repo-name/skill-name safety, and real npx skills install verification.

4070
AJ
anhvt52/jetpack-compose-skills
Developer tools

An agent skill for writing, reviewing, and reasoning about modern Android UI code using Jetpack Compose.

9470
ST
skywain/trip-planner-skill
Developer tools

Agent skill for AI trip planning (Claude Code · Codex · Gemini CLI · Cursor · Copilot · any SKILL.md agent) — verified, bookable itineraries: hour-by-hour days, real flight prices, offline KML maps,...

4170
CA
contextjet-ai/awesome-llm-observability
Analytics & monitoring

50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

4070