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。
MCP Servers

MCP Server with ArcGIS Pro Add-In

Manage Tampermonkey userscripts via Model Context Protocol (MCP). List, read, write, patch, and delete userscripts directly from AI-powered development tools.

A fully vibe-coded, experimental, MCP server to control firefox

A Model Context Protocol (MCP) server for running AWS Athena queries. This server enables AI assistants to execute SQL queries against your AWS Athena databases and retrieve results.

Live Web Access for Your Local AI — Tunable Search & Clean Content Extraction

This is an enhanced version of the excellent cyanheads/obsidian-mcp-server with additional features specifically tailored for remote Claude.

ExternalAttacker is a powerful integration that brings automated scanning capabilities with natural language interface for comprehensive external attack surface management and reconnaissance.

Claude Memory MCP Visualizer

MCP server for controlling OriginLab Origin Pro via COM automation — enables AI assistants to create worksheets, plot graphs, style figures, and run curve fitting

This is a Model Context Protocol (MCP) server that provides tools for interacting with Proxmox VE infrastructure.

Obsidian plugin bridging your vault with the RuVector Brain — DiskANN semantic search, AIDefence scanning, pi.ruv.io federated sync, DPO pairs, agent-shared MCP backend.

This MCP server provides access to Siri shortcuts functionality via the Model Context Protocol (MCP). It allows listing, opening, and running shortcuts from the macOS Shortcuts app.
Agent Skills

A that runs a free, open-source Google Maps scraper and lets drive it on autopilot — give Claude a city + a business type, get back a clean list of businesses (name, address, phone, website, rating,...

A self-improving prompt optimization skill for Cursor and Claude Code, derived from Andrej Karpathy's autoresearch pattern.

A comprehensive collection of 79 Claude Code skills for academic research in economics, finance, and social sciences — organized by workflow stage.

Spawns 8 parallel specialist agents to audit your codebase across vulnerability detection, authorization verification, secret scanning, supply chain analysis, IaC security, threat intelligence...

你的老板开会总爱追着问 impact、风险和 owner? 他一句“这个先别做”背后其实有一整套判断标准? 你总感觉自己不是不会做事,而是不知道该怎么向上同步、怎么报风险、怎么要资源?

一个 Claude Code skill:把一份参考 Word (.docx) 的排版样式(字体 / 字号 / 缩进 / 行距 / 对齐 / )**复刻到新内容上。

A production-ready skill that enables Claude Code to build Android applications following Google's official architecture guidance and best practices from the NowInAndroid reference app.

MyCodeAgent is a local-first, single-agent Python coding harness. It supplies the reliable machinery around an OpenAI-compatible model: one controlled loop, project-confined tools, permission...

Fable5 구조를 넣은 Sonnet이 Opus와 블라인드 테스트에서 사실상 비겼다!! 그것도 답 1건당 비용 3분의 1로!! Sonnet + Fable 5 structure virtually tied Opus in a blind test — at 1/3 the cost per response. (bench/)

A comprehensive collection of skills for Claude Code, Anthropic's official CLI for Claude.

novel-control-station 不是一个“帮你写几段正文”的普通小说技能,而是一套面向中文长篇小说的创作控制中枢。

A skill catalog that won't let you spend 6 months on a research gap that's already closed, isn't a real contribution, or isn't feasible.