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

OpenCrab is the public integration repository for the LocalCrab ontology factory and the OpenCrab hosted ecosystem at opencrab.sh.

MCP server that lets Claude Code pause mid-task and ask a human a question via Slack — then resume once you reply.

Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses Cloudflare.

An experimental way to connect MCPs to Pi using Code

A Flutter MCP to interact with your flutter app

DEBUG-only iOS SDK that embeds an HTTP + WebSocket server in your app: browser console + MCP bridge for inspecting files, databases, network, logs, and the live screen. Zero third-party dependencies.

@amap/amap-maps-mcp-server

Unofficial Mi Fitness data export to local SQLite, CSV and JSON, with a local stdio MCP server. 小米运动健康数据导出;实验性,兼容性依设备与地区而异。

— DSGVO, BFSG Barrierefreiheit und Einwilligungs-Widerruf. Auf Basis echter Gesetzestexte via rechtsinformationen.bund.de MCP.

tradingview mcp which connect claude code via chrome devtools protocol

Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, docs pages, GitHub examples, MCP output, or large MCP schemas.

AnalyticDB for MySQL MCP Server is a universal interface between AI Agents and AnalyticDB MySQL. It provides two tool groups:
Agent Skills

PostHog context and skill assembly for AI agents and LLM tasks

Zerion for AI agents and developers: hosted MCP docs, wallet-analysis skill, and a JSON-first CLI.

PowerSkills are some Agent Skills for power system analysis. This repository provides AI agents with specialized knowledge and instructions for performing power system simulations, analysis, and...

Migrate Claude Code skills and Agents to Open AI Codex native skills and agents. Semantic mapping preserves original behavior, classifies migration risk (MECHANICAL / MANUAL / REFACTOR), validates...

大模型技术快速演进,正在改变 CTF 与代码审计的传统工作方式。当前模型对源码的理解能力已经相当成熟,不少团队已将 LLM 引入 CTF 解题、Web 代码审计与漏洞挖掘流程。

Single-file agent goal ledger for Claude Code and Codex CLI - pairs with /goal mode

Run, deploy and monitor CLI agents in secure cloud sandboxes.

Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.

Codex skill for e-commerce product visuals from product and reference images

Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants

A complete catalog of Agent Skills (agentskills.io) for Zephyr RTOS development.

Enables LLM to use a cli environment.