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
Lean Theorem Prover MCP
An MCP for WireShark (tshark). Empower LLM's with realtime network traffic analysis capability
MCP server for Claude to access Outlook data via Microsoft Graph API
An implementation of Model Context Protocol (MCP) server for Argo CD.
Local-first Apple Health MCP server. Lets AI assistants answer questions about your sleep, workouts, activity and heart data from a local export.
Things.app MCP Server
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure.
A docker MCP Server (modelcontextprotocol)
Official SonarQube MCP Server for code quality and security in AI agents
An MCP for Godot that lets you create and edit games in the Godot game engine with tools like Claude
vs-punk: ADT to MCP bridge - Vibe code in ABAP / AMDP
TDA - Thread Dump Analyzer (for Java). Analyze your Thread Dumps with a GUI or use it as MCP Server.
Agent Skills
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki.
Harness engineering beginner tutorial, from 0 to 1
OpenShell is the safe, private runtime for autonomous AI agents. It provides sandboxed execution environments that protect your data, credentials, and infrastructure — governed by declarative YAML...
Formerly known as the ODIN Claude Plugin. The repo URL stays the same; the brand has matured.
Claude Code skills and sub-agents for .NET Developers
Personal dotfiles with modern shell tooling, optimized for Laravel/PHP development. Features fast startup times, smart directory navigation, and modern CLI tools.
The open-source AI workbench for scientific research
In its final days before getting removed from the Subscription, Claude Fable 5 distilled its own way of approaching problems into a set of skills any model can run: classify the ask before touching...
is an open source agent microharness, a complete agent harness with a core of about 10K lines of Bash.
the runtime your coding agents live on
Think package.json, requirements.txt, or Cargo.toml — but for AI agent configuration.
is an open-source, LLM-powered knowledge framework built for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning.