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 workshop using Golang
ToyAIKit is a minimalistic Python library for building AI assistants powered by Large Language Models (LLMs).
Model Context Protocol server written in Scala
BloodHound MCP (Model Context Protocol) is an innovative extension of the BloodHound tool, designed to enable Large Language Models (LLMs) to interact with and analyze Active Directory (AD) and Azure...
Links to samples, tools, and resources for building and integrating Model Context Protocol (MCP) servers on Azure using multiple languages
MCP桥接浏览器插件，让网页端的AI具备调用MCP工具的能力
A Model Context Protocol (MCP) server that provides programmatic access to the Supabase Management API.
A full write-up can be found here: https://blog.securitybreak.io/building-a-threat-intelligence-genai-reporter-with-orkl-and-claude-a0ae2e969693
Zero burden, ready-to-use Model Context Protocol (MCP) server for interacting with MySQL and automation. No Node.js or Python environment needed.
This Model Context Protocol (MCP) server provides a tool for scraping webpages and converting them to markdown format using Puppeteer, Readability, and Turndown.
A headless Ghidra server that speaks MCP (Model Context Protocol), giving AI agents full access to deep reverse-engineering workflows: program lifecycle, disassembly, decompilation, patching, types,...
Native dialog system for MCP (Model Context Protocol) servers.
Agent Skills
A curated list of awesome OpenAI Codex plugins, skills, and resources.
Packages OpenClaw for nix.
👆 showing how CLAUDE.md guides AI pair programming in Claude Code.
llmdoc is a doc-driven workflow for both Claude Code and Codex.
SkillOps = Validate, manage, and deliver skills at scale.
We've all been there: asking Claude to use Entity Framework, only to get EF6 patterns in a .NET 8 project. Explaining to Copilot that Blazor Server and Blazor WebAssembly aren't the same thing.
是一个**，支持 Claude Code、Codex、Cursor、GitHub Copilot、Gemini CLI 等主流 AI 编程工具。
面向法律人的 Skills 集合。
Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
A structured development workflow for AI coding agents that brings , , and (only humans should) to AI-assisted development. TRIP helps you enter flow state and eat features like buttered noodles.
Expose your local web server to the internet with a public URL.
Repo-Docs: Keep up with the code your agents write. An evidence atlas for agent-built code. Vibe coding makes code move faster than memory.