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

A type-safe implementation of the official Model Context Protocol (MCP) schema in Rust.

Building Agents with LLM structured generation (BAML), MCP Tools, and 12-Factor Agents principles

Clojure/ClojureScript library for making MCP server and client

A Mattermost integration that connects to Model Context Protocol (MCP) servers, leveraging a LangGraph-based AI agent to provide an intelligent interface for interacting with users and executing...

An MCP server that exposes AWS EC2 pricing data with an option to search by CPU, RAM, networking

ops-mcp-server is an IT operations management solution for the AI era. It achieves intelligent IT operations through the seamless integration of the Model Context Protocol (MCP) and Large Language...

OWASP MCP Taxonomy

A collection of MCP servers for mainland China services. 支持 MCP 的国内服务一览。

This project shows how to implement an MCP (Model Context Protocol) server of Apache ECharts.

A Model Context Protocol (MCP) server that enables AI assistants to interact with Tenzir—a data pipeline engine for security operations.

A lightweight wrapper around mcp-swift-sdk that integrates with LLM Swift libraries such as SwiftOpenAI and SwiftAnthropic to easily create your own MCP Clients in macOS applications.

This is an implementation of the Model Context Protocol (MCP) that integrates with Google's Gemini API to provide analytical thinking capabilities without code generation.
Agent Skills

My personal library of domain-agnostic agent skills, reused across every project. Small, composable, and hackable — works with any harness that supports skills: Claude Code, Codex, opencode, Cursor,...

AI got superpowers through Skills and MCPs. What about humans?

Reusable Agent Skills for single-page SEO auditing. Give it a URL — get a structured HTML report with actionable findings.

The easiest way to evaluate your Agent Skills. Tests that AI agents correctly discover and use your skills.

The central challenge in AI development isn't a lack of ideas, but the inconsistent process of turning them into robust, reliable skills.

An Agent Skill that reviews scientific and engineering manuscripts for writing quality, applying the methodology from Dr. Kristin Sainani's Writing in the Sciences course at Stanford (2012).

Vibe-coded products are ugly in the same specific way: indigo gradients, glowing cards, emoji everywhere, a mascot in every corner, ALL-CAPS stat-cards.

Codex skills for translating market information into testable investment research frameworks.

One command. 25 agent skills. Zero to profitable business.

On February 28th, 2026, DeerFlow claimed the 🏆 #1 spot on GitHub Trending following the launch of version 2. Thanks a million to our incredible community — you made this happen! 💪🔥

A collection of Claude Code skills for academic research workflows.

Write a SKILL.md, drop in some evals, and find out — empirically — whether your skill actually makes the model better at the task.