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
Samples for MCP servers on Windows
A powerful Model Context Protocol (MCP) server implementation for seamless Apollo.io API integration, enabling AI assistants to interact with Apollo.io data.
Complete agent workflow: user input → tool approval → execution → streaming response
A generic mcp server fuzzer
🐉 The fast, PHP way to build MCP servers
Automated AI code reviews powered by Claude Code. Assign a reviewer on your merge request — Claude reviews the code, tracks progress in real time, and follows up when you push fixes.
is a modular library for building Model Context Protocol (MCP) servers using NestJS. It provides decorators, modules, and integration patterns to expose MCP resources, tools, and prompts in a...
A Kubernetes-focused Model Context Protocol (MCP) server built in Go. It exposes Kubernetes operations as MCP tools and supports stdio, sse, and streamable transports.
Community version of MaxMCP-Dev-main
mcp_dart is a dual-era Dart and Flutter SDK for MCP clients, servers, and AI hosts. It implements the complete core client/server wire surface of the locked MCP 2026-07-28 specification, retains the...
A Rust framework that bridges clap command-line applications with the Model Context Protocol (MCP)
Cross-platform C SDK for Model Context Protocol (MCP), in modern🚀 C23.
Agent Skills
The Best AI Agent Framework for Agent Collaboration.
The open sharing protocol for the agentic era. A Linux Foundation AI & Data Project
Agent Skills
- : Turn your idea into a video using your coding agent. - : Edit and animate using drag and drop. - : Connect to data, and manage complexity with code.
Reverse-engineer any design system into a Claude-ready skill. Pure static analysis. No AI. No API keys.
Craft AI-driven interface effortlessly🤖
Official Pulumi Agent Skills for writing, migrating, and operating infrastructure with AI coding agents
- [2026/05/01] 🔥 (📃Paper) has been released.
A Claude Code of the skills we share at AI Builder Club for building : agents that get triggered on their own, pick up work, ship it, verify it, and log what they learned, so the work compounds...
"To achieve great things, two things are needed: a plan and not quite enough time." - attributed to Leonard Bernstein
Commonplace studies how agentic systems can change after deployment through inspectable knowledge artifacts.
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.