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
Kernel-level sandboxing for LLM agent tool calls made through the Model Context Protocol (MCP).
"The question is not what you look at, but what you see." — Henry David Thoreau
Ollama MCP is a tool for connecting Ollama-based language models with external tools and services using the Model Context Protocol (MCP).
mcp4k is a compiler-driven framework for building both clients and servers using the Model Context Protocol (MCP) in Kotlin.
This is a Model Context Protocol (MCP) server that converts Figma designs to React components. It provides tools for fetching Figma designs and generating React components with TypeScript and...
The Model Context Protocol enables AI models to interact with external systems through tools, resources, and prompts.
A TypeScript library that bridges OpenAI's Realtime API with Model Context Protocol (MCP) servers, enabling voice-driven tool execution.
A conversational AI agent and voice assistant application built with the LiveKit Agents framework, capable of using Model Context Protocol (MCP) tools to interact with external services for SRE and...
A collection of AI-assisted automation tools for and , built around the Model Context Protocol (MCP).
Reference servers that demo how authentication works with the current Model Context Protocol spec.
This repository demonstrates building an MCP (Model Context Protocol) server with HTTP transport and JWT authentication, progressing through iterative steps.
飞书MCP服务器是一个基于Model Context Protocol的服务，提供飞书API集成，使AI模型能够轻松与飞书服务交互。
Agent Skills
A skill that gives the AI specialized guidance for writing, debugging, and maintaining tests in . Use it in any repo where you work with Playwright so the assistant follows best practices for E2E,...
UnrealCV: Connecting Computer Vision to Unreal Engine
This project is currently in the testing stage. Star it, try it, and feel very welcome to share suggestions and feedback.
这是一个用 Python 从零构建 AI Agent 的教学项目。项目核心是 build-agent-example/：从一次模型调用开始，后续每一步都保留前一步的全部代码和能力，逐步加入循环、history、system prompt、工具、skills、memory、规划、子代理、团队协作、MCP 和 hooks。
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
Mac OS X utility to un-archive .webarchive files (like when saving from Safari)
Browser automation agents forget everything between runs. Same site, same page structure to figure out, every single time. Wasted time, wasted tokens.
给 Gemini CLI、Claude Code、Codex 等 AI 编程助手使用的 HarmonyOS NEXT 离线参考技能库。
⚠️ qu-ai-wei 仍在迭代，规则、分类、API 都可能变动。欢迎提 issue / discussion / PR 反馈。 繁體有自己的 AI 腔特征、用字偏好、排版规范，规则需要单独维护，留给后续版本。
我建了一个 （付费），聊 AI 短剧的工作流、工具和实操。 有兴趣的加我：，添加时**。
LightClaw: The Real Lightweight AI Assistant
Feishu knowledge base export, writing, and cloud-space management tool with Markdown, WeChat import, CLI, TUI, and OAuth 2.0