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
Control DaVinci Resolve from AI assistants (Cursor, Claude) via MCP. Full read + write bridge with 44 tools and local Whisper transcription.
MCP Code Example
"The Most Comprehensive WordPress MCP Server - 145 Tools, Zero Compromise!" 🖤
MCP server for ROS to control robots via topics, services, and actions.
- Node.js (v18 or higher) - npm (comes with Node.js) - Cursor IDE (recommended)
This local proxy package is deprecated in MetaMCP's 2.0 all-in-one architecture.
MCP server for Jupyter Notebooks and JupyterLab
MCP Server to make line-based edits to a file.
Manage test cases, execute manual or automated tests, debug issues, and even fix code—directly within tools like Cursor, Claude, or any MCP-enabled client, using plain English.
One config to rule them all. Practical standard layer for multi-LLM development.
MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.
MCP server for Google search and page fetching using headless Chromium
Agent Skills
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
provide for AI agents, helping them build complete automated document workflows. Before large-model reasoning begins, ComPDF Skills can handle document parsing, OCR, data extraction, and structured...
Codex-first toolkit for open-source maintainers: AGENTS.md, skills, automation, and verification workflows.
用 GitHub 打造 AI 智能体：长期记忆 + AI Agent 技能包（UI/UX、图片生成、SEO）+ GitHub Actions 自动化 + Copilot 编程 Agent，支持 Vibe Coding 快速孵化项目。
micro-agent orchestrator for local agents
AI agents should not give project advice from vibes.
Lightweight AI assistant framework in Rust with pluggable LLM providers (Ollama, llama.cpp, vLLM), built-in tool calling, agent skills, and customizable system prompts.
This repo contains the (the heavy, browsable skill files).
Running 5 AI agents in parallel is easy. Making them not break each other's code is the hard part.
for creating, directing, validating, and delivering image, video, audio, voice, music, 3D, avatar, and interactive media.
🧠 plan · 🔨 implement · 🔍 review · ✅ QA gate · 🚢 merge Thirty-five agent skills that run a full PR pipeline. Install them into any repo, with any coding agent.
A structured Agent workflow for CUMCM, MCM/ICM, and Diangong Cup — designed to keep a 72–96 hour modeling project coherent from the first decision to the final submission.