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
🚀 You're viewing the bleeding-edge dev docs! For other versions, check out the release/* branches.
Complete Docker-based AI operations infrastructure: Paperclip, n8n, Supabase, OpenClaw, ruflo, and MCPs
AgentMail has one MCP tool implementation, hosted at:
An MCP server that connects Claude Code to Perplexity Comet - enabling agentic web browsing, deep research, and real-time task monitoring.
Offensive security you run yourself — a local MCP workflow for authorized testing, in CI or against staging.
claude-mem-lite is a (also called long-term memory or cross-session context) system for — Anthropic's CLI coding agent.
MCP server for integrating LightRAG with AI tools. Provides a unified interface for interacting with LightRAG API through the MCP protocol.
AI 에이전트에게 라고 말하면, 흩어진 자료(웹 링크·PDF·대화 로그·텍스트)를 **하고, 관련 있는 노트끼리 **하고, **하고, **까지 해 주고, 원하면 **해주는 **이에요. (Codex엔 "플러그인 설치(/plugin)"가 없어서, 대신 저장소를 받아 codex mcp add로 **해 연동해요.)
Commands · MCP Servers · Plugins · Tools · Workflows · Agent Frameworks
swagger-mcp is a tool that reads a Swagger 2.0 or OpenAPI 3.0 specification and dynamically generates MCP tools at runtime — one tool per API endpoint.
小红书自动评论工具（MCP Server） 这是一款基于 Playwright 开发的小红书自动搜索和评论工具，作为 MCP Server，可通过特定配置接入 MCP Client，帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布智能评论等操作。
is a battery-included implementation of the framework with support for the multi-agent architecture. Ship autonomous agents that can reason, write, execute & iterate over code.
Agent Skills
Most code review looks at how the code is written. The Quality Playbook looks at what the code is supposed to do, and whether it actually does it.
Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.
Codex pets are tiny ambient companions for the work happening in Codex. This project adds one more layer to that idea: your pet can quietly show how much Codex capacity you have left, without turning...
A portable framework that reduces the cognitive load of working with AI coding agents — plan, build, verify, milestone by milestone.
A synthesis of Claude Code best practices, aggregated from Twitter.
一个中文文案「去 AI 味」skill，可以在 CoPaw、OpenClaw、Claude Code、Hermes，或者任何能读取 SKILL.md 并执行本地 shell 命令的 agent 里使用。
OpenCode port of academic-research-skills: 4 skills, 13 slash commands, 38-agent pipeline for academic research, writing, peer review, and revision
Generate beautiful dark-themed system architecture diagrams as standalone HTML/SVG files. Works as a Claude AI skill.
Direct work across Claude Code, Codex CLI, and Grok Build.
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.
*Tuned for (1M-token MSA context, native multimodal input) and (Agents Window, canvases, Design Mode, /worktree, /best-of-n, Await, MCP Apps). Written to stay useful across model changes.*
This is the official website for TuriX Computer-use-Agent