Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human
Open-source, local-first memory and context for AI agents. One memory store, every agent.
AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems.
This project is a for automating and managing interactions on a Facebook Page using the Facebook Graph API.
A starting point for Claude Code to Codex collaboration
The purpose of the repo is to teach you how to make MCP servers. The target audience are non-technical with no real coding experience.
IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.
Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.
Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.
The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.
Visit the website MCP Tool Use Agent App to explore MCP Servers with sota agentic AI Search/Deep Research, Finance Data,Chart Creation, Excel Spreadsheet/Powerpoint usage.
MCP server implementation for using Claude API with Claude Desktop, providing advanced API integration and conversation management.
Agent Skills
is a fork of browser-use/video-use with the paid ElevenLabs Scribe dependency replaced by free, pluggable transcription backends.
A general-purpose for LLM-based code vulnerability analysis. Designed to be loaded by AI coding agents (Claude Code, OpenAI Codex, etc.
最近一直在看自动化渗透相关，尝试性写了几个框架，但是最后效果都不太满意。相反，之前当玩具写的 Skill 放在 Claude Code 里面，效果却出乎意料地好。
Give your AI agents the skill of visualizing data the way Edward Tufte intended.
大厂 AI 模拟面试官：基于 JD + 简历 生成专属面试问题，模拟更接近真实大厂风格的技术面、HR 面与薪资谈判。现已支持国内外大厂，如字节、腾讯、阿里、美团、Google、Meta、Amazon、Microsoft 等。
基于 Claude Skill 架构的智能数据分析平台。提供两套完整的技能体系：
A local OpenTelemetry ingest + TUI viewer for development, backed by SQLite. Point your app's OTLP/HTTP exporters at the local motel server and debug with real runtime evidence — from a terminal, the...
Eyes and ears for your AI agent. watch-cli composes yt-dlp + ffmpeg + a Whisper-class ASR into a single command that hands an agent the raw materials to "watch" any video: VIDEO + FRAMES +...
A sophisticated multi-agent research framework that implements OpenAI's Deep Research and Google Gemini's Deep Research capabilities using Claude Code's native features.
Started from a PyMol plugin, towards a comprehensive molecular design assistant.
A universal OpenCode workflow setup with specialized agents, skills, commands, and plugins for any software project.
X (Twitter) marketing skills for Claude Code and Codex: write tweets, threads, and replies in your voice, strip AI tells, and publish via Publora. Open source, MIT.