Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers

A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript and C++.

MCP server to access Garmin data

Enable your AI agents to read, analyze, and modify Figma designs.

基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server

next-devtools-mcp is a Model Context Protocol (MCP) server that connects coding agents like Claude and Cursor to your running Next.js dev server.

We don't make AI smarter. We make it experienced. AI coding memory — the local-first memory + judgment layer for AI coding agents. Save up to 50%+ of AI tokens. Stop repeating yesterday's bug.

Agent-native knowledge engine — search, deep-read, and build knowledge bases from Markdown, PDF, DOCX, and PPTX.

The local runtime, CLI bridge, SDK, drop-in adapters, and wallet/auth/signing layer are MIT and readable here, so you can verify what runs on your machine rather than trust a black box.

MCP Server for Metasploit

MCP server for long term agent memory with Mem0. Also useful as a template to get you started building your own MCP server with Python!

The open-source tunnel that scales with you. Don't pay for idle time. Secure, Rust-fast, and Pay-as-you-go.

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero now; Obsidian, Apple Notes & local docs on the road).
Agent Skills

A collection of agent skills maintained by @mizchi, distributed via APM (Agent Package Manager).

在本地,快速找回过去 AI 对话中的答案。 Search the memory of your AI work. macOS · Windows · Linux

Production-ready configuration for Claude Code. One-command install of global instructions, multi-language coding rules (Python / TypeScript / Go), 21 curated plugins across 10 marketplaces, seven...

- rw-consulting-ppt:把行业报告、会议纪要、访谈笔记和半成品 bullet,转成 proof-object-first 的图片版咨询 PPT。 - ppt-to-editable:把单张 slide 图片、PNG/JPG、截图,或 image-only PPTX 转换成更可编辑的 PowerPoint。

image-to-code is a Codex skill for turning a selected UI image, screenshot, or Figma export into an adaptive code implementation, high-density transparent PNG assets, and optional editable Figma...

它不只帮你写“电影感、高清、光影漂亮”。 它会先判断这段素材是谁拍的,用什么设备拍的,在哪个年代拍下来的,再把设备缺陷、自然失误、环境声音和时间轴写进提示词。

A library of Agent Skills for , covering the full testing surface that an Android engineer touches, from unit-test fundamentals to ADB-driven E2E.

Agent Skills are small capability files an AI agent loads only when it needs them. This repo gives your agent and a that picks the right ones for you.

像 vibe coding 一样编辑你的简历:告诉 AI 你想怎么改,它直接修改网页简历,再一键导出为 PDF。

IEEE Transactions on Robotics (T-RO) , 2026

*\Other names and brands may be claimed as the property of others.

We welcome issues and pull requests for missing work on harness agents, agent skills, memory, self-improvement, agent RL, evaluation, and safety.