Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
Static analysis that finds the mess vibe coding leaves behind — dead code, duplicated logic, scaffolding artifacts, and disconnected functions — across 16 languages.
Connects MCP clients to Roblox Studio's edit context and live server/client VMs. Agents can modify places, run Luau inside active playtests with the same module state as game scripts, automate solo...
MCP server for web search powered by Google AI Mode (Gemini). Free, unlimited, no API key.
The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.
Junjie.M tool https://github.com/junjiem/dify-plugin-tools-mcp_sse issues
- Node.js (v18 or higher) - npm (comes with Node.js) - Cursor IDE (recommended)
Qwen3-30B-A3B-Thinking via OpenRouter plus multi-source web synthesis with citations.
The missing link between AI models and the real‑world web: one API that delivers clean, structured data from any site.
Supports (one database per minor stream), , and . Works with Claude Code, Cursor, Windsurf, or any MCP-compatible AI tool. No Unity installation required. See the supported versions.
An MCP server that gives AI agents first-class access to your running Neovim session. It connects through Neovim's native msgpack-RPC socket — no plugins required.
MCP server for . Index your codebase once, then search using natural language.
The Model-Context-Protocol (MCP) gives LLMs a way to call APIs and thus access external systems in a well-defined manner.
Agent Skills
This project is under active development and evolving rapidly. Contributions, feedback, and discussions are warmly welcome.
Agent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants
A high-performance Markdown parser and renderer for Angular, React, Svelte, Vue, HTML and ANSI.
A collection of Codex/agent skills for planning, documentation access, frontend development, and browser automation.
简单说，就是跟 Claude 说一句话，它会帮我从每天的新论文里筛一轮，挑出值得看的，再把重点论文读完、写成 Obsidian 笔记。日常不用记一堆命令，基本就是：