Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.
Real reap --agent output, run against a generated sample stack ( hero-fixture.sh ) — not anyone's install. The numbers further down are measured on mine.
Open security engineering for code written by humans and AI agents. Discover. Repair. Verify.
Agent Browser eliminates the need to configure each MCP server in every client. Connect your clients once to Agent Browser, and it will manage all your Server-Sent Events (SSE) MCP servers for you.
MCP-based assistant for busy people who are context switching
Point Claude at any audio file and it can tell you the key, tempo, dynamics, timbre, percussive character, stereo field, structural sections, and how the music evolves over time -- all from raw audio...
Thunderbird MCP gives an AI agent real control of the Thunderbird already running on your machine — your mail, your folders, your contacts, your calendar, your filters, and your actual settings.
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
makes it easy to deploy and serve Haystack Pipelines and Agents.
MCP server that scrapes public posts from X, LinkedIn and Hacker News in a local browser that is never signed in
(pronounced arc one [ɑːrk wʌn]) — Enterprise-ready MCP server for SAP ABAP systems. Secure by default, deployable to BTP or on-premise, and hardened with large unit/integration/E2E test coverage.
This repository contains a complete tutorial on how to create an MCP (Modular Computational Platform) client in Python using FastAPI.
Agent Skills
Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.
16 reusable skills and 6 agents for Codex, Claude Code, Cursor, OpenCode and Grok Bot: Humanizer, ML debugging, PR review and Skill Watch.
Claude Code skill for recursive research up to PhD level across any domain. Source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction.
minimalist/toy terminal agent harness written in bash
GitHub Knowledge Base Manager - A Claude Code skill for managing local GitHub projects
Your AI Platform Engineer. Self-hosted cloud built for AI agents — deploy, monitor, and operate your infrastructure through natural language. One VPS. One command.
Ultracode Codex plugin
Sprint planning agenda: capacity, ready backlog, commit bar — no overfill.
Playable 3D previz for AI video. Stage environments, act with keyboard controls (WASD), cut dynamic cameras, and feed exact motion into generative video models.
Refusal handling skill for vulnerability research evals
AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results
Harness for humans with ADHD