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

Open security engineering for code written by humans and AI agents. Discover. Repair. Verify.

A lightweight way to use environment variables in your Cursor MCP server definitions.

28 plugins and MCP servers for Claude Code — parallel exploration, iterative refinement, binary reverse engineering, structured decision-making, and more.

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...

MCP server to extract contents from a PDF file

Local-first creative studio with 37 model routes, transparent costs, local archives, and MCP access.

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.

Chat with AI, run tasks on autopilot, and manage your projects — all from one tab.

MCP server implementation for using Claude API with Claude Desktop, providing advanced API integration and conversation management.

- — MCP Protocol v2 (spec revision 2026-07-28, streamable HTTP) and experimental StrongDM API support are here — see the release notes.

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.
Agent Skills

Developer Kit is a for Claude Code that teaches Claude how to perform development tasks in a repeatable, high-quality way.

comprehensive skills based on the Anthropic Skills guide and our design and development philosophy

Zero-skill cinema. Senior-director prompts on autopilot.

I built an OpenClaw agent that manages Google Ads accounts through intent analysis instead of bid automation. All three layers — Read → Draft → Apply — are live and tested on real accounts.

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。

Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.

A two-pass pipeline for removing the signs of AI writing from outward-facing text, packaged as Claude Code Skills.

把 deepseek-v4-flash 或 deepseek-v4-pro 注册为 Codex 原生自定义子 Agent,并验证实际派发路由。DeepSeek V4 Pro 的 8·13 更新继续使用 deepseek-v4-pro API 标识。

这里收的东西,目标都很直接: - 能单独看懂 - 能尽快跑起来 - 能在真实工作流里省时间

上帝skill

This is the v3.0 rewrite of EasyApi. For the source code of stable v2.x releases, see the stable/v2.x.x branch.

⚠️ 本项目是作者为**而创建的个人学习项目,代码结构和实现均以探索为目的,。 :网页版 AI 对工具调用的支持参差不齐,稳定性和准确性均有较大局限,距离实用仍有差距。 OpenLink 通过浏览器扩展模拟用户操作来驱动网页 AI,,不适合作为日常 API 调用使用。请合理使用,勿滥用。