Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
⚠️ This implementation stores OAuth credentials in ./mnt/mcp-creds/ which are currently committed to the repository. Proper OAuth flow for MCP servers is coming soon to the Agencii platform.
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
The AI Config Plaza. Stop configuring AI tools from scratch. Discover, share, and one-click install verified configurations for MCP servers, Agents, and Prompts.
Git-native API client with encrypted secrets.
Making AI coding assistants experts at Swift and iOS development.
本项目是一个本地 Streamable HTTP MCP Server，用于把 WMPFDebugger 暴露的裸 Chrome DevTools Protocol WebSocket 包装成 MCP 工具，辅助 Codex / Cursor / VS Code Agent 对已授权调试的微信小程序进行安全评估、证据采集和报告整理。
A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.
Linked API MCP server connects your LinkedIn account to AI assistants like Claude, Cursor, and VS Code.
A CLI tool for managing MCP servers configurations for MCP clients.
OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.
Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.
Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.
Agent Skills
A collection of Claude Code skills for building high-quality web animations and visual effects — built from real production work on a luxury watch brand site.
独立开发者信号雷达 Dashboard — 每天自动采集 19 个国内外信息源（App Store 新应用/GitHub 热榜/即刻圈子/36氪等），可视化浏览 + 收藏单条信息 + 中文翻译
McKinsey-grade market research decks for Claude Code — adversarially verified numbers, 15 McKinsey methodologies as executable workflow, multi-agent pipeline. 一条指令产出敢被挑战的麦肯锡级市场研究 deck。
A single-file CLI to inspect and manipulate .env files, designed to be safe by default: values that look like secrets are in all output unless you explicitly ask otherwise.
Pixel-perfect webpage cloning playbook. Paste a URL, get a measured Vite + React replica.
Harness for humans with ADHD
AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results
Refusal handling skill for vulnerability research evals
Playable 3D previz for AI video. Stage environments, act with keyboard controls (WASD), cut dynamic cameras, and feed exact motion into generative video models.
Sprint planning agenda: capacity, ready backlog, commit bar — no overfill.
Ultracode Codex plugin
Analyze your Claude Code session history to discover patterns that should become reusable skills.