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

— This project is under active development. APIs and tool behavior may change between releases. Use at your own discretion. Feedback and bug reports welcome via GitHub Issues.

An MCP server that lets AI assistants (Claude, Cursor, VS Code, …) drive your Electron app: click buttons, fill forms, take screenshots, read console logs, and run JavaScript inside it — all over the...

A Model Context Protocol (MCP) server for DigiKey's Product Search API using FastMCP.

This is a Model Context Protocol (MCP) server that provides integration with rust-analyzer, allowing AI assistants to analyze Rust code, get hover information, find definitions, references, and more.

💰 Candidates using Career Agents' ATS Resume Studio, STAR Interview Lab, and FAANG Company Tracks successfully cracked top-tier software engineering roles — securing compensation offers up to !

Servidor MCP (Model Context Protocol) para integração com o sistema PJE (Processo Judicial Eletrônico) brasileiro, com suporte completo a certificados digitais A1 e A3.

Manage your MCP (Model Context Protocol) server definitions in one place and apply them to supported agents.

A comprehensive Model Context Protocol (MCP) server for stock analysis and trading insights. This server provides advanced stock screening, fundamental analysis, insider trading data, social media...

A powerful Model Context Protocol (MCP) server that provides AI-powered image and video analysis using Google Gemini and Vertex AI models.

A Model Context Protocol (MCP) server for programmatic diagram generation using Draw.io (Diagrams.net). This server generates Draw.io XML directly — no browser extension or Draw.io instance required.

A Model Context Protocol (MCP) server that provides AI assistants with structured access to your Logseq knowledge graph.

An open-source MCP server that turns LLMs into condition monitoring assistants for reliability engineers. Its core design rule: .
Agent Skills

Local-first harness for agent-built codebases. Humans steer, agents execute, maestro is the substrate.

一句话:输入一个基金代码,Agent 把基金经理 8 年的每一笔买卖翻出来,拿 12 个月后的真实走势逐笔验对错,最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测,全都有。

A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...

Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.

The #1 Terraform skill for Claude Code and Codex, measured by GitHub stars.

The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.

An that runs end to end on the Atlas Cloud API + local ffmpeg, usable by any coding agent (Claude Code, Codex, etc.). You give it a one-line topic; it gives you an mp4.

Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.

Elves is an open-source Agent Skill for handing planned development or research work to a separate worker without locking the run to one model provider.

The #1 Kubernetes skill for Claude Code and Codex, measured by GitHub stars.

是由同花顺官方提供和维护的 A股金融数据服务,面向 AI Agent、量化研究者和应用开发者。

Everything you need to know about OpenCode — from your first prompt to custom agents, skills, plugins, and MCP integrations.