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

Search a codebase by meaning, then follow the result into definitions, callers, and dependency paths.

MCPSafari: Native Safari MCP Server for AI Agents

Deploy anything on your own servers. Connect a server, click deploy, done. MIT licensed and free to self-host forever.

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

A live layered dependency map for bottom-up development — MCP server + terminal pane for Claude Code, Codex CLI and any MCP client.

Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.

Total recall for your terminal. Shared memory for your AI agents.

A domain harness for AI-assisted mobile development and testing. Unified device logs, network traffic interception, and UI automation — exposed through APIs and MCP tools that let AI agents...

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

An MCP server that lets AI agents read and draw on the Figma canvas — safely. Paired with a Figma plugin, it provides structured verification, safe-by-default drawing, and resilient multi-window...

allows AI to control the Godot Editor to create scenes, nodes, scripts. It can debug script errors, debugger and output logs.

This MCP server enables dynamic creation, editing and saving of PowerPoint presentations. Built upon the MCP and using the python-pptx library, it provides a flexible interface to add slides, images,...
Agent Skills

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

Main Agent spawns Subagents like a hen with her chicks 🐔🪺🐦

Blueprint helps agents decide what to build, make focused changes, test them, get an independent review, and open pull requests.

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...

Compatible with 13,000+ OpenClaw community skills — the largest AI agent skill ecosystem. One command to search and install.

Deploy any Agent as an API via POST /run . The open, multi-model runtime for AI agents — works with any LLM, on any infrastructure.

中文内部技术写作的 agent skill。约束设计文档、评审稿、postmortem、分享稿等场景的语气、句法、结构,让产出贴近技术汇报,避开营销稿和散文气质。

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

mim·e·o — to reproduce, to copy, to imitate.

A collection of skills for AI agents. Follows the Agent Skills specification. This repository is my personal skill testing ground.

ProductSpec is the open standard for product intent. It acts as a Product Harness for AI-native software work: what to build, what not to build, how to prove completion, and when intent changes.

Community-driven agent skills for AI coding assistants