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

Early WebMCP proposal / implementation - since evolved and worked on by much more capable folks that develop the web: https://github.com/webmachinelearning/webmcp

Auto Browser is an MCP-native browser control plane for authorized workflows. It gives MCP clients, LLM agents, and operators a shared Playwright browser with human takeover, reusable auth profiles,...

NEW · Agent in the loop — Using AI to assess the risk of one-off operations. Read more → One Gateway Between Your Team and Your Infrastructure. hoop.

Find risky code, AI-agent vulnerabilities, and supply-chain issues before they ship. Website · Docs · Security & Data Flow · Benchmark · Pricing · Blog

Casbin AI & MCP security gateway for HTTP, online demo: https://door.caswaf.com

Agentic Capabilities and Package Manager

Buoy is a floating dev menu that ships inside your React Native app — every request, state change, render, and frame, live on the phone, on your desktop, and in Claude or Cursor.

Diagram generation for understanding codebases and system architecture using Nano Banana Pro.

MCP server wrapper for OpenAI Codex CLI that enables Claude Code to leverage Codex's AI capabilities directly.

adb-mcp is a proof of concept project to enabled AI control of Adobe tools (Adobe Photoshop and Adobe Premiere) by providing an interface to LLMs via the MCP protocol.

MCP configuration to connect AI agent to a Linux machine.

All in one vscode plugin for mcp developer
Agent Skills

把图片、图片型 PPTX、PDF 页面复刻成对象级可编辑的 PowerPoint。

Everything AI agents need to work with Dynatrace, starting with skills.

把一段内容,变成第一眼就想点进去、一眼能认出是「你」的小红书 / 公众号图文卡片。

Run Anthropic-style Agent Skills in Gemini CLI using the skillz MCP server.

Physics-first Flutter animations with a composable, timeline-driven API for building polished transitions, expressive UI motion, and reusable animation systems without wiring imperative controllers...

你可能需要花时间整理材料,把问题发给大模型,review大模型给的答案,再去尝试理解某些晦涩的概念,并判断大模型的回答是否足够可信。忙完以上的一切,还要忙着去除人机味

- — wrap third-party SDK clients (Stripe, Resend, AWS, etc.) with Effect using the "use" pattern: type-safe tagged errors, automatic tracing spans, config-based secrets, and clean dependency...

teamEvolver 位于 Agent 运行时之外,负责团队能力的持续进化与治理。它接收真实 Session 和领域资料,提取可追溯 Evidence,生成 Skill Candidate 或 Memory Change,再经过静态检查、True Replay、人工门禁、版本发布和受控分发形成闭环。

A framework-agnostic, git-native standard for defining AI agents

科研写作助手 (Research Writing Assistant)

Pi extension for async subagent delegation with truncation, artifacts, and session sharing

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge...