Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации 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.
The polished public release — native ComfyUI design system, live activity cards for every agent edit, and multi-tab support. Search in ComfyUI-Manager to install, or see the docs.
douyin-mcp 让 AI 同时读懂你的抖音创作数据和视频内容 本地运行 · 音轨文案按需提取 · 数据可追溯 · 面向个人创作者的 MCP Server
The MCP ecosystem has grown to 10,000+ servers, but discovering and installing them remains painful. Existing directories — Glama, PulseMCP, mcp.so — are all closed source.
This repo provides a reference implementation for creating a remote MCP server that supports the Streamable HTTP & SSE Transports, authorized with OAuth based on the MCP specification.
A simple MCP server that lets AI assistants help you with domain research - checking availability, looking up WHOIS info, finding expired domains, and more.
让 ChatGPT 通过 MCP 调用本机原生 Codex 会话的轻量 Windows 桥接器。
Open security engineering for code written by humans and AI agents. Discover. Repair. Verify.
](https://github.com/rust-mcp-stack/rust-mcp-sdk/actions/workflows/ci.yml) ](examples/hello-world-mcp-server-stdio)
A Docx document processing service based on the FastMCP library, supporting the creation, editing, and management of Word documents using AI assistants in Cursor.
Roblox Studio MCP server & plugin for Claude Code, Cursor, Codex, and Gemini. AI-powered scripts, terrain, assets, lighting, and bidirectional project sync.
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。
Agent Skills
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...
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.
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
Blueprint helps agents decide what to build, make focused changes, test them, get an independent review, and open pull requests.
AI coding agents are great at Python. They hallucinate in Spring Boot.
agnix Lint agent configurations before they break your workflow
Compatible with 13,000+ OpenClaw community skills — the largest AI agent skill ecosystem. One command to search and install.
一个 AI 编程助手 Skill（支持 Claude Code / Codex / OpenClaw），用自然语言描述你的设计需求，即可生成可直接运行的 Vivado / Vitis HLS / Vitis Unified / PetaLinux 脚本。覆盖从 HLS 算法到启动镜像的完整 FPGA/MPSoC 设计流程。
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly. Instead of making language models reconstruct molecular structure from cryptic strings, MoleCode lets...
This guide is intended for anyone with zero or a small background in programming, AI, or machine learning who wants to become a strong AI engineer in 2026.
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。
Deploy any Agent as an API via POST /run . The open, multi-model runtime for AI agents — works with any LLM, on any infrastructure.