Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
MD2Card Markdown 转知识卡片 将 Markdown 文档转换为精美的知识卡片，支持多种风格
SpringAI和SpringAI-alibaba都发布了最新依赖稳定版本（之前基于快照版本需要设置Repository 如今已经不需要设置），如果遇到依赖下载不下来请按照最新的官方文档修改依赖版本，官网快照版本更新很快可能出现API冲突的情况 请以最新版本的API设计为准 推荐参考文档：https://java2ai.com/docs/1.0.0.
RimBridgeServer runs an MCP server inside RimWorld so AI agents and external tools can remotely control and observe a running game.
is the easiest way to connect any MCP client (like Claude or Cursor) with the browser using browser-use.
A secure Windows SSH workspace and MCP server for Codex, Claude Code, Cursor and other AI agents.
Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.
Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
A powerful Clojure-based MCP server built for querying DataScript and integrating with AI workflows.
Use ChatGPT Developer Mode as a local coding agent for your repo through MCP.
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
make your ai track the progress of your project without drifting off
Agent Skills
Speclip Skills：开源 AI 视频工作流、FFmpeg、字幕布局与视频剪辑 Agent Skills
人们往往是在看过具体画面之后，才真正知道自己在意什么。 所以 UI Skill Lab 先让团队看到 UI 长什么样，再让 Codex / Claude Code 按定稿实现、验收和修复。
Curated agent skills for CesiumJS development — 14 domain skills covering ~551 public symbols across the CesiumJS v1.143 API surface.
A collection of reusable AI agent skills for research, intelligence gathering, design, and content creation. Drop a folder into your agent's skills directory and it just works.
A collection of Claude Agent Skills for Shopify Liquid theme development. Three skills organized by scope — Liquid language fundamentals, coding standards, and accessibility.
可执行、可复核的缠论(缠中说禅) AI Agent Skill —— 先定级别·先认结构·先写失效点。研究/学习用途,不荐股。An operational 缠论 (Chan Theory) Skill for AI agents; research only.
A benchmark and generation framework for malicious agent skills.
Open-source legal AI agent skills for PKULaw, citations, and DOCX workflows
AstrBot skill for codeagent!
Run tests with statements and method calls removed to help identify broken tests
Custom proactive skills for Azure SRE Agent — governance, cost intelligence, architecture quality, AI workload posture
Fact-checking and disinformation detection skill for Claude and Codex