Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
下载 AI-Browser-MCP-x64-v3.0.0.zip（~157MB），解压运行 AI-Fbowser-Mcp.exe。在 Cursor / Claude 里说句话，**自动执行：采集数据、逆向 POST 加密、CDP 定位签名算法、自动填表。
🦞 A Digital Life Embryo for your MCP Client. An intelligent micro-kernel with Nociception, Memory Apoptosis, and a Curiosity Drive.
蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.
一个 MCP Server 连接所有数据库，数据库 MCP Server 的瑞士军刀。
is a remote MCP service provided by Aqara Agent. It lets MCP-enabled AI applications securely connect to Aqara smart home capabilities.
Local-first PC activity recorder for Windows. Captures screenshots, accessibility text, UI events, clipboard activity, and optional audio transcription into a local SQLite database — then exposes...
AI-native video editor driven as a local MCP server. Linux + Windows: ingest, transcribe, edit graph, melt/ffmpeg render, QC.
XCode CLI MCP: Convenience wrapper for Xcode CLI tools & iOS Simulator. Progressive disclosure of tool responses to reduce context usage. Use --mini param for build-only with tiny context footprint.
The only MCP Server you need. Connect any MCP host with the tools you use daily through our no-code, secure integration hub.
把 Google Antigravity 的 Nano Banana 生图能力封装成 MCP Server，让任何支持 MCP 的 AI 客户端都能画图。
基于 SunnyNet 中间件和 SunnyNetTools 抓包工具扩展的 MCP Server
"Reduce system lag by 99%, eliminate loading times, and cut token costs by 90%."
Agent Skills
AI assistant for Obsidian with , , and powered by Google Gemini.
基于 Claude Code Agent Skills 的 AI 提示词工程系统 - 10个场景化专家，自动路由，精准生成优秀提示词 ## 项目简介 这是一个基于 Claude Code Agent Skills 技术的智能提示词生成系统。通过自然语言请求，系统会自动路由到对应的专业 Skill，帮助用户写出高质量的 AI 提示词。
基于 LangGraph 和 DeepAgents 框架的智能体 Skills 能力演示项目。
基于 GJB 438C-2021 [5.10] 标准模板的 SRS 文档自动生成
Generate and review MiniMax H3 video prompts from user goals and multimodal references.
面向 AI Agent 的精选 Skills 集合。每一个 skill 都在日常工作中实际使用、迭代、踩过坑，覆盖内容创作、设计视觉、工具集成、合规文书等场景。
Command-line tool for distributed LLM inference benchmarks on SLURM clusters using TensorRT LLM, SGLang and vLLM.
Ready-to-run training recipes for reinforcement learning (GRPO, DAPO, GSPO, CISPO), preference optimization (DPO, ORPO), and supervised fine-tuning (SFT) on Fireworks.
A git custom command that enhances Git's native worktree functionality with interactive features, automation, and repository migration capabilities.
先归根，再分化；先明道，再造物。 从混沌需求出发，生成可运行、可验证、可进化的 Agent Skill。
"Writing doesn't just communicate ideas; it generates them."