Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

影刀RPA:一个RPA低代码平台,一款人人可用的RPA自动化产品,能够将人从重复的劳动中解放出来。 影刀AI Power:一个AI低代码平台,能够快速创建AI智能体、AI工作流,帮助用户把AI用起来。

A Model Context Protocol (MCP) server that enables Claude to read and manipulate in real-time through a WebSocket bridge to a Figma plugin.

A high-performance code knowledge graph server implementing the Model Context Protocol (MCP). Indexes codebases into a structured AST knowledge graph with semantic search, call graph traversal, and...

The knowledge harness for AI‑native finance. Website · Docs · 中文

is an intelligent security agent designed to integrate seamlessly with AI coding assistants (like Cursor, GitHub Copilot, Claude Code, etc.).

MCP server for controlling Android emulators and devices via ADB. Gives AI assistants the ability to see, interact with, and debug Android apps — taking screenshots, tapping elements, reading logs,...

A Model Context Protocol (MCP) server implementation for the Deepseek R1 language model. Deepseek R1 is a powerful language model optimized for reasoning tasks with a context window of 8192 tokens.

A specialized Model Context Protocol (MCP) server for Svelte 5 frontend development, providing curated knowledge, code examples, and intelligent assistance for modern Svelte development with runes,...

is an advanced Model Context Protocol (MCP) server that empowers AI assistants to generate high-quality images and vector graphics.

Memorizer is a .NET-based service that allows AI agents to store, retrieve, and search through memories using vector embeddings.

A Model Context Protocol (MCP) server implementation of Atom of Thoughts, a decomposition-based reasoning framework.

A Model Context Protocol (MCP) extension for DuckDB that enables seamless integration between SQL databases and AI assistants like Claude.
Agent Skills

Vite plugin that reimplements the Next.js API surface — deploy anywhere

一个 的 PPT 工作流 skill,用来把一个模糊的 PPT 需求,逐步推进成:内容基底、风格预览、定稿规划,以及后续可执行的生成流程。

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

"To achieve great things, two things are needed: a plan and not quite enough time." - attributed to Leonard Bernstein

飞鼠格式 FlyingMouse Format - Windows 免费文件格式转换工具(离线可用,内置 FFmpeg/LibreOffice/Poppler/Tesseract)。图片/文档/表格/PPT/PDF/音视频/WPS 格式互转 + OCR + 批量转换;音频仅支持普通格式。作者:牢蜂(LaoFeng)|仅供个人免费使用,禁止商业售卖/转卖/套壳

Plugin-skill wrapper around Z4nzu/hackingtool. Runs locally on any OS — native Bash on Linux/macOS, WSL on Windows, or purpose-built Docker images (instrumentisto/nmap, projectdiscovery/nuclei,...

Due-Process Review for Bounded LaTeX Revision

Reproducible skills, regression fixtures and evaluation workflows for coding agents maintaining ecommerce codebases.

一个面向 claude code / Codex / OpenClaw 的跨境电商和国内电商通用视觉创作 Skill。GPT-Image-2 上线以来,电商圈已经被刷屏了。图像生成的边界,如今又被推了一大步。下面是我精选的 25个高质量案例,涵盖纯色底产品主图、场景化生活图、平铺图、电商详情图、真实场景等等,全部配完整提示词,都可以利用 GPT-Image-2 API生成最终效果。

Universal memory layer for AI Agents

Agent Skills for Google products and technologies

Meteor, the JavaScript App Platform