Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers

A lightweight way to use environment variables in your Cursor MCP server definitions.

An MCP server that lets AI agents read and draw on the Figma canvas — safely. Paired with a Figma plugin, it provides structured verification, safe-by-default drawing, and resilient multi-window...

PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human

Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.

Outcome-Based Persistent Memory MCP Server

Total recall for your terminal. Shared memory for your AI agents.

开源金融数据 MCP / HTTP 服务,面向 AI Agent、量化脚本和普通后端集成。

allows AI to control the Godot Editor to create scenes, nodes, scripts. It can debug script errors, debugger and output logs.

Google Ads Agent Skills for Claude — campaign analysis, account auditing, safe write ops, PPC math, and MCP server integration

The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

The ngrok alternative with .local domains, a scriptable CLI, and an MCP server for AI agents

Autonomous agents that find your clients on LinkedIn, on a server you own. An MCP server with 26 tools, so Claude or Cursor can run it. Self hosted LinkedIn outreach, AGPL, one command install.
Agent Skills

Agent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants

![NPM version][npm-url] ![Downloads][downloads-url] ![License][license-url] ![twitter][twitter] ![Discord Chat][discord-invite]

Lakehouse graph database for context assembly & multi-agent coordination Multimodal retrieval · Git-style branching · object-storage native

The MATLAB Agentic Toolkit brings trusted MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.

zvm (Zig Version Manager) lets you easily install/upgrade between different versions of Zig.

https://github.com/user-attachments/assets/023c0a9c-194a-45a9-bb88-ac8f16f5ffd5

为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and...

Reactive MobX Form State Management

for quasi-experimental designs in Python.

fly ai agent skill

Codex Skill for producing authorized digital-human talking-head videos with MiniMax overseas voice cloning and HeyGen Image-to-Video.

简单说,就是跟 Claude 说一句话,它会帮我从每天的新论文里筛一轮,挑出值得看的,再把重点论文读完、写成 Obsidian 笔记。日常不用记一堆命令,基本就是: