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

MCP Server Starter gives you a basic structure to run local tools with Cursor, Claude, and others using the MCP standard.

You've got a Paperless-ngx instance. You've got hundreds (thousands?) of documents. You know you should tag them, set correspondents, organize them properly. But who has time for that?

A Model Context Protocol (MCP) server that provides hourly and daily weather forecasts using the AccuWeather API.

A Model Context Protocol (MCP) server using the TypeScript SDK for LinkedIn integration. Allows an AI agent (e.g. Claude) to authenticate with LinkedIn and share posts or links.

MCP Server & CLI for keyword research, domain analytics, backlinks, traffic analysis, and competitive intelligence.

Advanced Ansible Model Context Protocol (MCP) server in Python exposing Ansible utilities for inventories, playbooks, roles, and project workflows.

A Model Context Protocol (MCP) server for interacting with the Scryfall API. It provides tools to look up Magic: The Gathering card details, card rulings, and price information.

This project provides a dedicated MCP (Model Context Protocol) server that wraps the @google/genai SDK (v0.10.0).

A Model Context Protocol (MCP) server for Google Photos integration, enabling Claude, Gemini, and other AI assistants to photos from your Google Photos library.

The Membrane MCP Server is a Model Context Protocol (MCP) server, it provides actions for connected integrations on Membrane as tools.

⚠️ : This project is in active development and subject to rapid changes. Features and APIs may be modified frequently.

A powerful MCP server that provides intelligent summarization capabilities through a clean, extensible architecture.
Agent Skills

求职最难的不是没经历,是**,或者**。这个 skill 把整条链路走完,缺一不可:

Past Claude Code, Codex, Kimi Code, and Pi sessions -- queryable by your agent, browsable by you.

xianxia-visual-director 是一个面向 Codex / Agent Skills 体系的东方仙侠环境视觉导演 Skill,用于把简短构想、已有提示词或视觉参考,扩展为结构清晰、可控、可衍生的电影级图片提示词。

一套面向 AI 编程助手的 ComfyUI + Anima 二次元生图技能包。当前主线是 v2mini:去掉多层代理式路由,只保留 Anima 生图所需的核心约束、Danbooru tag 精确校验和 ComfyUI 执行链路,让 AI 和人类把更多注意力留给画面本身。

Turn quantitative finance research — papers, drafts, reports, or strategy ideas — into validated, executable trading strategies. Automatically.

Persistent, isolated workspaces for AI coding agents.

Personal coding-agent skills for TypeScript engineering, architecture, Cloudflare composition, and agent workflows.

This repository is a public, executable playbook for U.S. utility-patent work. Not a chatbot wrapper. Not a "talk to a lawyer" landing page. A set of agent skills — SKILL.

Built by a physician-researcher, tested on real publications.

把一句「把这个流程做成 Skill」,变成一个真正能被发现、能稳定触发、能通过验证、还能一键开源的 Skill。

A collection of reusable AI agent skills for Unity workflows. Compatible with Claude Code, GitHub Copilot, Cursor, Cline, and 50+ other agents.

用于 Agent Skills 的 Agnes AI 生成技能,封装 Agnes 官方文本、图片、视频 API。它采用标准 SKILL.md 结构,可安装到 Codex、Claude Code、OpenClaw、Cursor、Windsurf 等支持 Agent Skills 的客户端。