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

This server implements long-term memory capabilities for AI assistants using mem0 principles, powered by PostgreSQL with pgvector for efficient vector similarity search.

Gives Goose/Cursor access to your iOS/macOS project index through the Model Control Protocol (MCP) and IndexStoreDB.

A static MCP server that provides AI models with persistent tool context, preventing context loss between chats.

Turn any MCP Client into a "multi-agent" system (via prompting)

AutoHotkey v2 MCP Server with prompts, code completion, and diagnostics

This server interacts with the Unstructured API to manage sources, destinations, and workflows. It is not actively maintained and is kept here for reference.

A MCP server to connect to wolfram alpha API.

Bidirectional, stateful control of Logic Pro from AI assistants. Combines (CoreMIDI, Accessibility, CGEvent, AppleScript, OSC) into a single MCP server with smart routing, fallback chains, and...

Collection of mcp servers and skills/plugins

This repository contains the code and examples for the FreeCodeCamp course on Model Context Protocol (MCP).

Let any AI agent run DaVinci Resolve — MCP server with live Studio control, free-edition FCPXML/LUT workflows, reference color matching, beat-aware music cuts, dialogue tightening, broadcast-loudness...

182 adversarial-input security tests, defusedxml everywhere, sandboxed writes, no patched binaries, no private APIs — plus a private disclosure channel with externally reported fixes already credited...
Agent Skills

A framework-agnostic skill system for AI agents that implements - a powerful pattern for managing context efficiently.

A Claude skill that delivers 10-15x the depth of surface-level research on any topic — markets, products, features, competitors, regulations, or opportunities.

A production-grade Claude Code configuration: skills, agents, hooks, rules, and permissions working as a system, not as isolated features.

A Claude Code skill that scans any codebase and generates a self-contained HTML service-design journey map — no manual diagram work required.

A library of (SKILL.md + optional references/) covering 3 kinds (persona / tool / workflow) across 60+ domains.

Make AI text sound like a real person wrote it.

A practical kit for building motion-graphics videos with Hyperframes — HeyGen's open-source HTML-to-MP4 renderer. Three levels of effort matched to three different goals.

这是一个 Claude Code 技能(skill),帮助你快速掌握任何陌生的行业、领域或技能。它会自动搜索最新信息、下载相关图片和视频、生成 AI 概念图,最终输出一份精美的学习笔记。

A Staff-level Architect AI Skill designed specifically for (AI-assisted programming). It transforms your vague app ideas into rigid, context-safe technical specifications and step-by-step...

WindFtsy的WEB应用黑盒测试技能

10 种视觉风格 × NanoBanana API × 2K/4K 分辨率 × 5 种比例(也可以自己定义比例) Wan2.7 也适配,需要写完整需要呈现的文字 https://canary-create.wan.video/

I'm an engineer building a product solo. I can write code all day — but that's maybe 30% of what shipping a product actually takes.