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 Guard secures your MCP client from prompt injection attacks and more.

A production-ready MCP server that provides seamless integration with Just command runner, enabling AI assistants to discover, execute, and introspect Justfile recipes through the standardized MCP...

An MCP (Model Context Protocol) server for controlling SideFX Houdini via hrpyc, enabling AI assistants like Claude, Cursor, and Letta agents to interact with Houdini sessions.

is a Model Context Protocol server, written in Rust, that lets an AI agent . Instead of wiring up dozens of narrow tools, you give the agent one tool — run_js — and it writes code: looping,...

An open-source MCP server that gives any LLM long-term memory using a knowledge graph + vector search hybrid.

Tired of juggling a messy collection of prompts across notes, files, and spreadsheets? Prompt House is a powerful prompt manager that not only helps you save, tag, and organize your prompts but makes...

tela is a self-hostable, markdown-native team wiki built for a world where agents are first-class authors and readers.

An MCP (Model Context Protocol) server that enables AI assistants to interact with Zemax OpticStudio for optical design tasks. Works with , , and (local LLMs).

A Model Context Protocol (MCP) server that lets AI assistants search secondhand marketplaces. Search Facebook Marketplace, eBay, Depop, and Poshmark for used and secondhand items — filter by price,...

A server that provides AI assistants with comprehensive access to your Plex Media Server, Sonarr, Radarr, and Trakt.tv — all from a single unified server.

The Karpathy LLM Wiki pattern, productionized. MCP server that gives Claude a librarian for your Obsidian vault — graph traversal, auto-wikilinks, trigram search.

A MCP server for automated website deployment to 1Panel (Experimental)
Agent Skills

通用盗号网站注册轰炸机 适用于针对QQ、Steam等平台的各类盗号网站

A to run (Anthropic) on the host via the claude CLI (Agent SDK).

A compact high-signal benchmark for evaluating frontier agents

这是一个面向 LSPosed 模块开发 的低 Token Skill 包。它保留完整知识,但通过“启动版 + 按需知识库 + 模板 + 案例索引”的结构降低常驻上下文占用。

simple, type safe, elegant command line framework. the CLI framework for agents

Skills helping you write robust Zig code.

A coding agent harness built specifically for Motif-3

Official plugin marketplace repository for PI-Desktop

ReasBook main branch mirror for self-hosted CI

A single, readable bash script that takes a fresh Ubuntu/Debian VPS from default install to a hardened, ready-to-use server.

Skill for Hermes, and other agents, to ask typesafe's jev

A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference