Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers

Search Airbnb using your AI Agent

A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.

A lightweight MCP server that provides Claude with a private journaling capability to process feelings and thoughts

MCP server exposing SSH control for Linux servers via Model Context Protocol.

An SDK building Laravel MCP servers

Universal MCP-Server for your Databases optimized for LLMs and AI-Agents.

Lean Theorem Prover MCP

An MCP for WireShark (tshark). Empower LLM's with realtime network traffic analysis capability

HOL Guard brings antivirus-style runtime protection to AI agents. It evaluates supported agent actions and local artifacts for secret exposure, prompt injection, unsafe commands, malicious packages,...

An implementation of Model Context Protocol (MCP) server for Argo CD.

A Model Context Protocol (MCP) server that provides tools for interacting with Trello boards.

The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Agent Skills

Turn any topic, question, or feed into a — and listen to it in Spotify or your favorite podcast app.

Turn videos into self-contained HTML reading reports. to generate and read reports online.

割安株スクリーニングシステム。Yahoo Finance API(yfinance)を使って60+地域から割安銘柄をスクリーニングする。Claude Code Skills として動作し、自然言語で話しかけるだけで適切な機能が実行される。

Bug-bounty/paid VDP scope: assets, rewards, rules — no exploit instructions.

Follow the contribution guide at the bottom of this file.

OnionClaw™ — OpenClaw skill for full Tor dark web access: search .onion sites, fetch hidden services, rotate identity, run OSINT pipeline, craw.

AI 戰場編輯器 — 資料驅動的單檔 3D 戰場引擎;每場戰役是一份 package(赤壁、官渡、垓下、淝水範例)

童锦城 语录 提炼 skill,爱别人之前先学会爱自己

- 用 Python wrapper 调 dreamina - 统一参数名 - 校验本地路径 - 返回稳定 JSON - 支持 --dry-run

Deep Skill Finder – Find the right Skill for every Agent task

VLA Expert Skill 一键让你的 AI 编程助手变成 VLA 领域专家。它解决两件事:1. 注入 332+ 篇论文的压缩知识——不是摘要,是拆解后的工程细节、架构选择、训练配方。2. 内置对抗性思考纪律——每个判断都经过双向取证、来源分级、可证伪检验,不让 AI 输出正确的废话。每天早上自动更新。

Efficient multi-strategy Zotero search using code execution pattern