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

MCP server for orchestrating Claude Code or Codex sessions via iTerm2 or tmux

A Model-Context Protocol server for the MITRE ATT&CK knowledge base

gives AI agents a persistent, searchable memory they can use across sessions. V2.1 adds SQLite, full-text search, user-editable categories, safer Docker defaults, and verified backup-first upgrades.

Bilibili 视频字幕/弹幕/评论提取 MCP Server — 扫码登录,自动提取字幕/弹幕/评论与元数据,输出结构化 Markdown 供 AI 理解

An MCP server implementation that integrates with SearXNG, providing privacy-focused meta search capabilities.

Safe DOCX suite: docx-primitives, docx-comparison, safe-docx MCP server

微信 4.0 (Windows) 本地数据库解密工具。从运行中的微信进程内存提取加密密钥,解密所有 SQLCipher 4 加密数据库,并提供实时消息监听。

AI-powered CLI and MCP server for browsing GitHub project documentation (unofficial tool)

Production-grade vector memory MCP server for Claude Code. Semantic search, per-project isolation, rules enforcement, team sharing via git.

Autonomous DFIR agent — SANS SIFT Workstation MCP server for incident response

轻便的人机共读MCP

A Claude Code skill + MCP server setup for expert-level Google Ads campaign analysis
Agent Skills

You found an amazing open-source project and want AI to help you understand and work with it, but faced these problems: Too much code for AI to read? Complicated configuration AI can't handle?

Claude Code skill for web scraping with scrapling - auto Fetcher selection, Cloudflare bypass, site patterns

Experimental skills for Claude Code Superpowers - new techniques and tools under active development.

Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity.

is a lightweight Python framework for . It is purpose-built for complex, decomposable tasks that require independent, multi-perspective analysis without logical contamination.

This is a professional Skill toolkit for writing Chinese Party and government official documents (公文).

I built an OpenClaw agent that manages Google Ads accounts through intent analysis instead of bid automation. All three layers — Read → Draft → Apply — are live and tested on real accounts.

~100 skills for Claude Code — meeting pipelines, research, image generation, TDD, publishing, personal analytics, and Claude Code ops. Each skill is a self-contained folder with a SKILL.

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

40+ strategy files, 39 API scripts, and battle-tested frameworks for LinkedIn, Meta, and Google Ads - built from managing $200K+/month in B2B ad spend across 12+ accounts.

The official Vast.ai Python package — provides both the CLI and SDK for managing Vast.ai GPU cloud resources, plus a serverless client for endpoint inference.

Turn any LLM into a deterministic World Cup prediction engine with one prompt.