Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
Claude spawning scene objects and controlling their transformations and materials, generating blueprints, functions, variables, adding components, running python scripts etc.
为 AI Agent 提供统一、可路由、可追溯的多市场金融数据 19 个稳定 MCP Tools · Tushare / Qveris / Binance · stdio + Streamable HTTP
Headless IDA Pro MCP Server
Autonomous bug-bounty framework for Claude Code and 6 other AI coding tools — 50 agents, 26 commands, 19 CLI tools, 11 skills, 2 MCP servers.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro,...
MCP server for Docker
This repo contains the source code for running an MCP server that interacts with the Google Ads API.
An MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations.
An MCP server for interacting with Sentry via LLMs.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action...
🧠 Self-Reflecting AI Queries → MCP Protocol Integration → Intelligent Vulnerability Scanning
Talk to a Cloudflare Worker from Claude Desktop!
Agent Skills
为 Seedance 2.0 视频生成模型撰写产品宣传动画提示词的 AI Skill。
这是一个面向中国高校研究生、科研人员和技术团队的通用 Agent 指令与工具包，用于将论文、学位论文、技术报告、源代码和科研手稿 整理为可追溯、可复核的中国发明专利申请初稿。
自带分领域中英文播客订阅库（AI / 科技商业 / 人文社会 / 文化艺术 / 健康），可一键补全官方 RSS、导入订阅、同步元数据、全文转录、生成章节与摘要、本地全文搜索。
A custom skill for Claude Code and OpenClaw that generates professional Chinese visual note cards (视觉笔记卡片/信息图) as single-page HTML infographics.
X (Twitter) marketing skills for Claude Code and Codex: write tweets, threads, and replies in your voice, strip AI tells, and publish via Publora. Open source, MIT.
Collaborate with Codex from Claude Code. Run tasks, get code reviews, do parallel research, all without leaving your Claude session.
Most research-idea workflows fail in one of three ways:
Chinese-market job application assistant, forked and localized from MadsLorentzen/ai-job-search
10 agentes (8 de núcleo, Selina si hay frontend y Lucius bajo demanda), catálogo de 11 skills de proceso, memoria persistente de decisiones por proyecto, 6 flujos de trabajo con quality gates...
A grab-bag of experimental transformer kernels and utilities (mostly PyTorch + Triton).
One CLI. The whole modern .claude/ surface — settings.json, agents, skills, slash commands, hooks, PRPs — wired correctly the first time.
A Claude Code plugin that audits your mobile app against store review policies — the store rejects it.