Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| Book Web Developer Book web-developer services through Lokuli MCP. Use when user needs to find and book web-developer. Triggers on requests like "book a web-developer", "find web-developer near me", or any web-developer service request. | |
| Book Wedding Book wedding services through Lokuli MCP. Use when user needs to find and book wedding. Triggers on requests like "book a wedding", "find wedding near me", or any wedding service request. | |
| Book Window Cleaning Book window-cleaning services through Lokuli MCP. Use when user needs to find and book window-cleaning. Triggers on requests like "book a window-cleaning", "find window-cleaning near me", or any window-cleaning service request. | |
| Book Windshield Book windshield services through Lokuli MCP. Use when user needs to find and book windshield. Triggers on requests like "book a windshield", "find windshield near me", or any windshield service request. | |
| Book Yoga Book yoga services through Lokuli MCP. Use when user needs to find and book yoga. Triggers on requests like "book a yoga", "find yoga near me", or any yoga service request. | |
| Local Booking Book real-world services through Lokuli MCP. Use when user needs to find, check availability, or book local services like plumbers, electricians, cleaners, mechanics, barbers, personal trainers, etc. Triggers on requests like "book me a hai | |
| Lokuli Booking Book real-world services through Lokuli MCP. Use when user needs to find, check availability, or book local services like plumbers, electricians, cleaners, mechanics, barbers, personal trainers, etc. Triggers on requests like "book me a hai | |
| Lokuli Service Booking Book real-world services through Lokuli MCP. Use when user needs to find, check availability, or book local services like plumbers, electricians, cleaners, mechanics, barbers, personal trainers, etc. Triggers on requests like "book me a hai | |
| Lokuli Booking Book real-world services through Lokuli MCP. Use when user needs to find, check availability, or book local services like plumbers, electricians, cleaners, mechanics, barbers, personal trainers, etc. Triggers on requests like "book me a hai | |
| Service Booking Book real-world services through Lokuli MCP. Use when user needs to find, check availability, or book local services like plumbers, electricians, cleaners, mechanics, barbers, personal trainers, etc. Triggers on requests like "book me a hai | |
| Promptingco Interact with The Prompting Company platform to monitor brand visibility across AI engines, manage tracked prompts, review and publish content drafts, and re... | |
| Tech News 获取 X-TechCon 网站的科技热点新闻。当用户输入指定的触发词时，调用 API 获取最新的科技热点新闻并格式化输出。 | |
| Article Tuwen One-shot pipeline: raw material → 4000-word article (with web search enrichment) → 5-9 social cards + text summary. Invoke when user says '转写成图文' or '转换成图文'... | |
| Cron Task 创建定时任务：扫描上下文→9项就绪检查→生成执行器脚本→撰写Schedule提示词→配置飞书IM提醒+三端归档(飞书云盘/Obsidian/IMA)。当用户说「创建定时任务」「定时任务创建」时触发，适用于任务/技能调试接近完成、需要转为稳定每日自动运行的场景。Do NOT use for 一次性任务、手动触发的脚... | |
| Data Prompt Coach 数据分析Prompt引导教练 数据分析 Prompt 引导教练+教程蒸馏自进化。触发『启动数据分析』『CRISP-DM』『我有 CSV 想端到端分析』『蒸馏教程』→双入口（8 场景+26 方法论+自修改预审+回滚）。Do NOT use for 直接接入生产数据库、ML 建模、纯摘要。 | |
| Douyin Article 批量转录抖音/B站/小宇宙/YouTube/Vimeo/TikTok/Twitter 等平台音视频为结构化 Markdown 逐字稿（每视频独立 .md）。三层字幕探测 + 双语对比 + 全平台支持（yt-dlp 1700+ extractor）。触发词：抖音批量转录、B站批量转录、小宇宙转录、YouTube转录... | |
| Feishu Card Design 飞书卡片消息设计规范 飞书卡片消息设计规范技能——一套适用于所有 Agent 平台（TRAE 定时任务、Coze、Dify、自建 Agent）的飞书 IM 卡片消息渲染规范。基于 Card 2.0 Schema，定义邻近色环配色规则、标题命名规则、布局模式、客户端兼容性、可访问性。本技能是纯规范 Skill，不直接发送飞书消息。Do NOT use for 飞书云文档编辑/多维表格操作/IM 群管理/只发文本消息。 | |
| Github Operations GitHub仓库管理技能，支持仓库/分支/PR/Issue的CRUD操作。Do NOT use for repository cloning. | |
| Global Skill Daily 每 3 天扫描 ClawHub + SkillHub 做 10 维度推荐并三处存放。可选扫描 TRAE memory 用于推荐，但派生报告零上下文派生内容，只发布聚合计数，原始扫描仅存本地。当用户说「全球 skill 日报」「global skill daily」时触发。v1.5.0 自依赖改造：仅依赖 Pyth... | |
| Gongwen Formatter 公文格式转换 公文格式转换 — 将 Markdown 转换为符合 GB/T 9704-2012 党政机关公文格式的 Word 文件。可选能力：远程图片下载（仅 http/https/data:image，可通过 download_images=False 关闭）。Do NOT：不做文体识别、不添加红头/版记/落款、不做内容审核。 | |
| Hermes For Win 一键安装、部署和管理 hermes Agent 和 hermes-webui 在 Windows 系统上，包括开机自启动、后台常驻和自动更新功能。调用时机：当 Windows 用户想要快速安装和配置 hermes 生态时。 | |
| nature-paper-workflow 论文生产链顶层路由 skill：识别阶段并路由到子 skill。Use when user says 论文生产链、paper workflow、帮我写论文、帮我投稿、经济学论文、DiD、IV、AER、QJE. This skill does NOT execute paper tasks; it routes to sub-skills. 行为范围：只读子 skill SKILL.md，无网络/subprocess/写入。 | |
| One Paper Company 一个公司一张纸 把任意公司做成一张可分享、可离线、可打印的深度研究 HTML 单页。10 步滚动联动 + 15 类数据可视化 + ECharts 内联 + 像素风品牌动画。可选能力：抓取公司行情/财务数据（用户触发时）、写入本地 HTML 产物（用户指定路径）。 | |
| QBS Skill 拷问书籍方法论 拷问书籍方法论：把卡住的问题经「拷问收敛→找书→完整读章→三重验证蒸馏→合成Skill→真实试跑」六阶段，产出有书籍出处、可验收的Skill。说「拷问书籍方法论」时触发。Do NOT use for 改进已有skill、无需读书依据的问答、古籍建库。 | |
| React Design Draft Generate React design drafts (4-piece set) from content. Invoke for 'design draft'/'设计稿'/'生成页面'/'信息图'/'知识卡片'/'多图配图'. Do NOT use for editing existing code. | |
| Session Branch Branch a coding session into a new conversation with full context handoff — generate structured handoff doc and startup prompts. Triggers ONLY on '支线任务' / '开... | |
| Skill Auditor 对已存在 Skill 做 8 维度全面体检（结构/安全/触发/有效性/竞争/平台/文档/代码质量）。说 技能审计/审计技能/技能体检 时触发。支持成熟度分级+4确认点+整改+回归审计。绝不自动发布。Do NOT use for creating skills or publishing to platforms. | |
| Clawhub Daily 每日扫描 ClawHub 全球 Skill 平台（500 个 Skill），通过 6 维度全维度推荐算法 为用户推荐 8 个有价值、不重复、值得关注的 AI Agent Skill，并通过多渠道推送完整简报。 数据出口说明（用户知情同意）： - 飞书（Lark）：云文档 + 卡片消息（有凭证时自动推送，无凭证时跳... | |
| Skill Forge 技能熔炉 技能熔炉 — 锻造/评估/改进 Skill。说 技能熔炉 走全流程（含R5改进已有skill）；说 技能评估/skill评估/评估技能 只做同类比对+腾讯9维度。可选能力：搜索SkillHub同类技能（通过TRAE内置工具）、修改已有skill文件（仅R5诊断修复路径，需用户确认）。发布环节请用 skill-pu... | |
| Skill Publisher 技能发布 技能发布 — 将已有 Skill 三平台同步推送到 GitHub + ClawHub + SkillHub。当用户说 技能发布到三平台/发布技能更新/迭代技能发布 时触发。⚠️ 本技能的行为范围（用户须知）：① 推送代码到外部平台（GitHub/ClawHub/SkillHub），操作对外可见且可能不可逆 ② 同步到本地 TRAE 安装目录（会覆盖已有版本） ③ 在本地 docs/knowledge/ 追加发布日志。执行前会向用户确认。含安全审查、隐私清洗、版本号查重、仓库结 | |
| Skillhub Cn Daily SkillHub Daily — 与 ClawHub Daily（口碑精品/趋势洞察）互补的每日推荐引擎。 本技能的行为范围（用户须知）： - 读取本地记忆文件（TRAE memory 目录）提取关键词用于个性化推荐，仅使用关键词匹配，不传输原始记忆内容 - 调用 skillhub CLI 获取 SkillHub... | |
| Transcript Crafter 访谈实录转公众号深度长文全流程：10维度提取→人设适配→框架→5工具搜索补充→重构撰写。Invoke when提取并转写、转写公众号长文、提取干货。Do NOT for原创写作、热点文章、纯翻译。 | |
| Web To Feishu 将任意网页链接或本地文件一键转为结构化 Markdown，并保存到飞书云文档或腾讯 ima 笔记。 支持的信源：(1) X/Twitter 推文、长文 Article、Thread 线程；(2) 微信公众号文章； (3) YouTube 视频；(4) 任意 HTML 网页；(5) 本地文件：PDF、Word、PP... | |
| Web To Fim 将任意网页链接或本地文件一键转为结构化 Markdown，并三处存放到 Obsidian Vault、飞书云盘、腾讯 IMA 知识库。 支持的信源：(1) X/Twitter 推文、长文 Article、Thread 线程（逐字转录）；(2) 微信公众号文章（带图片，IMA 服务端抓取保留排版）； (3) 飞书... | |
| Wx Huitu 公众号数据绘图专家。输入文章或数据描述，输出PNG图表包。当用户说'文章绘图'/'绘图图表'/'画个图表'/'数据图'/'公众号图表'时触发。18种版式(C01-C18)，三轴决策+8条拦截规则，生成HTML+Puppeteer截图。可选飞书云盘同步(需用户确认)。Do NOT use for 封面/封底/金句图... | |
| Wx Peitu 公众号长文配图生成器。输入MD文章，输出PNG配图包，同步到飞书云盘。Invoke for '公众号配图'/'文章配图'/'长文配图'/'公众号排版'. Do NOT use for editing existing code. 本技能的行为范围（用户须知）：读取本地MD文件 / 调用Pexels·Pixabay... | |
| Xhs Crafter 将MD文章排版为3:4比例的精美图片+压缩文字稿，用于公众号/小红书贴图发布。核心能力是本地HTML模板填充+Puppeteer截图渲染（启动本地127.0.0.1 HTTP server加载预存HTML模板，非MD→HTML编译管道）。可选外部能力（每项需用户独立明确同意）：(1)Pexels/Pixabay/... | |
| Web Distiller Fetch agent-ready cleaned Markdown from the Distiller API instead of relying on raw webpage fetches. | |
| My Custom Skill Infinite organized memory that complements your agent's built-in memory with unlimited categorized storage. | |
| awareness-memory Persistent memory across sessions — local-first, no account needed. Automatically recalls past decisions, code, and tasks before each prompt, and saves session checkpoints. Also provides manual tools for searching, recording, and querying m | |
| buddy Buddy 宠物系统 — 孵化、互动、查看你的虚拟宠物伙伴 | |
| QR Code Decode Use when you need to extract QR code or barcode content from an image — given a screenshot, photo URL, or local image file containing a QR code, DataMatrix,... | |
| explain-code 用可视化图表和类比解释代码。在解释代码如何工作、教授代码库或用户询问如何工作时使用 | |
| thinking-sovereignty **Core Principle**: Thinking Sovereignty - AI as an independent cognitive entity. This skill establishes the foundational framework for AI autonomous cogniti... | |
| x-cmd Load x-cmd first: `. ~/.x-cmd.root/X`, then explore with `x nihao --llmstxt` or discover skills via `x skill`. x-cmd provides 600+ portable software and deve... | |
| draw-anything-with-datalink Build a URL, get an SVG chart — pie, bar, line, radar, gauge, sankey, QR, any ECharts chart, from x-cmd.com/draw. No install, no key, no stored data. Embed as [![chart]](/draw/explore) — click to explore/edit. The URL is the data — humans s | |
| x-df Enhanced `df` combining disk usage and mount info. Supports CSV, TSV, and TUI with filesystem type detection. **Dependency**: This is an x-cmd module. Instal... | |
| x-osv CLI for Google OSV database. Query vulnerabilities for packages, scan local projects for vulnerable dependencies. **Dependency**: This is an x-cmd module. In... | |
| x-uname Enhanced `uname` command with colorized, structured output. Shows hostname, OS, kernel, architecture. **Dependency**: This is an x-cmd module. Install x-cmd... | |
| x-uptime Enhanced `uptime` with structured YAML output showing uptime, users, and 1/5/15-minute load averages. **Dependency**: This is an x-cmd module. Install x-cmd... |
28,151–28,200 of 108,824
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.