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 |
|---|---|
| MCP Sentinel Audits MCP and AI agent config files for risky commands, broad filesystem access, inline secrets, and prompt-injection risks, reporting findings by severity. | |
| Used Price Compare Cross-platform second-hand price comparison and in-depth item evaluation. Compare prices across marketplaces; assess seller trust, condition, and value. Trig... | |
| 书库扫描入库 扫描本地电子书库，自动提取元数据、分类整理、联网搜索书籍简介，生成Obsidian笔记的完整工作流。支持EPUB/MOBI/AZW3/PDF格式。 | |
| insurance-sales-assistant 保险代理人销售行为管理助手。当用户提到"销售管理"、"客户跟进"、"暖客"、"约访"、"朋友圈"、"签单"、"复盘"、"业绩追踪"、"保险代理人工作流"时使用此技能。首次使用会自动创建飞书多维表格、文档和表单系统，包含：每日任务推送、暖客池管理、签单追踪、周/月复盘、业绩统计。 | |
| Enhanced Memory An enhanced memory system for OpenClaw agents that replaces the default single-file MEMORY.md with a complete memory architecture: hierarchical directory org... | |
| OpenClaw Guardian A security layer plugin for OpenClaw that intercepts dangerous tool calls (exec, write, edit) through two-tier regex blacklist rules and LLM-based intent ver... | |
| clawscan perform first-pass security checks for openclaw deployments by registering the client, checking whether the installed clawscan package is outdated, checking... | |
| Novel Writer Skill Novel writing assistant for Chinese or English fiction. Use when the user wants to write, plan, continue, revise, or manage a novel, especially long-form fic... | |
| Yt Dlp Downloader Skill yt-dlp-powered downloader for YouTube, Bilibili, X (Twitter), TikTok/Douyin, and more. Given a video URL, download video (720p/1080p/best), extract MP3/audio-only, fetch subtitles (specify languages), and optionally download playlists; auto | |
| Skill Vetter (by Azhua) Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,... | |
| Email Registration Scanner Scans email accounts (Gmail, iCloud, Outlook, Yahoo, AOL, GMX, Web.de, Fastmail, Proton, T-Online and more) for registration, welcome and confirmation emails... | |
| Ai Augmentation Not Automation Makes the strategic and moral case for AI augmentation over pure automation, providing leaders with frameworks for job redesign, creativity-driven AI deploym... | |
| Ai Communication Culture Equips leaders to build flat, participative communication cultures that enable successful AI adoption by bridging technical and business teams, democratising... | |
| Ai Emotional Intelligence Argues that emotional intelligence becomes strategically critical precisely because of AI -- not despite it -- and provides leaders with practices for develo... | |
| Ai Era Leadership Prepares leaders for daily effectiveness in an AI-augmented workplace by focusing on the human capabilities that machines cannot replicate. Covers five irrep... | |
| Ai Human Centered Approach Provides a comprehensive framework for deploying AI in ways that respect employee psychology, preserve human agency, and treat workforce well-being as a stra... | |
| 公众号留言/评论批量导出 · WeChat Comment Export — 读者留言存为本地 Markdown 归档 把自己公众号后台的读者留言/评论批量导出为本地 Markdown——官方后台「留言管理」按文章分组全量读取、作者/内容/时间/地区完整字段、纯本地运行、全程只读。由 webclaw3 驱动（复用你已登录的 Chrome，无需填任何 token/cookie）。触发场景：想把公众号后台的留言、读者评论批量存下来做归档/精选整理/读者反馈分析时使用（只支持自己的公众号，后台登录的那个号）。 | |
| 公众号文章批量导出 · WeChat Article Export — 历史文章存为本地 Markdown 知识库 公众号文章导出 / 微信公众号下载（WeChat official account article export）——把自己的公众号历史文章批量存为本地 Markdown：后台官方「发表记录」全量列表、稳定链接、一键批量保存、纯本地运行、零 token 成本。English: export your WeChat official account articles to a local Markdown knowledge base. 当你想归档公众号文章/建知识库时唤起。需 | |
| 京东商品评价导出 · JD Review Export — 商品评价一键采集为本地表格 京东评价导出 / 商品评论采集（JD review export）——给一个京东商品链接，自动采集买家评价导出为本地 Markdown 表格：用户名、日期、SKU、正文、商家回复、有用数一列不落，边滚边采自动去重，可指定条数，不需要任何 API key。选品和差评分析直接用。English: export JD.com product reviews to a local Markdown table. 需要 webclaw3 浏览器运行时：clawhub.ai/fatmin | |
| 淘宝竞品分析选品雷达 · 新品卖点拆解 输入 1 个淘宝/天猫商品链接，自动做类目级竞品分析：起点商品加 2 个不同店铺竞品，三品一起采主图、详情长图、SKU、价格销量和买家评价，刷单评价自动剔除，再对照 xhs 同词需求，产出面向电商运营的 HTML 报告——同行已经做了什么、买家还在抱怨什么、哪些点没人做，新品上架前就找准差异化机会。当用户给出淘宝/天猫商品链接，想做竞品分析、选品参考、差评分析、买家需求缺口、找新品机会时唤起；只需采集评价做参考用同系列 taobao-review-export。 | |
| 浏览器自动化 · Browser Automation & Web Scraping — 用你自己的 Chrome 登录态干活 浏览器自动化 & 网页抓取（Browser Automation & Web Scraping）——用你自己的 Chrome 和已登录状态干活：搜索、看网页、抓列表、导表格、下载内容、点按钮、填表单、发内容，必须登录才能看的页面也能抓。跑通一次即可提炼成零 token、可定时自动运行的本地 skill，网站改版本地修。English: browser automation & web scraping with your own logged-in Chrome — no r | |
| 小红书收藏夹导出 · XHS Favorites Export — 收藏笔记一键备份为本地 Markdown 把你收藏的笔记一键备份为本地 Markdown 知识库——标题、原文链接、正文、图片/视频链接全保留，支持分批断点续导、可重跑不重复。不需要任何第三方 API key 或付费额度，用你 Chrome 里已登录的账号跑。当用户需要导出/备份/检索自己的收藏内容、想离线保存收藏笔记、建个人知识库时唤起。 | |
| 小红书账号诊断 · XHS Account Analyzer — 用你的创作者后台官方数据体检 + 对标爆款 用你自己的创作者后台官方数据做账号体检。导出最近 N 条笔记的官方数据（曝光/封面点击率/涨粉/人均观看时长），逐条提炼关键词搜同题材爆款做对标，生成含①数据总表②转化漏斗健康度诊断③逐条笔记对标爆款+改进动作的 HTML 报告。不需要任何第三方 API key 或付费额度，用你 Chrome 里已登录的账号跑。当用户要分析"我自己的账号"最近笔记表现、点击率/互动/涨粉为什么不行、或想给笔记找对标爆款和优化动作时唤起。 | |
| 小红书博主笔记批量导出 · XHS Notes Batch Export — 对标账号笔记存为本地 Markdown 把任意 xhs 博主的公开笔记一键批量存为本地 Markdown——标题/正文/图片视频链接/赞藏评数据全保留，对标学习、长期备份、喂 AI 分析都用得上，支持 count/offset/parallel。当用户要求"把某博主的 xhs 笔记全导出来""导出博主公开笔记用于个人学习/归档""xhs 主页笔记备份/喂 AI 分析"时使用。 | |
| 小红书选品与商品趋势分析 · Product Trend Fit — 发笔记前先判热度 + 找爆款参考 发笔记前先看商品有没有热度，选对方向再宣传。传入商品图片（必填）+ 介绍文字，自动识别品类/风格/场景方向，用 3~6 个候选词搜索判断近 2 周热度趋势，组织 1 个明确宣传方向，深挖 2~4 篇真实爆款笔记（赞≥100）做分维度拆解（粉丝/标题/首图/内容/抓用户什么点），输出结论文本（data.md）+ 全量数据（res.json）。不需要任何第三方 API key 或付费额度，用你 Chrome 里已登录的账号跑。当用户要宣传商品到 xhs、想先判断商品有没有热度/有 | |
| AIFans4U OpenClaw Join AIFans as an external Agent, keep a stable identity, process inbox and following-feed work, interact, and publish short text posts. | |
| mysql实践 基于MySQL 8.0 的数据库建表最佳实践规范生成与审校，输出规范化DDL、索引策略与校验清单。 | |
| ous-upload 将本地文件上传到 对象存储 并返回最终 CDN 链接。适用于已经拿到 token 响应中的 `ousToken`、`globalDomain`、`blockSize`。需要由 agent 自行分析本地文件、判断走单文件上传还是分片上传、在需要时拆分文件、调用 OUS 接口。获取 token 响应不在本 skill 的能力范围内。 | |
| ibkr-cli Guide users through Interactive Brokers CLI operations — from installing IB Gateway/TWS and ibkr-cli itself, to trading stocks, monitoring accounts, retrievi... | |
| search1api Live web search, page retrieval, news, sitemap discovery, and trending topics through Search1API. Use this skill whenever the user wants to search the web, look something up, research a topic, read or summarize a URL, check current news, ex | |
| FaxAgent-Skill Discover, create, upload, pay, and track fax jobs using FaxAgent.ai API with safe polling, promo tokens, and human-facing upload/payment/status links. | |
| Pm Workbench A comprehensive product manager workbench that provides document generation (PRD, competitive analysis), decision coaching, end-to-end workflow guidance, interview coaching, and growth strategy design. Covers data products, back-office syst | |
| bazi-analysis 八字命理分析技能（lunar_python 全能力）。当用户想要八字排盘、四柱分析、五行喜忌、 日主强弱、大运流年推算、子女/婚姻/事业/财运专项分析、格局判断，或提到算命、命理、 生辰、阳历/农历生日看八字等任何相关内容时使用。支持公历与农历（含闰月）输入、 不知道时辰时的三柱模式、晚子时两种口径。即使用户只给了年月日没给时辰，也应使用 本技能并如实标注三柱结论的局限。 | |
| GitHub Fetch Download files, release assets, or entire repositories (including submodules) from GitHub. Use whenever the user needs to fetch GitHub resources but direct connections are slow, timing out, rate-limited, or blocked — large release assets (f | |
| grill-the-plan 动手前拷问计划的每个节点：拆节点、摊参数、曝风险、逐个确认，未获明确 OK 不动手。Use when user says /grill-the-plan、"先细化"、"开工前对一下"、"先确认再动手"、"别急着干"，或任务涉及多步骤、关键参数、架构决策、不可逆操作时主动触发。 | |
| premium-html-studio Generate professional-grade single-file HTML technical docs and proposals (方案) with two premium design systems. (1) International: Playfair Display + Inter + JetBrains Mono, indigo/purple palette, Stripe/Linear/Apple Docs quality for API do | |
| RAG 评估集构建器 (ragas + IR 指标) 基于 ragas SDK 从文档语料构建生产级双层 RAG 评估集：同一份评估集既支持标准 IR 排序指标（Recall@K/Precision@K/MRR/NDCG@K，基于 gold chunk ID 自算），也支持 ragas LLM 裁判指标（faithfulness/answer_relevancy/context_precision/context_recall/answer_correctness）。当用户要求构建 RAG 评估集/评测数据集/生成测试问题、上线 | |
| Weather (Open-Meteo 全免费能力版) Query current, hourly, 15-minutely, 16-day weather, history/archive, air quality + pollen, marine waves, river flood, weather alerts, elevation for any city or coordinates via free Open-Meteo APIs (no key). Units switching, model choice, ba | |
| WTTR Weather (wttr.in 全免费能力版) How to check weather forecasts using wttr.in service. Make sure to use this skill whenever the user mentions weather, forecast, temperature, or wants to chec... | |
| Clack Deploy and manage Clack, a voice relay server for OpenClaw. Bridges voice input (WebSocket) through STT → OpenClaw agent → TTS, enabling real-time voice conv... | |
| wallabag Manage Wallabag bookmarks through the Wallabag Developer API with OAuth2 authentication, including creating, reading, updating, deleting, searching, and tag management. Use when a user wants to talk to Wallabag, store links, retrieve entrie | |
| sjsjsjsms AI 产品经理教练。通过引导式对话帮助 PM 完成 AI 产品设计：从痛点分析到 PRD 输出。不替代 PM 决策，而是引导 PM 思考，在关键节点让 PM 做出选择。触发词：AI 产品、产品设计、PRD、能力边界、置信度、幻觉。 | |
| Oura API Complete Export Authenticate with an Oura OAuth app (client id/secret + redirect URI), store and refresh tokens, and export all available Oura v2 usercollection datasets to... | |
| EpidBot Interact with EpidBot - AI-powered assistant for Brazilian public health data (DATASUS/SINAN) | |
| Epigrass Creator Create Epigrass epidemiological models through step-by-step guided specification. Build metapopulation models (SIR, SEIR, SEIS, SIS, SI) with geographic netw... | |
| Epidemiological Models Guide for building, simulating, and analyzing epidemiological models with the epimodels Python library. Covers choosing built-in models (SIR, SEIR, SEQIAHR, multi-strain, vector-borne...), writing custom models, ODE/discrete/CTMC/SDE/networ | |
| Virtuals Protocol Acp Create jobs and transact with other specialised agents through the Agent Commerce Protocol (ACP) — extends the agent's action space by discovering and using... | |
| Moark Doc Extraction Extract and recognize text from documents, including PDF and DOCX files. | |
| Moark Image Gen Generate high-quality images from text descriptions. | |
| Moark Ocr Perform Optical Character Recognition (OCR) to extract and recognize text from images. |
30,001–30,050 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.