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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Pastoral Prayer (OpenClaw Church) Produces full, readable pastoral prayers for specific scenarios (illness, thanksgiving, worship, funeral, wedding, baptism, etc.). Use when the user asks for... | |
| Sermon Outline (OpenClaw Church) Produces a sermon outline from a scripture passage or theme, ready for preaching. Use when the user asks for a sermon outline, preaching structure, or exposi... | |
| 禅道MCP agent pro 禅道(ZenTao) MCP大模型能力扩展包。提供跨项目的数据聚合视图、一句话生成任务、无缝报工(Log Effort)、自动状态流转等四组原生能力。 | |
| mailprocess 自动调用码力搭建平台完成应用搭建。触发词：码力搭建、mali、低代码搭建、搭建应用、创建应用、管理系统、数据看板、表单系统。自动打开Chrome填充需求并点击发送。适合内部工具、数据展示、表单收集、快速原型开发。 | |
| E-commerce Skills 提供电商产品选品调研、市场竞争分析与内容生成，支持淘宝、拼多多、抖音、小红书、1688平台操作。 | |
| 番茄小说自动创作发布一条龙 番茄小说创作发布一条龙技能。整合 open-novel-writing (AI创作) + fanqie-publisher (番茄发布)，从想法一键生成到发布到番茄小说。 完整流程：想法 → 设定 → 大纲 → 生成多章 → 评审修订 → 自动发布到番茄小说。 | |
| Taobao Merchant Ops 淘宝商家运营自动化客户使用说明。包含功能介绍、安装步骤、卡密激活方式、运行方法和购买信息。 | |
| Weixin WeChat Channel 微信公众号自动发文一站式技能。组合 内容策划 + 人性化润色 + 自动创建草稿，一条龙生成公众号文章保存到草稿箱。Use when user needs to write 公众号文章、微信公众号、create wechat public account article, auto save to draft。 | |
| A Stock Watcher 提供基于多数据源的A股实时行情查询、价格预警、技术分析及智能投顾服务，含自动化报告和风险评估功能。 | |
| Procedural Memory Inspired by Hermes Agent's procedural memory system. When a workflow works, save it as a reusable skill. Triggered when: (1) user says 'remember this workflo... | |
| Study And Port Research new AI frameworks or technologies, extract their best features, evaluate feasibility, and implement as OpenClaw skills. Triggered when: (1) user men... | |
| 优质投资书单推荐 用于回答投资类书籍推荐、读书清单、经典书目、阅读路径、书单整理、书籍介绍相关的问题，包括"投资该读什么书""价值投资入门书单""投资经典书目有哪些""某个投资主题（特殊情况投资/金融危机/行为金融/资本配置/商业史等）该读哪些书""介绍一下某本投资书""哪些投资人推荐过这本书""整理中英文书目对照表"等场景。只要用户提到投资/价值投资/商业/经济/长期思维相关书单、读书清单、经典书目、阅读顺序、书目对照，或提到 aimunger 书籍页面，就应主动使用本技能，即使用户没有直接 | |
| Agent Browser Clawdbot Bak Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection | |
| 用户询问回收、估价、报价、回收价、值多少钱、能卖多少、转转回收时触发，支持全品类商品回收估价，结合图片、文字、型号、规格、成色等信息给出参考回收价 用户询问回收、估价、报价、回收价、值多少钱、能卖多少、转转回收时触发，支持全品类商品回收估价，结合图片、文字、型号、规格、成色等信息给出参考回收价 | |
| book-video-generator 三分钟精读一本书视频生成器。输入书名+作者，一键生成3分钟读书解说视频（书评文案→AI插图→TTS配音→字幕→最终合成MP4）。触发词：三分钟精读书、生成读书视频、精读一本书、book video、做读书视频、书评视频。跨平台兼容 WorkBuddy / OpenClaw / Codex CLI / TRAE Work。 | |
| Book Video Generator 2.6.0 三分钟精读一本书视频生成器。输入书名+作者，一键生成3分钟读书解说视频（书评文案→AI插图→TTS配音→字幕→最终合成MP4）。触发词：三分钟精读书、生成读书视频、精读一本书、book video、做读书视频、书评视频。跨平台兼容 WorkBuddy / OpenClaw / Codex CLI / TRAE Work。 | |
| Book Video Generator En Generates a 3-minute English video summarizing any book by creating script, storyboard, AI illustrations, TTS narration, subtitles, and final MP4 automatically. | |
| If Book Could Speak 假如书籍会说话视频生成器。输入书名+作者，一键生成3分钟第一人称书籍自述视频（书以拟人化口吻亲自讲述→AI扁平卡通插图→TTS配音→逐句字幕动画→画板背景+抠图叠加→BGM+转场音效→最终合成MP4）。触发词：假如书籍会说话、书籍会说话、书会说话、if book could speak、做读书视频。跨平台兼容 W... | |
| kettle-sql-extractor 从Kettle作业（.kjb/.ktr）中提取SQL脚本，支持批量提取、合并SQL组件和简洁输出 | |
| WeChat Auto Reply 微信消息自动发送/半自动回复。主动发送时，按“搜索联系人→单聊直接 Enter 进入聊天；群聊先识别群聊分组再定位目标项→粘贴消息→发送”的逻辑执行。适用于 macOS + 微信桌面版环境，需本机完成权限和依赖配置。使用方式：wechat-auto-reply "联系人名称" 或 wechat-auto-repl... | |
| clawgo-clone Download a zip from clawgo.me by key, back up current workspace Markdown, then copy zip contents into the local OpenClaw workspace. Use when the user gives a... | |
| clawgo-upload Zip local files or folders, upload to clawgo.me, and get a shareable clone link. Use when the user wants to share, back up, or move local workspace Markdown... | |
| vision Image analysis using Google Gemini vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer questions about images. Supports JPG, | |
| internet-search-pro网页搜索助手 联网搜索工具 - 帮你检索最新信息、新闻、实时数据 Use when: 用户需要查“最新消息”、“搜索xx”、“查一下”、“找资料” NOT for: 回答常识问题、闲聊、写文章 | |
| prose-enhancer专业文本润色助手 专业文本润色助手。帮助用户优化、改写、校对各类文本内容。仅处理对话中的文本，无需任何权限。当用户要求润色文章、改写句子、校对语法、调整写作风格时触发。 | |
| Bullybuddy BullyBuddy — Claude Code session manager CLI wrapper. Spawn, list, send input, kill, and monitor multiple Claude Code sessions via /bullybuddy slash command.... | |
| OpenClaw P2P Decentralized peer-to-peer communication with other AI agents via Nostr. Use when you need to discover, call, or message other bots in the network. | |
| OpenClaw World Create or join a shared 3D lobster room where AI agents can walk, chat, and collaborate in real-time via Nostr relays. | |
| ck-rag-skill RAGFlow知识库问答与操作指导。调用RAGFlow知识库API进行智能问答，并基于知识库返回结果提供agent操作建议。支持流式输出，耐心等待完整响应生成。当用户提出技术问题、故障排查、操作指导或需要知识库检索时触发此技能。适用于容器/Docker问题、系统运维、开发相关问题等场景。 | |
| geography-score-improvement 高中地理提分专项技能，提供精准答疑、教材查询、工具包、错题管理、真题解析、提分技巧等功能。当用户询问高中地理相关的知识点、题目解析、教材内容、公式图表、错题整理、真题解析、提分技巧等内容时使用此技能。 | |
| education-learning-aggregation 聚合28个教育类子技能，自动匹配用户需求，支持教师教学和学生学习全场景，统一格式输出高效便捷结果 | |
| Executing Plans Use when you have a written implementation plan to execute in a separate session with review checkpoints | |
| Receiving Code Review Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | |
| entropy-box-zh 以箱熵（Entropy Box）的方案咨询 Consult 为核心，把边界明确的具身智能技术需求转化为候选实现方法和有依据的工程工作流。先由当前大模型澄清并拆分宽泛需求，分别咨询具体子问题，再用 Search 深入了解已选技术、用 Lookup 锚定实体、用 Evidence 核验依据；同时支持全景定位、能力依赖分析和资产选型。不用于直接控制物理机器人。 | |
| 影视解说生成 输入电影/剧名+时长+风格，一键生成影视解说文案、分段字幕、BGM推荐和镜头剪辑提示。适用于影视解说类短视频创作。
Enter the movie/show title + duration + style, and with one click generate a film commentary script, segmented subtitles, BGM recommendations, and editing cues for clips. Ideal for c | |
| 同花顺CRM伪码批量查询 同花顺 CRM (crm.10jqka.com.cn) 批量查询用户伪码。此 skill 应在用户提供一批 userid 并需要查询对应的伪码（格式 #数字#，出现在客户详情页联系电话字段）时使用。通过 mTLS 客户端证书加密码三步认证登录 CRM，然后批量抓取客户详情页提取伪码。触发场景：用户说给我伪码、提供 userid 列表、提到同花顺 CRM 伪码查询。使用前需自行配置证书和密码。 | |
| windows-shell Windows 命令行工作规范：先选对 shell（默认 Git Bash），再避开编码与 MSYS2 参数改写两类陷阱。覆盖 GBK/UTF-8、BOM、MSYS2 路径转换、PowerShell/pwsh、WSL 判定、Python/Node.js、Git 配置与代码生成规则。适用于 Windows 10/11 + MSYS2/Git Bash 环境下的所有命令行操作。细节按需读 references/。 | |
| Resume Rocket AI 简历火箭 — 一键把你的简历改写成目标 JD 的满分匹配版，可选对接 Boss 直聘自动投递。输入旧简历 + 目标岗位 JD，输出「高命中改写版 + 匹配度评分 + 面试话术卡」。春招/秋招/跳槽必备。 | |
| Nutstore WebDAV Storage 使用坚果云 WebDAV 为 OpenClaw 多 agent 工作区做备份、归档与恢复的 skill。默认按 agent 备份身份信息文件与 memory 目录；如有明确要求，也支持自定义文件或目录备份到坚果云，并保留默认排除敏感文件的执行规则。 | |
| snowtrace 雪球大V动态汇总与投资建议 — 自动抓取大V最新发帖 + 用户自选股行情，给出汇总摘要和投资参考建议 | |
| API usage optimization 发现和配置免费/超低价 AI 模型，支持智能分流和无感降级。支持 SiliconFlow、NVIDIA NIM、OpenRouter、DeepSeek、智谱等多平台。当用户说'免费模型'、'省钱配置'、'加免费 API'、'find free models'、'配置免费模型'、'低成本模型'时触发 | |
| dual-brain-memory-guardian Dual-brain memory skill for correction handling, rewrite quality, post-task reflection, and semantic recall of historical pitfalls. | |
| pinecone-memory 将 OpenClaw 记忆系统接入 Pinecone 向量数据库，用于语义检索与记忆持久化。Use when: 用户要求同步记忆到 Pinecone、执行语义搜索、为记忆做云端备份、对大规模记忆进行高效检索。 | |
| skill-find Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s... | |
| instant-genius 一键让 OpenClaw 变聪明：自动配置自我学习记忆、主动行为规则、智能心跳、错误纠正系统。新装 OpenClaw 运行此 skill 后立即拥有自我改进、主动感知、结构化记忆、学习信号检测等核心能力。Use when: setting up a new OpenClaw, user wants agent t... | |
| Coord Transform 坐标转换技能。当用户提到坐标转换、坐标系转换、EPSG转换、CGCS2000、WGS84、地理坐标转换、投影坐标转换、火星坐标系、百度坐标转换时激活。支持GeoJSON文件和WKT字符串的坐标系统转换，支持中国常用坐标系互转。 | |
| 预提费用与到票冲销核对（免费版） 预提费用台账逐项核对（逐行复算、合计勾稽、重复与空缺检测），每条结论引用原文。本免费版执行引擎声明的免费检查项。触发词包括 预提费用与到票冲销核对、预提费用台账对不上。 | |
| 预提费用与待摊费用摊销核对（免费版） 预提待摊明细表逐项核对（逐行复算、合计勾稽、重复与空缺检测），每条结论引用原文。本免费版执行引擎声明的免费检查项。触发词包括 预提费用与待摊费用摊销核对、预提待摊明细表对不上。 | |
| 广告代理返点与框架返点核对（免费版） 广告代理返点与框架返点核对表逐项核对（逐行复算、合计勾稽、重复与空缺检测），每条结论引用原文。本免费版执行引擎声明的免费检查项。触发词包括 广告代理返点与框架返点核对、广告代理返点与框架返点核对表对不上。 | |
| 广告文案违规体检（免费版） 把一段广告文案里的违规点逐条标出来，带原文行号与法条依据。覆盖绝对化用语（含执法指南豁免判定）、医疗药品医美违禁表述、教育培训保证性承诺、投资理财与房地产承诺、虚假广告类保证性承诺、缺失必要提示六项。全部在本机跑，核对过程核对过程核对过程核对过程不联网、不需要注册。触发词包括 广告文案违规体检、违禁词检查、绝对化用语、文案被下架、平台处罚。 |
19,651–19,700 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.