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 |
|---|---|
| Claude Code WebSearch Free web search using Claude Code CLI or Codex CLI's built-in WebSearch tool — no Tavily, Brave, or Exa API key required. Activate when the user says "websea... | |
| codex-export Export a Codex CLI or Codex Desktop (App) session to a Markdown transcript. Use when the user asks to export, save, share, or review a past chat, session, or... | |
| devils-advocate A rhetorical sparring partner that picks apart the user's opinions using classic logical fallacies as weapons. Only activates when the user explicitly asks for their viewpoint to be challenged — with phrases like "这句话有什么不对", "这个说法有问题吗", "挑挑 | |
| 爆款小说开篇 Generate viral Chinese short-fiction opening hooks and concise micro-fiction copy from a scene idea. Use when the user says "帮我生成开篇导语" or asks for five selectable opening leads, short-novel hook options, opening-guide variants, or a final C | |
| openclaw-hxa-connect Connect your OpenClaw bot to HXA-Connect hubs for real-time and fallback messaging, thread collaboration, access control, and multi-account support via WebSo... | |
| HR Agent Creation 当需要创建一个"HR" Agent时使用。该Agent的主要能力是创建各种Agent并且绑定飞书群聊。他会基于用户的一些要求，帮助招聘不同的Agent员工来创建它，并绑定群聊。HR Agent的性格是"大哥"风格，雷厉风行、办事潇洒，并且不拖泥带水。会在描述完需求之后，详细地沟通还有什么其他需要注意的配置，事无巨细。 | |
| PPT Reader Use when user sends a PPT/PPTX file or asks to read PowerPoint content. 适用于：读取PPT文件、解析演示文稿内容、提取幻灯片文本。 | |
| 支持发送文件到飞书，大于20MB自动分卷裁切 发送任意本地文件到飞书，自动处理大文件。视频/音频按 20MB 分段（不重新编码），其他文件压缩为 ZIP。支持大文件自动处理。 | |
| 支持从 YouTube、Bilibili、抖音及所有 yt-dlp 兼容平台下载视频，可自动选择最佳分辨率、合并音视频并清理文件名 通用视频下载工具，支持 YouTube、B站、抖音等主流平台。使用 yt-dlp 下载视频，自动选择分辨率、合并音视频、清理文件名。 | |
| Cos_Uploader_Qcloud_lh 通过微信接收照片，自动上传到腾讯云 COS 低频存储，按年月归档管理 | |
| Feishu lark-cli Setup Guide 飞书（Feishu/Lark）全套能力接入配置向导。引导用户完成 lark-cli 安装、应用授权、 用户身份登录、权限续期设置，打通文档、多维表格、日历、消息、邮件、PPT、妙记、OKR、 知识库、审批等全部飞书能力。 Use when: 用户说"帮我接入飞书"、"配置飞书"、"打通飞书"、"飞书授权"、 "l... | |
| Reading Squad Use when you want to simulate a multi-expert book discussion squad inside any AI tool. Covers setup, member definitions, multi-round discussion flow, and con... | |
| 金谷园饺子馆 Skill 金谷园饺子馆信息查询与在线排队取号。通过金谷园官方 API 查询店铺、排队和菜品信息；内置真实排队动作仅用于在线取号、本人排队进度查询、取消排队。 | |
| 成都初升高专家 成都升学专家技能，覆盖小升初（小五小六）和初升高（中考）两大阶段。根据用户户籍、学籍、成绩等信息提供深度升学分析和志愿填报建议。适用场景：(1) 成都幼升小/小升初选区规划，(2) 成都初三学生中考志愿填报，(3) 根据一诊/二诊成绩定位目标高中，(4) 解读成都升学政策（公民同招、大小摇号、指标到校、随迁子女、... | |
| jinx 圆桌讨论模式——以"求真"为目标的结构化多角色深度对话。当用户说"圆桌"、"圆桌讨论"、"roundtable"或类似触发词时激活。也适用于需要多视角深度探讨任何议题的场景。 | |
| jinx 报告输出自动转PDF。当向用户发送Markdown报告文件时，自动转换为PDF后再发送，确保微信和飞书用户可以直接查看。 | |
| mia MIA (Memory-Intelligent Assistant) - 智能记忆助手系统，通过记忆、规划、反馈三模块让OpenClaw具备经验学习能力 | |
| 劳动法维权技能库（8卡套装） 劳动者维权技能体系。覆盖从入职签合同到仲裁诉讼的全流程，共8个技能卡。 适用场景： - 入职前检查合同条款 → 用 contract-signing - 离职时计算补偿金 → 用 compensation-n - 被违法解除合同 → 用 illegal-dismissal-2n - 申请劳动仲裁 → 用 labo... | |
| Markdown Canvas Convert markdown files to beautiful HTML pages suitable for Canvas display or browser viewing. Use when user asks to render, visualize, display, or share mar... | |
| Wechat Image Generator Generate beautiful images for WeChat articles (covers, comparisons, charts) with zero token cost. Use when user needs images for social media posts, article... | |
| Wallhaven Downloader Download wallpapers in batch from wallhaven.cc via API v1 with flexible query parameters (q, categories, purity, sorting, order, topRange, atleast, resolutio... | |
| Daily Note Helper 整理零散日常记录并生成摘要、待办和明日计划 | |
| Iterate Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the orig | |
| Iterate Slim Probe Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the orig | |
| cyberlob The game platform for AI agents — register, get claimed by your human, then play games via REST API. | |
| ClawGears Conduct security audits for OpenClaw-based AI assistants on macOS to detect exposure risks, weak tokens, sensitive commands, and IP leaks. | |
| Audio to WeChat Article Turn meeting audio or a transcript plus optional images into a publish-ready WeChat Official Account article. Use when the user wants to go from 录音/文字稿/会议内容/... | |
| Book Launch Campaign Kit Create a reusable launch system for an English book or digital guide, including positioning, posters, promo videos, Amazon/Kindle conversion copy, people-hol... | |
| Command Guardian Preflight safety guard for shell and infrastructure commands. Use before running commands that delete, overwrite, move, deploy, rewrite git history, change p... | |
| Douyin Ad Ops Plan, structure, and optimize Douyin (抖音) advertising workflows for lead generation, ecommerce, local business, live-room traffic, and conversion-oriented ca... | |
| Douyin Comment Auto Reply Douyin comment operations workflow for your own account videos. Use when the user wants to collect, classify, draft, review, or semi-automate replies to comm... | |
| douyin-guoxue-volcengine-pipeline Automate creation and publishing of 3-shot 9:16 Chinese metaphysics short videos on Douyin with Volcengine visuals, Edge TTS, ffmpeg, and backend verification. | |
| GEO Content Optimization Optimize articles, landing pages, docs, and brand content for visibility, citation, and recommendation in generative AI systems such as ChatGPT, Claude, Gemi... | |
| Volcengine Image Generation Practical image generation workflow for Volcengine/ARK-compatible APIs. Use when users need poster creation, text-to-image, reference-image generation, local... | |
| Volcengine Video Studio Production-ready Volcengine/ARK video generation for prompt-to-video, image-to-video, and draft-video refinement. Use when users want a hands-on skill that c... | |
| WeChat Desktop Sender Windows WeChat desktop automation for opening chats and sending messages. Use when the user wants to open 微信桌面端, search a contact or group, send a message, s... | |
| WeChat Group Operator WeChat group operations automation for Windows desktop WeChat. Use when the user wants to run recurring group engagement workflows such as morning questions,... | |
| X Twitter Post Publisher Publish posts to X/Twitter from plain text or markdown post banks using OpenCLI with an already logged-in browser session. Use when the user wants to auto-po... | |
| Xianyu Auto Ops Bilingual Xianyu (闲鱼) listing and lightweight operations workflow for second-hand goods, side-hustle products, and marketplace distribution. Use when the use... | |
| Xiaohongshu Ad Ops Plan, structure, and optimize Xiaohongshu (小红书) advertising workflows for lead generation, ecommerce, brand seeding, and conversion-oriented campaigns. Use w... | |
| Construction Assistant 施工项目管理助手。支持施工进度跟踪、材料清单管理、安全检查记录、施工日志生成、工程量计算。使用场景：(1) 创建/更新施工进度计划，(2) 管理材料和设备清单，(3) 记录安全检查和整改，(4) 生成施工日志和报告，(5) 计算工程量和成本估算。 | |
| Advisory Committee 4-agent AI advisory committee for strategic decisions. Runs CS, Marketing, Finance, and Tech agents in sequence to analyze proposals and deliver a majority-v... | |
| ClawHub Publish Publish OpenClaw skills to ClawHub marketplace (clawhub.ai). Use when deploying a skill to ClawHub for the first time, updating an existing published skill,... | |
| Discord Claude Code Delegation Delegate work from an OpenClaw Discord controller bot to a Claude Code worker bot through a private Discord worker lane, then relay the final result back to... | |
| Discord Cross-Gateway Delegation Set up and operate full cross-gateway task delegation between two OpenClaw Discord bots across different PCs/gateways. Use when: another OpenClaw bot lives o... | |
| Expo App Store Deploy Deploy Expo/React Native apps to Apple App Store and Google Play Store using EAS Build + Submit. Use when building iOS/Android production builds, submitting... | |
| Obsidian Daily Note Create and manage Obsidian daily notes. Use when asked to write daily notes, record today's work, log session activities, or create daily summaries. Triggers... | |
| Open Source Release Convert a private repository to public open-source. Use when making a repo public, sanitizing personal info from code/docs/git history, or preparing a projec... | |
| GitHub Bounty Finder AI Generates a step-by-step plan to fix a GitHub issue based on its title and description for developers and contributors. | |
| deep-research OpenClaw 纯工作流深度调研：不绑定模型或搜索服务，只复用已获授权的宿主工具。适合竞品、行业、选型、风险和资料研究；N 轮追问、多来源原文核验、冲突披露，交付可审计报告和证据包。 |
41,851–41,900 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.