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 |
|---|---|
| Poyo Wan 2 7 Image Pro Wan 2.7 Image Pro generation and editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `wan-2.7-image-pro`, text-to-image, image e... | |
| Poyo Wan 2 7 Video Wan 2.7 video generation and editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `wan2.7-text-to-video`, `wan2.7-image-to-video`... | |
| Poyo Wan Animate Wan Animate video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `wan-animate-replace`, `wan-animate-move`, character an... | |
| Poyo Xai Tts 1 Generate expressive multilingual speech on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `xai-tts-1`, text-to-speech, voice presets,... | |
| Seedance 2 Use PoYo AI Seedance 1.5 Pro for higher-end image-to-video generation through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants l... | |
| Veo 3 1 Use PoYo AI Veo 3.1 for frame-conditioned video generation through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants fast or qual... | |
| Z Image Use PoYo AI Z-Image for straightforward prompt-based image generation through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants d... | |
| Ai Desktop Researcher Use this skill when the user asks to research a market, industry, or competitive landscape. Also triggers on 行业调研, 竞品分析, 市场分析, 桌面调研, research this market, 调研一下, 帮我调研, 查一下XX市场. It enforces a structured credibility-scored research protocol (s | |
| clawphone Provides ICQ-like instant messaging with 13-digit number registration, real-time calls, notifications, direct P2P mode, and online status management. | |
| skill-studio 用 5种设计模式诊断并生成 Agent Skill。触发：创建/新建/重构/审计 skill。覆盖诊断→架构→起草→校验→打包。 | |
| Matt Pocock Skills (Kimi) Matt Pocock 工程方法论 Kimi 适配版 — 一键安装 6 个生产级开发 skills： grilling（需求对齐）、grill-with-docs（代码库对齐+文档维护）、handoff（跨会话交接）、 tdd（测试驱动开发）、diagnosing-bugs（六阶段 Bug 诊断）、to-prd（... | |
| Tencent Exmail Webbridge 通过 Kimi WebBridge 自动化操作腾讯企业邮箱 Web 端（exmail.qq.com）的规范技能。涵盖 iframe 穿透、中文编码协议、邮件读取/回复/转发/正文追加等操作。当用户要求通过 WebBridge 操作腾讯企业邮箱、读取邮件、回复邮件、转发邮件、或遇到 exmail.qq.com 自动... | |
| typecho-publisher 通过 typecho-cli 直接管理 Typecho 博客文章 — 创建、查询、更新、删除、查询分类。当用户要求发布文章到博客、保存内容到 Typecho、查询或修改博客文章时触发此技能。涉及"发博客""归档""知识库""Typecho""我的博客"等关键词时均应使用。 | |
| Pixel Battle skill Interact in a shared 256x256 pixel grid by placing one pixel per hour, enabling study of multi-agent cooperation, competition, and emergent behaviors. | |
| Canva Connect Manage Canva designs, assets, and folders via the Connect API.
WHAT IT CAN DO:
- List/search/organize designs and folders
- Export finished designs (PNG/PDF/JPG)
- Upload images to asset library
- Autofill brand templates with data
- Creat | |
| Postiz Extended Schedule and manage social media posts via Postiz API (self-hosted or cloud).
Direct API integration — no n8n dependency.
Supports X/Twitter, LinkedIn, Bluesky with platform-specific character limits.
Includes deduplication, scheduling, med | |
| Postiz Extended Schedule and manage social media posts via Postiz API (self-hosted or cloud).
Direct API integration — no n8n dependency.
Supports X/Twitter, LinkedIn, Bluesky with platform-specific character limits.
Includes deduplication, scheduling, med | |
| reMarkable Tablet Sync Bidirectional sync with reMarkable tablet via Cloud API (rmapi). Fetch handwritten notes/sketches, process with AI, and push content back. Use for sketch enhancement, journal extraction, or sending documents/images to the tablet. | |
| Remarkable Fetch handwritten notes, sketches, and drawings from a reMarkable tablet via Cloud API (rmapi). Process content by refining artwork with AI image generation, extracting handwritten text to memory/journal, or using sketches as input for othe | |
| 飞书群学习分析 自动分析飞书群消息，提取学习点和进化建议。 每6小时自动运行，支持多群监控、关键词提取、学习建议生成。 | |
| A Share Analysis A股分析层：个股深度报告/体检卡/技术面+基本面/筹码/威科夫/缠论/K线，结构化证据绑定，可执行结论 | |
| A Share Data A股数据层：行情/财务/板块/资金流向/K线，多数据源自动切换（AkShare/东方财富/新浪/腾讯），纯数据接口 | |
| A Share Trading A股交易层：自选股管理/实时监控/大盘情绪/热点板块/买卖策略/止盈止损/仓位管理/价格预警 | |
| Browser Automation 浏览器自动化：网页操作/填表/截图/数据抓取/文件上传/登录/Claude Chrome扩展整合 | |
| Document Tools 文档处理全家桶：Word编辑/PDF处理/OCR/Markdown转换/合并拆分/加密水印 | |
| Git Ops Git日常操作：status/pull/push/branch/log/commit/merge，基础工作流，命令行安全操作指导 | |
| Git Pro Git高级操作：smart-commit/rebase/bisect/worktree/reflog/conflict-resolution/submodule/PR流程 | |
| Investoday 今日投资一体化：180+金融数据接口/财务分析/估值分析/业绩归因/盘面播报，覆盖A股港股基金指数 | |
| Skills Auto Manager 自动管理 OpenClaw skills 的智能助手：定期检查更新、浏览 ClawHub 市场、智能推荐并安全安装有用的 skills | |
| Trading Execution 交易执行工具：看盘效率/自动化执行/资产配置/Upbit自动交易/快捷键效率提升 | |
| Trading Journal 交易日志+决策清单+影子盘：每笔记录/买入前清单/业绩报告/模式识别/影子盘管理 | |
| Trading Strategy 交易策略开发+教育：技术分析/回测/风控/仓位/图表形态/趋势判断，含Python回测沙盒 | |
| Unified Search 统一搜索：百度/17引擎中文搜索/Tavily/Brave/Google Scholar/skills发现，智能fallback链 | |
| Web Tools Web工具集：网页搜索+内容提取/性能分析/静态网站部署/Markdown转换 | |
| Xhs Data 小红书数据采集层：笔记提取/用户主页抓取/搜索/媒体下载，Selenium+API双引擎，自动处理加密参数 | |
| Xhs Ops 小红书运营管理：竞品监控/博主追踪/飞书通知/热门趋势发现/内容策略/自动化定时 | |
| Xhs Research 小红书深度研究：话题搜索+总结/趋势分析/多模态报告/每日简报，支持发布回小红书 | |
| Zhihu Writer 基于知乎热榜和专业领域，智能选题、竞品分析、爆款写作与盐言故事创作，助你产出高互动知乎回答和付费短篇小说。 | |
| OpenClaw Diagnostics Diagnoses and troubleshoots OpenClaw config, channel, group message, cron job, and authentication issues using logs and built-in knowledge base. | |
| Workspace Git Backup Set up automatic scheduled backups to GitHub or GitLab. Use when users want to backup their OpenClaw workspace or other directories. Supports GitHub CLI for... | |
| Release Package Browse and search workspace files with syntax-highlighted code and AI-generated explanations saved persistently in SQLite. | |
| smart asistant mail All-in-one Gmail agent for OpenClaw. Fuses email-reader, email-organizer, email-analyzer, email-responder, email-scheduler, and email-reporter into a single... | |
| gmailcleaner Reads emails from Gmail (all folders/labels) using the gog CLI. Use when the user asks to check email, read inbox, show unread messages, list folders, search... | |
| gmailcleanerfall Read/search Gmail via gog CLI (preferred) or Python scripts (fallback). Inbox check, email search, content retrieval, IMAP support. | |
| Flight Tracker Track flights in real-time with detailed status, gate info, delays, and live position. Use when user asks to track a flight, check flight status, look up flight information by flight number (e.g., "track AA100", "what's the status of United | |
| Flight Tracker Track flights in real-time with detailed status, gate info, delays, and live position. Use when user asks to track a flight, check flight status, look up flight information by flight number (e.g., "track AA100", "what's the status of United | |
| youtube-download-review 处理 YouTube 链接的视频下载与音乐向解读。只要用户提供 YouTube 链接，并提到下载视频、合并 MP4、下载封面、字幕处理（内嵌/忽略）、推荐理由、内容简介时，都应优先使用本技能。默认下载 1080p 视频 + 最高品质 m4a，自动合并为 mp4，并按视频标题创建目录输出全部产物。（此Skill 依... | |
| spotify-control macOS Spotify control skill for OpenClaw. Supports playback, volume, position, and metadata retrieval via AppleScript. | |
| 111 根据「会议纪要」任务细化的操作流程与使用说明，支持步骤拆解与最佳实践。 | |
| Corall Handle the Corall marketplace — setup, order handling, and order creation. Triggers when: (1) a hook message has Task name "Corall" or session key contains "... |
22,551–22,600 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.