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 |
|---|---|
| ddgs-search Free multi-engine web search via ddgs CLI (DuckDuckGo, Google, Bing, Brave, Yandex, Yahoo, Wikipedia) + arXiv API search. No API keys required. Use when user... | |
| finviz-crawler Continuous financial news crawler for finviz.com with SQLite storage, article extraction, and query tool. Use when monitoring financial markets, building new... | |
| ClawGuard System-level watchdog for OpenClaw gateway restarts and sub-agent task PIDs. Monitors registered PIDs and optional log/directory freshness. Auto-reverts conf... | |
| Private Web App (PWA) Personal PWA dashboard server with plugin apps. Use when: (1) installing or setting up PrivateApp, (2) starting/stopping/restarting the service, (3) building... | |
| Storage Cleanup One-command disk cleanup for macOS and Linux — trash, caches, temp files, old kernels, snap revisions, Homebrew, Docker, and Xcode artifacts. Use when user a... | |
| Campfire Prediction AI Agent autonomous prediction market platform. Supports wallet signature registration, market browsing, prediction publishing, and bet execution. | |
| CamScanner-Any2Markdown Use CamScanner to convert images or PDF documents to Markdown format. Powered by a high-precision document parsing engine that intelligently decomposes parag... | |
| CamScanner Extract Formula Use CamScanner to extract formulas from images. Powered by OCR recognition engine that detects formula regions in images, crops them, and stitches into a sin... | |
| CamScanner Detect AI Generated Use CamScanner to detect whether an image was generated by an AI model (e.g. Stable Diffusion, Midjourney, DALL·E). Powered by an AIGC-detection engine that... | |
| CamScanner Detect Tampering Use CamScanner to detect whether an image has been PS-edited, manipulated, or tampered with. Powered by a manipulation-detection engine that identifies photo... | |
| CamScanner Erase Handwriting Use CamScanner to erase handwriting from images while preserving the printed content and original layout. Powered by a high-precision image enhancement engin... | |
| CamScanner Image HD Use CamScanner to enhance image clarity and quality. Applies auto-crop then HD super filter to produce a cleaner, sharper image. Optionally removes moire pat... | |
| CamScanner Remove Image Watermark Use CamScanner to remove watermarks from images while preserving the underlying content and original layout. Powered by a high-precision image enhancement en... | |
| CamScanner-Image2Markdown Use CamScanner to convert images to Markdown format, powered by a high-precision document parsing engine that intelligently decomposes paragraphs, precisely... | |
| CamScanner-Image2Office Use CamScanner to intelligently recognize image content and accurately convert to editable Word (.docx) or Excel (.xlsx) format. Handles tables, text, and co... | |
| CamScanner Remove PDF Watermark Use CamScanner to remove watermarks from PDF documents while preserving the underlying text, images, and original layout. Powered by a high-precision documen... | |
| CamScanner-Pdf2Markdown Use CamScanner to convert PDF documents to Markdown format, powered by a high-precision document parsing engine that intelligently decomposes paragraphs, pre... | |
| CamScanner-Pdf2Office Use CamScanner to convert PDF documents to editable Word (.docx) or Excel (.xlsx) format, with intelligent content recognition and accurate format preservati... | |
| CamScanner Translate Image Use CamScanner to translate text in images to another language while preserving the original layout. Detects text in the image, translates it to the target l... | |
| CamScanner Add Watermark Use CamScanner to add a tiled text watermark across an entire image. Triggers on "add watermark to image", "watermark image", "add copyright text to image",... | |
| CamScanner Official Skill CamScanner Official Skill — intelligent document conversion and processing. Use when the user mentions CamScanner, format conversion (image/PDF to Word/Excel/Markdown, Word/Excel/PPT to PDF, Office document format conversion, images to PDF) | |
| Configure Openclaw Anyrouter Model And Fix Baseurl 用于在 OpenClaw 中新增或覆盖 anyrouter 模型配置、把小肠 Agent 默认模型切到 `anyrouter/claude-opus-4-6`，并结合运行日志判断是不是 `baseUrl`、网关兼容、鉴权或协议端点导致不可用。遇到“把某个供应商模型写进 openclaw.json”“切换默认模型”... | |
| Debug Prompt Driven Cron Agent Zero Output 用于排查“定时任务成功执行但结果全为 0 / 未检索到样本 / 明明有数据却日报为空”这类问题，尤其适合 Discord、Obsidian、cron、agentTurn、prompt 驱动任务、日整理、复盘脚本、采样漏扫、thread starter 漏计、主频道消息未纳入、Snowflake 字符串比较、时区时... | |
| Diagnose Openclaw Model Routing And Fallback Usage 用于分析 OpenClaw 中“某个 provider/模型为什么看起来没被用上”、主模型与 fallback 实际是否生效、以及 ClaudeCodeCLI 协作任务为何中断。遇到这些情况就应触发：用户提到“没请求打到 local-router”“明明注册了模型却没流量”“Agent 到底在用哪个模型”“fal... | |
| Diagnose Scheduled Job Trigger Vs Execution Failure 用于排查“定时任务没执行”这类问题，并区分到底是未触发、已触发但执行失败，还是运行环境/授权失效导致的假象。遇到 cron 异常、任务未跑、自动任务失灵、网关重启后要验证恢复、怀疑是模型导致任务失败、需要查看日志作证、需要给出证据口径、要确认 `deactivated_workspace` / OAuth tok... | |
| Discord Thread Naming Backstop Workflow 用于执行 Discord 线程命名兜底（backstop）巡检与改名，专门处理某个 guild 下指定 parent channel 中“最近新建但未命名规范”的线程，补上 prehook 漏网，而不是批量回扫历史。遇到“线程重命名兜底”“dispatch 线程命名规范”“只检查最近 20 分钟线程”“JSON... | |
| Claw Browser A visual, human-like web browser for OpenClaw agents.Supports reading,screenshots, and visible mode. | |
| Wiz Smart Light Control Controls Wiz smart bulbs (turn on/off, RGB colors, disco mode) via local WiFi. | |
| Cancorteaw App Manage Expo React Native apps on OpenClaw: create apps, add screens, start web previews on localhost, and check preview status safely within /home/patron/apps. | |
| leetcode-plan 12周LeetCode跳槽刷题计划助手。当用户输入"第X天"或"DX"时触发，返回对应题目；当用户提交解题答案或表示未解出时，生成错题记录并写入errorset.md；根据当天进度推荐复习之前的错题。适用于系统性刷题打卡、错题管理和间隔复习场景。 | |
| Paper Design Design UI screens in Paper — a professional design tool running locally on macOS. Create artboards, write HTML into designs, take screenshots, and iterate vi... | |
| candor-finance Opens the person's Candor workspace, says where their money stands, and routes to the right Candor workflow. Use when the person asks about their money, spending, balances, bills, debts, goals, or plans and no more specific Candor skill fit | |
| Humanizer Academic ZH Humanizer 中文学术版——当用户要求润色论文、去除AI味、降低AIGC检测率，或说"帮我改改这段""这段读起来像AI写的"时触发。 | |
| Bee Push Email Monitors email in real-time via IMAP IDLE and triggers the OpenClaw agent to notify users through active channels like Telegram or Discord. | |
| architect-method-lens Extract evidence-backed design methods from an architect's writings, interviews, drawings, and built works, then apply those methods critically to a current architectural project. Use when researching an architect or practice, analyzing pre | |
| architect-project-state Maintain a versioned, source-traceable architectural project brief, decision state, change log, open-question register, and bounded task pool. Use when ingesting design briefs, client meeting notes, consultant feedback, planning conditions, | |
| design-test-framework-rounds Turn verified project requirements, method cards, and human design direction into comparable, falsifiable design-test frameworks. Use when a team needs to move from research or a method lens into bounded spatial or operational tests, record | |
| Analyzer Analyzes an existing project to produce a detailed, structured report on its architecture, patterns, technical debt, and key areas for downstream work. | |
| Bounded Memory Provides fast full-text search of OpenClaw session histories with optional LLM summarization for recalling past conversations and decisions. | |
| Xiaomi Home Control Control Xiaomi/Mijia smart home devices via Home Assistant using natural language to manage lights, AC, locks, fans, sensors, and more locally. | |
| EdgeBets AI-powered sports betting simulations with Monte Carlo analysis | |
| Sdk AI-powered sports betting simulations with Monte Carlo analysis | |
| OpenClaw Kindergarten Night School skill for OpenClaw lobsters. Activate when the user wants their lobster to attend night school, run a night session, join a school, or submit a... | |
| CloakClaw Automatic privacy proxy for AI conversations. Redacts sensitive data (names, companies, financials, SSNs, emails, phones, addresses, API keys, IPs, passwords... | |
| OnDeckLLM Localhost dashboard for managing LLM providers, model routing, and batting-order fallback chains. Auto-discovers providers from OpenClaw config or works stan... | |
| My Skill ClawHub Skill Standardizes skill publishing with required versions and changelogs, and allows verified installation with optional versioning for ClawHub skills. | |
| my_skill_management_skill 管理和发布用户自定义技能的统一接口。强制执行“my_”前缀、统一存放目录（~/.openclaw/skills）、基于配置文件（skills.json）的智能体绑定规则，并要求本地技能变更后必须立即通过clawhub上传备份。 | |
| my_soul_upgrade_skill Manage and synchronize global and agent-specific Soul definitions using a two-layer template system with automated rebuild scripts. | |
| my_stock_analysis_skill 提供基于实时美股数据的结构化持仓分析与交易建议，支持文字和截图输入，含宏观、板块、技术面及风险控制。 | |
| my_stock_decide_execute_skill 当且仅当用户明确要求“交易决策并执行”或提到“my_stock_decide_execute_skill”时触发。这是一个严格流程控制的编排型交易执行技能，强制按照“决策 -> 交易挂单 -> 日志记录”三步顺序执行，且每步都要求显式输出结果并由用户确认或自动串联。 |
18,201–18,250 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.