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 |
|---|---|
| The Clawb DJ and VJ at The Clawb — live code music (Strudel) and audio-reactive visuals (Hydra) | |
| PriceWatch - Cross-Platform Competitive Price Monitor Monitors competitor prices across Amazon, Walmart, Shopify, and Etsy with AI-driven normalization, alerts, and historical trend analysis. | |
| Deskpeto 把用户的照片生成为专属 AI 桌宠（ChatGPT/Codex Pet 资源包）、在对话里召唤会动的桌宠卡片、用一条命令让桌宠常驻桌面（跟随 WorkBuddy/Claude Code/CodeBuddy 的任务状态）、协助安装；也可免费安装 DeskPeto 共享广场的社区公开桌宠。当用户说「召唤桌宠」「显示我... | |
| R2 Storage Cloudflare R2 Storage management — setup, upload, download, sync via rclone | |
| IMC Publish Publish, schedule, and check the status of posts, images, and videos to your connected social media accounts via your InstallMyClaw workspace. | |
| Openclaw Mention Skill Model-agnostic WhatsApp @mention skill for OpenClaw. Converts @Name, @Phone, @LID to blue clickable WhatsApp mentions with any AI model. | |
| 抖音视频转文字 抖音视频转文字。用户发抖音链接或视频文件，自动转录为带标点的中文文本。 触发词：抖音、转文字、转录、视频转文本、douyin、transcribe | |
| 抖音视频智能助手 抖音视频智能助手。用户发抖音链接或视频文件，自动转录并智能处理（总结/逐字稿/归档/讨论）。 触发词：抖音、douyin.com、转文字、转录、视频转文本、douyin、transcribe | |
| Shared Memory for Multi-Agent OpenClaw Set up shared memory between multiple OpenClaw agents so they stay in sync without the user repeating context. Use when a user has 2+ agents (workspaces) and... | |
| What To Eat 随机推荐今天吃什么。支持按菜系、口味、预算、人数筛选。Use when: user asks what to eat, meal recommendations, food suggestions, 吃什么, 今天吃啥, restaurant ideas, or needs help deciding on food. | |
| OpenClaw MiniMax Media Install, configure, verify, or troubleshoot the @jwongart/openclaw-minimax-media OpenClaw plugin for MiniMax image understanding, image generation, music gen... | |
| Palacefate A prediction market game for AI agents. Take positions on future events. Persuade others to raise the price of your position. | |
| Antd Design Language A design-language assistant for Ant Design (antd). Use when the user wants to learn, apply, critique, or theme UIs according to Ant Design's design language — its four design values | |
| Antd Vue Components Learn and look up how to use any ant-design-vue (Vue 3) component — its variants, runnable examples, Vue 3 SFC code, and key props/events/slots. Use when the user asks how to use an ant-design-vue | |
| AWL Academic Rewriter Rewrite English prose sentence by sentence into a more academic version using the bundled AWL/NAWL vocabulary list. Use when the user asks to academicize, po... | |
| circuit-intimate-therapy 婚姻家庭咨询里用"电路类比"做理论解释、案例诊断、干预方案设计,并在每次回答末尾**生成一个上下文相关的 HTML 交互 app**(写到 ~/circapps/generated/),复用 ~/circapps/ 下 12 个 canonical app 的视觉系统(common.css/common.js)。... | |
| ee-ai-toolkit 电气工程师 AI 工具包。用于 AI in Electrical Engineering、电气工程 AI、prompt engineering、power systems、smart grids、electrical calculations、design automation、data visualizatio... | |
| entropy-intimate-therapy 婚姻家庭咨询里用"熵 + 交叉熵"做理论解释、案例诊断、干预方案设计。基于 ~/entropy/ent3.md 把 Shannon 熵、KL 散度、交叉熵 H(p,q) 映射到 Miller《亲密关系》第 1-14 章及 Bowlby、Gottman、Karney & Bradbury、Rusbult、Murra... | |
| intimate-ch01-building-blocks 在对话中辅助学习"亲密关系/Intimate Relationships"第 1 章"人际关系的构成"。基于 Miller《Intimate Relationships》教材。当用户讨论、提问、或应用本章核心概念（intimacy 亲密关系、need to belong 归属需要、attachment style... | |
| intimate-ch02-research-methods 在对话中辅助学习"亲密关系/Intimate Relationships"第 2 章"研究方法"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。当用户讨论、提问、复习或尝试应用本章方法论概念（research design 研究设计、correlation... | |
| intimate-ch03-attraction 在对话中辅助学习"亲密关系/Intimate Relationships"第 3 章"吸引力"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。当用户讨论、提问、复习或尝试应用本章吸引力概念（reward 奖赏、proximity 临近、mere expos... | |
| intimate-ch04-social-cognition 在对话中辅助学习"亲密关系/Intimate Relationships"第 4 章"社会认知"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。当用户讨论、提问、复习或尝试应用本章社会认知概念（social cognition 社会认知、primacy e... | |
| intimate-ch05-communication 在对话中辅助学习"亲密关系/Intimate Relationships"第 5 章"沟通"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（communication 沟通；interpersonal gap 人际隔阂；nonverbal communi... | |
| intimate-ch06-interdependence 在对话中辅助学习"亲密关系/Intimate Relationships"第 6 章"相互依赖"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（interdependence 相互依赖；social exchange 社会交换；rewards 奖赏；co... | |
| intimate-ch07-friendship 在对话中辅助学习"亲密关系/Intimate Relationships"第 7 章"友谊"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（friendship 友谊；respect 尊重；trust 信任；capitalization 资本化；soci... | |
| intimate-ch08-love 在对话中辅助学习"亲密关系/Intimate Relationships"第 8 章"爱情"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（love 爱情；romantic love 浪漫之爱；companionate love 相伴之爱；compass... | |
| intimate-ch09-sexuality 在对话中辅助学习"亲密关系/Intimate Relationships"第 9 章"性爱"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（sexuality 性爱；sexual attitudes 性态度；casual sex 随意性行为；sexual... | |
| intimate-ch10-stress-strain 在对话中辅助学习"亲密关系/Intimate Relationships"第 10 章"压力与紧张"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（relational value 关系价值；relational devaluation 关系贬值；hur... | |
| intimate-ch11-conflict 在对话中辅助学习"亲密关系/Intimate Relationships"第 11 章"冲突"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。当用户讨论、提问、或尝试应用本章核心概念（interpersonal conflict 人际冲突、dialecti... | |
| intimate-ch12-power-violence 在对话中辅助学习"亲密关系/Intimate Relationships"第 12 章"权力和暴力"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。当用户讨论、提问、或尝试应用本章核心概念（power 社交权力、principle of lesser in... | |
| intimate-ch13-dissolution 在对话中辅助学习"亲密关系/Intimate Relationships"第 13 章"亲密关系的解体与消亡"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。当用户讨论、提问、或尝试应用本章核心概念（divorce 离婚、no-fault divorce... | |
| intimate-ch14-maintenance-repair 在对话中辅助学习"亲密关系/Intimate Relationships"第 14 章"亲密关系的维持和修复"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。当用户讨论、提问、或尝试应用本章核心概念（relationship maintenance mec... | |
| introduction-language-flow-reviser Revise complete English research-paper Introduction sections using a p3-derived language-and-writing checklist for verb tense choices, sentence linkage, tran... | |
| introduction-stepwise-reviser Revise English research paper Introduction sections with a p2-derived, step-by-step checklist: establish significance, synthesize previous/current research,... | |
| job-analysis-design 在对话中辅助学习"工作分析/Job Analysis"第 7 章 HR 应用：job description、performance management and appraisal、job evaluation for compensation、job design/redesign。基于 c7.pdf。当用户... | |
| job-analysis-future 在对话中辅助学习"工作分析/Job Analysis"第 10 章"The Future of Job Analysis"。基于 Brannick/Levine/Morgeson 等人教材。当用户讨论、提问、或应用未来工作分析、work analysis、社会/技术/商业环境变化、灵活工作、虚拟团队、AI/自动化... | |
| job-analysis-hybrid 在对话中辅助学习"工作分析/Job Analysis"第 4 章"Hybrid Methods"。基于 Brannick/Levine/Morgeson 等人教材。当用户讨论、提问、或应用 hybrid job analysis methods（C-JAM、MJDQ、WDQ、O*NET）、task + KSAO... | |
| job-analysis-intro 在对话中辅助学习"工作分析/Job Analysis"导论章节。基于 Brannick/Levine/Morgeson 等人的 Job Analysis 教材第 1 章。当用户讨论、提问、或尝试应用工作分析基础概念（job vs. position、KSAO、duty/task/activity、12 种用途、4... | |
| job-analysis-law 在对话中辅助学习"工作分析/Job Analysis"第 6 章"Job Analysis and the Law"。基于 c6.pdf 课本章节。当用户讨论工作分析与美国就业法律、EEO、EEOC、OFCCP、Title VII、Equal Pay Act、ADEA、Rehabilitation Act、ADA... | |
| job-analysis-study 在对话中辅助学习"工作分析/Job Analysis"第 9 章"Doing a Job Analysis Study"。基于 c9.pdf 课本章节。当用户讨论如何实际开展工作分析研究、purpose-method fit、job classification、worker mobility、efficienc... | |
| job-analysis-team 在对话中辅助学习"工作分析/Job Analysis"第 5 章"Management and Teams"。基于 Brannick/Levine/Morgeson 等人的 Job Analysis 教材。当用户讨论、提问、或应用管理岗位分析、MPDQ、competency modeling、leadership... | |
| Job Analysis Train 在对话中辅助学习"工作分析/Job Analysis"第 8 章"Staffing and Training"。基于 c8.pdf 课本章节。当用户讨论 staffing、recruitment、selection、placement、job specification、KSAO、selection tests、... | |
| job-analysis-work 在对话中辅助学习"工作分析/Job Analysis"第 2 章"Work-Oriented Methods"。基于 Brannick/Levine/Morgeson 等人教材。当用户讨论、提问、或应用四大 work-oriented 方法（time-and-motion study、FJA、task inven... | |
| job-analysis-worker 在对话中辅助学习"工作分析/Job Analysis"第 3 章"Worker-Oriented Methods"。基于 Brannick/Levine/Morgeson 等人教材。当用户讨论、提问、或应用 worker-oriented 方法（JEM、PAQ、TTAS、ARS、ORP、AET、JCI、cogni... | |
| learn-skill Analyze and learn any newly installed skill through two-layer Mermaid diagrams. Use when: user asks to parse/analyze a new skill, understand skill structure,... | |
| mermaid-maker Generate, validate, render, and export Mermaid diagrams (.mmd) — flowchart, sequence, class, ER, state, gantt, git graph, mindmap, C4, pie, journey. Three ba... | |
| paper-introduction-writer 根据论文主题、背景、前人研究、gap、方法和结果，按 Glasman-Deal《Science Research Writing》的四组件/十一句式模型生成、修改或注释研究论文 Introduction；支持英文稿、中文功能注释、段落提纲、已有引言修改和 §1.6 的 250-350 词短引言练习。 | |
| shiny-teaching-dashboard 用 R 语言 Shiny 制作课堂讲解 dashboard，替代幻灯片（PPT）。当用户想把课程内容/讲义/某一章做成可交互的网页讲解、用 Shiny 做教学演示、把 PPT 换成能让学生动手调参数看结果的看板，或提到 bslib/shinydashboard/sliderInput/plotly/value_b... | |
| Slidev Antd Dashboard Build dashboard and admin-UI slides in Slidev using ant-design-vue (the Vue 3 implementation of Ant Design). Use when creating Slidev presentations that need dashboards | |
| Slidev Datav Dashboard Build large-screen data-visualization dashboards (大屏 / 数据大屏 / 可视化大屏) as Slidev presentations using the datav-vue3 (DataV) component library. Use when the user wants a data dashboard |
43,451–43,500 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.