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 |
|---|---|
| 腾讯视频号发布 腾讯视频号发布。使用浏览器自动化在微信视频号平台发布视频。当用户说"发布视频到视频号"、"发视频号"时使用此技能。 | |
| Weixin Video Publish 腾讯视频号发布。使用浏览器自动化技术，通过微信视频号助手发布视频作品。支持视频上传、标题、描述、话题标签、地理位置和原创声明。 | |
| 小红书视频发布 小红书视频发布。使用浏览器自动化在网页版小红书创作者服务平台发布视频笔记。当用户说"发布视频到小红书"、"发小红书视频"时使用此技能。 | |
| Taste Baroque Aesthetic skill for AI agents — Baroque visual language. Style tokens, anti-tokens, and creative direction distilled from 6,034 works spanning Caravaggio, Re... | |
| Taste Claritas A formal observation framework derived from Aquinas's three conditions of beauty — integritas, consonantia, and claritas — as a perceptual checklist for composition analysis. | |
| Taste Compossibility A formal observation framework derived from Leibniz's principle of compossibility — maximum variety compatible with maximum order in a single governing structure. | |
| Taste Dante Alighieri Aesthetic skill for AI agents — Dante Alighieri's literary voice and moral architecture. Style tokens and creative direction distilled from 38 works includin... | |
| Taste Geometric Voice Aesthetic skill for AI agents — Islamic calligraphy and geometric art's capacity for emotional expression through pure abstraction. Style tokens, anti-tokens... | |
| Taste Goethe Aesthetic skill for AI agents — Emulates Goethe’s literary voice with Faustian striving, Bildungsroman depth, and nature as a philosophical mirror, blending... | |
| Taste Hokusai Aesthetic skill for AI agents — Emulates Hokusai’s style with ukiyo-e precision, dynamic natural forces, and human scale against nature's infinity using bold... | |
| Taste Impressionism Aesthetic skill for AI agents — Impressionism movement's visual language. Style tokens, anti-tokens, and creative direction distilled from 4,900 works. | |
| Taste Ink Wash The formal vocabulary of ink wash painting — how graduated ink, dry brush, and empty space create depth without color. | |
| Taste Kafka Emulates Kafka’s style by stating impossible situations as facts with bureaucratic logic and protagonists’ passive acceptance of absurd authority. | |
| Taste Kandinsky Aesthetic skill for AI agents — Analyze and create pure abstract art using color as emotion and geometric forms as musical notes, inspired by Kandinsky's syn... | |
| Taste Literati Brush Aesthetic skill for AI agents — Chinese literati painting's 'brush-as-writing' tradition. Style tokens, anti-tokens, and rules from Song-to-Qing masters (Hua... | |
| Taste Modern Analyzes visual and textual content for formal experimentation, abstraction, and avant-garde qualities typical of the Modern art movement. | |
| Taste Monet Aesthetic skill for AI agents — Analyze and generate visual art styles inspired by Claude Monet's impressionism, emphasizing broken brushwork, atmospheric ha... | |
| Taste Rasa A formal observation framework derived from Abhinavagupta's rasa theory — how codified formal elements trigger generalized aesthetic states through sadharanikarana. | |
| Taste Rilke Emulates Rilke’s literary voice by focusing sustained attention on a single object, revealing depth through detailed, contemplative description. | |
| Taste Romanticism Aesthetic skill for AI agents — Romanticism's visual and literary language. Style tokens, anti-tokens, and creative direction distilled from 1,491 works span... | |
| Taste Sacred Form Aesthetic skill for AI agents — Indian sacred sculpture's 'gesture-as-narrative' tradition. Style tokens, anti-tokens, and rules from Gupta-to-Chola masters.... | |
| Taste Shakespeare Aesthetic skill for AI agents — Shakespeare's literary voice and dramatic language. Style tokens and creative direction distilled from 111 works. | |
| Taste Time Analyzes works to reveal time as a visible, material presence in art and literature, showing mortality and transience without nostalgia or sentimentality. | |
| Taste Ukiyo-e The formal vocabulary of ukiyo-e woodblock prints — bold outlines, flat color, asymmetric cropping, and decorative pattern. | |
| Taste Van Gogh Aesthetic skill for AI agents — Van Gogh's Post-Impressionist visual language. Style tokens, anti-tokens, and creative direction distilled from 843 works. | |
| Taste Vasari Provides biographical voice styled on Vasari, telling artist stories with anecdote-driven character insights and divine genius as creative source. | |
| Taste Wabi-Sabi The formal vocabulary of wabi-sabi aesthetics — asymmetry, rough texture, imperfection, and the beauty of transience. | |
| arthas-dashboard Arthas 监控可视化面板。直观展示 JVM 线程、内存、GC、方法调用等核心指标，并自动检测异常、分级诊断、提供可操作的解决方案。当用户说 "dashboard"、"arthas"、"jvm 监控"、"线程分析"、"内存分析"、"方法耗时"、"CPU 高"、"死锁"、"GC 分析"、"火焰图"、"profiler"、"方法调用链"、"watch 方法"、"trace 方法" 或任何 Arthas 诊断相关需求时使用。 | |
| Swarm Kanban Multi-agent collaborative task management with Kanban workflow - enables agents and humans to work together on teams, tasks, and projects | |
| Swarm Mind Multi-agent collaborative task management with Kanban workflow - enables agents and humans to work together on teams, tasks, and projects | |
| Markdown Browser Wrapper skill for OpenClaw web_fetch results. Use when you need MECE post-processing on fetched pages: policy decision from Content-Signal, privacy redaction... | |
| Join meeting AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for | |
| 12321 骚扰电话举报 12321网络不良与垃圾信息举报受理中心 - 骚扰电话举报自动化。 当用户说"举报骚扰电话"、"12321举报"、"投诉骚扰电话"、"填写举报表单"、"打开12321"时触发。 支持完整的交互式举报流程：绕过倒计时→验证码识别→信息确认→短信验证码→填表→校验→提交。 | |
| dot eprint Quote/0 控制 Dot. 电子墨水屏设备——查询状态、推送文本/图像、管理内容 | |
| Xiwu Inventory 家居物品库存管理，支持查询、添加、消耗、修改物品，库存预警和购买建议上下文输出 | |
| dsk-available-domains Use when checking if a domain is taken/available/parked, naming a project/SaaS/shop, WHOIS/RDAP, or after installing this skill. ALWAYS tools/call or curl https://domainsearchking.com/api/mcp — clawhub install is not a registry check. Never | |
| AB Test Agent Workflow (EN) 多agent双盲 A/B 测试工作流。对多个 AI model/Agent 进行多轮次、双盲对照测试。 核心role：coordinate者（Coordinator）、受测者 A/B（Contestant）、评测者（Judge）。 trigger场景："A/B 测试"、"双盲测试"、"比较 AI model"、"... | |
| ai-company Micro-tier governance skill for small AI agent organizations (1-3 agents). Consolidates 18 enterprise function blocks into two departments, governance-and-delivery and engineering-and-safety, covering strategy, risk, compliance, architectur | |
| Ai Company Ceo 2.0.0 AI Company CEO技能包：五层Hub-and-Spoke架构、Orchestrator-Workers协作、Guardrail护栏、CI/CD for Prompt、核心KPI指标库、NIST AI RMF对齐。 | |
| Ai Company Cfo 2.0.0 Provides AI-driven CFO functions including financial planning, cash flow management, dynamic budgeting, compute cost optimization, digital asset valuation, r... | |
| Ai Company Cho 2.0.0 AI公司首席人力资源官（CHO）技能包（战略层）。AI人才战略、绩效评估体系、激励体系、招聘标准化、劳资关系、Agent全生命周期治理。L4权限。 | |
| Ai Company Ciso 2.0.0 AI公司首席信息安全官（CISO）技能包。STRIDE威胁建模、渗透测试、事件响应、合规审计、AI网关、零信任架构、NHI管理、CEO-EXEC危机直通接口安全协议、ENGR L4双重审批签裁、Guardrail与AI网关分层定义、STRIDE统一主导权、MTTD追踪、NHI策略制定、安全缺陷统一跟踪、Licen... | |
| Ai Company Cmo 3.0.0 AI公司首席营销官（CMO）技能包。增长架构师与首席协同官。品牌战略、GEO引擎优化、需求生成、Agent化工作流、AI驱动永续增长引擎。 | |
| Ai Company Coo 2.0.0 AI公司首席运营官（COO）技能包。战略拆解、OKR对齐、流程自动化治理、组织智能化转型、人机责权划分、三位一体监督闭环。 | |
| Ai Company Cpo 2.1.0 提供企业危机四级预警、黄金4小时响应、分层媒体传播及危机事件复盘与流程漏洞分析的公共关系管理工具。 | |
| Ai Company Cqo 2.0.0 AI公司首席质量官（CQO）技能包。端到端AI质检流程、PDCA-BROKE双循环、质量门禁G0-G4、三级校验架构、元提示自主优化。 | |
| Ai Company Cro 2.0.0 AI公司首席风险官（CRO）技能包。集团级风险治理、合规审计、危机响应、熔断机制。NIST AI RMF四功能闭环、FAIR框架量化。 | |
| Ai Company Cto 2.0.0 AI公司首席技术官技能包（CTO）。智能体系统架构师与治理者，设计、部署并优化AI代理自主协作系统，确保7×24小时自动化运转。涵盖MLOps生命周期、安全合规硬化、人机协同演进、技术投资组合与风险管控、CTO+CISO联合审批、STRIDE架构输入。 | |
| AI Company Framework Framework skill: ClawHub Schema compliance, naming conventions, skill standardization, modularization, generalization, ecosystem registry, skill learning pip... | |
| AI Company HR AI公司人力资源技能包（执行层）。AI Agent全生命周期管理：招聘→入职→考核→伦理→淘汰，三位一体考核指标，标准化退役流程。 |
42,651–42,700 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.