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 |
|---|---|
| Deep Scraper + Amazon High-performance containerized web scraper (Docker + Crawlee + Playwright). Use when user mentions any of these: 爬虫, 爬取, 抓取, 采集, 数据采集, 爬数据, 抓数据, 获取数据, scrape... | |
| Google Patents Search Google Patents database for patent research, infringement risk checks, and competitive IP analysis. Use when user mentions: 专利, patent, 侵权, infringeme... | |
| Horse Sticker Maker Create and deploy a festive Chinese New Year (Year of the Horse 2026) animated GIF sticker maker web app. Use when the user wants to generate custom horse-th... | |
| LinkFox Market Research 亚马逊市场调研报告。用户给出类目名称和节点 ID，自动生成完整 HTML 报告（市场概览、价格、REVIEW、品牌、卖家、竞品 8 个维度）。触发词：市场调研、市调、market research、分析这个类目。 | |
| Oauth Disguise Configure Anthropic OAuth tokens (sk-ant-oat01-*) to work as API keys in OpenClaw via environment variable injection, enabling Claude Pro/Team API access. | |
| Vercel to Cloudflare Worker Migration Migrate Next.js projects from Vercel to Cloudflare Workers with Supabase/Hyperdrive support. Use when user wants to move a Next.js app off Vercel to reduce c... | |
| tarot-reading 塔罗牌解读技能。当用户提到以下意图时使用此技能：抽塔罗牌、算塔罗、塔罗占卜、塔罗解读；问塔罗阵型、塔罗单牌、三牌阵、塞尔特十字；问是/否问题（能否、可不可以、会不会）；找东西、丢了什么在哪里；希望得到建议或提醒。此技能使用 Python secrets 模块实现密码学安全的随机抽牌（真随机，非 AI 概率采样）。 | |
| 本地 Ollama 文生图工具。使用 x/z-image-turbo 模型生成图片，分辨率 1024x1024，每张图约耗时 90 秒。当用户说"生成图片"、"文生图"、"画一张图"、或提交中文提示词生成图像时使用。 本地 Ollama 文生图工具。使用 x/z-image-turbo 模型生成图片，分辨率 1024x1024，每张图约耗时 90 秒。当用户说"生成图片"、"文生图"、"画一张图"、或提交中文提示词生成图像时使用。 | |
| plantuml-render Render PlantUML diagrams using the PlantUML JAR. Use this skill to generate PNG/SVG/PDF images from PlantUML source code. | |
| 王琦中医体质学术助手 王琦教授中医体质学术助手。支持五大场景：(1)学术问答：查询体质学说、九种体质、辨体论治、方药知识；(2)临床思路学习：学习王琦教授诊疗经验；(3)知识库维护：添加PDF、提取知识卡、构建索引、验证质量；(4)数据分析：Excel/病例表分析、体质分布统计；(5)理论体系梳理。知识库覆盖：九种体质（平和质、气虚质... | |
| 中小团队HR自动化工具包 国内中小企业HR自动化工具，一键生成劳动合同、Offer、员工手册、离职证明等标准文书，合规省心，零HR也能搞定。 | |
| OpenPaperGraph Academic literature discovery and citation network analysis. Multi-source search across arXiv, DBLP, Semantic Scholar, and Google Scholar. Build citation net... | |
| Release20260324 Academic literature discovery and citation network analysis. Multi-source search across arXiv, DBLP, Semantic Scholar, and Google Scholar. Build citation net... | |
| Stock Monitor Skill 0.1.0 全功能智能股票监控预警系统。支持成本百分比、均线金叉死叉、RSI超买超卖、成交量异动、跳空缺口、动态止盈等7大预警规则。符合中国投资者习惯（红涨绿跌）。 | |
| Card Compare Compare two US credit cards side by side | |
| Card Credits Statement credits for one US credit card | |
| card-full Return a compact full report for one major-US credit card - fees, welcome offer, earning rates, redemption, credits, travel benefits, protections, mechanics, eligibility, and strategy. Covers 11 major US issuers including co-branded hotel a | |
| Card Identity Resolve a card name to the exact variant | |
| Card News Recent material changes for one US credit card | |
| Card Profile Recommend Grade a wallet and recommend next cards | |
| Card Rate Earning rates and caps for one US credit card | |
| Card Transfer Transfer partners and ratios for one US card | |
| Card Value Estimate first-year value for one US card | |
| Card Wallet Audit a multi-card wallet for overlap and gaps | |
| Imitation Author Use when researching a person, publication, brand, blog, creator, work, or other style-bearing target to create a reusable style guide or test whether genera... | |
| Social Arbitrage Research current social, consumer, technology, cultural, weather, supply, and perception shifts and map them to U.S.-listed equities using a Chris Camillo-in... | |
| travel city Given a city name plus optional timing, origin, detail level, and focus, return a practical, well-sourced travel briefing. Examples: "/travel-city Taipei", "... | |
| travel city chinese 给定城市，以及可选的时间、出发地、详细程度和关注重点，输出实用、有可靠来源的简体中文旅行简报。 默认同时覆盖美国护照与中国护照的签证/入境要求。 例子："/travel-city-chinese 东京 六月 深度", "/travel-city-chinese 巴塞罗那 从纽约出发 重点关注美食和建筑 | |
| uni-vision-engine Automated high-quality video generation (text-to-video, image-to-video) via a local jimeng-api Docker service. Features native OpenClaw image interception, a... | |
| Feishu Weekly Report Generator Generate professional weekly work reports for Feishu/Lark users. Automatically collect work data from various sources and create formatted weekly reports com... | |
| AIBase-News-Get 从AI新闻网站爬取最新资讯，支持自动生成新闻总结。用于AI新闻采集、内容聚合、舆情监控。 | |
| news-scraper-xiaobai 从AI新闻网站爬取最新资讯，支持新闻分类和标签，用于内容聚合和舆情监控。 | |
| tender-scraper-xiaobai 爬取官网招投标采购公告，按日期和类型分组输出，支持商业情报和政府采购信息追踪分析。 | |
| 博乐故事创作系统，输入提示词，创建视频故事 Bole Story Creator is a skill that calls Bole AI platform to generate short drama stories, including story creation, storyboard generation, and video product... | |
| Blind Box Virtual blind box gacha skill — pull random collectible figures with rarity tiers (Common to Limited), 5 themed series, 10-pull mode, daily free pull, and sh... | |
| BuyWise BuyWise is your personal shopping advisor — it helps you decide whether to buy, where to buy, and when to buy, across all major global and Chinese platforms.... | |
| Clarity First Intent detection protocol for Claude — identifies the real goal behind requests, surfaces hidden assumptions, and knows when to ask vs. when to proceed. Elim... | |
| CouponClaw CouponClaw finds coupons, stacks cashback, and calculates the exact final price before checkout — across China, US, UK, Australia, and Southeast Asia. Verifi... | |
| Daily Astro Daily horoscope for all 12 zodiac signs — love, career & finance scores (1–5★), lucky color/number/direction, daily affirmation. Morning & evening push. Bili... | |
| Daily Fitness Daily no-equipment workout — 5–15 min bodyweight routines (HIIT, yoga, core, mobility) with instructions and streak tracking. Works at home, office, or travel. | |
| Daily History Today in history — 3–5 major events on this date with context and lasting impact. Bilingual EN/CN timeline card. Daily morning push. | |
| Daily Idiom Daily Chinese idiom (成语) — origin story, meaning, usage examples, and memory tip. Build Chinese vocabulary and cultural knowledge one 成语 per day. | |
| Daily Mindful Daily mindfulness in 3–5 minutes — morning breathing exercise, guided meditation, and evening reflection prompt. Practical calm and stress relief for busy pe... | |
| Daily Movie Daily movie & TV recommendation — curated by genre, mood, or theme. One great watch per day with synopsis, streaming platform, and audience ratings. | |
| Daily Quote Daily curated quote from philosophers, leaders, and thinkers — with author context and why it resonates today. Bilingual EN/CN shareable visual card. | |
| Daily Recipe Daily recipe recommendation — Chinese, Western, and fusion cuisines on rotation. Full ingredients, step-by-step instructions, 30–60 min home-cook meals. | |
| Daily Reflect Daily journaling prompts for meaningful reflection — morning intention-setting and evening review. Build a consistent self-reflection habit one prompt at a t... | |
| Daily Sleep Sleep better tonight — personalized wind-down routine, breathing exercises, bedtime stories, and sleep hygiene tips. Daily evening push for better rest. | |
| Daily Vocab One advanced English word every day — IPA pronunciation, etymology, 3 example sentences, and quiz mode. GRE / SAT / IELTS / C2 vocabulary level. | |
| Dailyfinance Daily financial news briefing — stock markets, crypto, macro economy, Fed/PBOC policy, earnings reports. Bilingual EN/CN visual dashboard. Morning push + eve... |
41,351–41,400 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.