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 |
|---|---|
| Ticktick Manage TickTick tasks and projects | |
| PARA Second Brain Organize your agent's knowledge using PARA (Projects, Areas, Resources, Archive) — then make it ALL searchable. The symlink trick enables full semantic search across your entire knowledge base, not just MEMORY.md. Includes session transcrip | |
| Proactive Agent Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞 | |
| Logseq Bridge Pure file-based interaction with a local Logseq graph. Read, write, search, and manage Logseq journals and pages via direct `.md` file operations. No plugins... | |
| Skill Publisher Prepare and publish an OpenClaw AgentSkill to ClawHub. Use when a skill directory is ready and needs to be published, or when upgrading an already-published... | |
| WSL Proxy WSL2 HTTP proxy setup via Windows host. Automatically detects proxy running on Windows (Clash/V2Ray/SS/Surge etc.) and configures WSL2 environment variables.... | |
| Access global ocean tides model. Functions include tide height at a given date/time/location, tide extrema, and grid weather data. Access global ocean tides model. Functions include tide height at a given date/time/location, tide extrema, and grid weather data. | |
| Aliyun Skills Manage Alibaba Cloud resources using the Aliyun CLI tool. Use this skill whenever the user wants to manage any Alibaba Cloud resource via the aliyun CLI, inc... | |
| creem-audit-kit Generate a Creem audit-ready compliance pack with legal policies, a preflight checklist, and site surface punchlists for MoR onboarding or review. | |
| Hamibot This skill should be used when working on the Hamibot CLI project — an open-source Node.js command-line tool for authorized remote Android automation. Device... | |
| Edge Tts Zh 中文语音合成（Text-to-Speech），使用Microsoft Edge TTS引擎，无需API key，完全免费。内置中文最佳声音列表（男声/女声/不同风格）。适用于：(1)将文字转为语音消息 (2)新闻/文章朗读 (3)语音通知和提醒 (4)播客/视频配音。支持语速/音调调节和字幕生成。 | |
| FlexArm Robot Arm: Physical Tap, Swipe, OCR for Real Phones Give AI agents physical eyes and a hand to operate any smartphone. Built-in 50+ atomic actions (click, swipe, OCR, screenshot). AI can call them directly. Also supports YAML scripts. Script Store: once one AI learns an app, all AI agents in | |
| X Alpha Scout Scan crypto and NFT sentiment on X/Twitter for daily alpha reports or token/NFT/project on-demand analyses with sentiment, trends, and red flags. | |
| AgentFiles Use this skill when you need to publish, fetch, search, list, share, or watch AgentFiles artifacts from Codex, Claude Code, OpenClaw, or other agent runtimes... | |
| OpenBotAuth Get a cryptographic identity for your AI agent. Generate Ed25519 keys, sign your work, prove who you are — across any platform. | |
| Cricket Stats Skill Cricket statistics lookup. TRIGGER when user asks about cricket stats, scores, records, player averages, match results, rankings, or any cricket data (e.g. '... | |
| project-keeper Enhances your agent's ability at keeping structured records of user projects including status, goals, architecture, and key development plans in dedicated workspace directories to minimize wasted context and time explaining | |
| 飞猪联动 用高德 995 万 POI 数据库解析任意地名（商圈、地铁站、网红餐厅、小区……），再调飞猪实时房价和预订链接。突破飞猪 --poi-name 只认头部景区的限制，任意地点均可锚定。 | |
| 小安智能健身 查询、介绍并预约小安智能健身线下一对一私教训练服务 | |
| 飞书云盘助手 基于飞书官方 API 的云盘管理技能，支持文件列表查询、上传、下载、文件夹创建、权限管理、文件搜索、统计信息、快捷方式、复制移动等完整功能。参考 feishu-drive 技能开发，修复了原技能中的 API 调用错误，并新增了自动化权限管理功能。 | |
| 小说创作 辅助规划和生成长篇小说，支持人物世界设定、大纲管理、分章创作和写作风格锁定。 | |
| 微信创作 自动将 Markdown 文章转为适配微信公众号格式的 HTML，并批量发布至公众号草稿箱，支持封面图生成与专题管理。 | |
| APPM: Atlas-Parallel Project Management Manages AI Agent project memories by creating and updating .openclaw/MISSION.md and SNAPSHOT.md for parallel project progress tracking. | |
| K线超短线选股 A 股短线（日/尾盘）选股与买点核查清单技能。当用户想用技术分析纪律筛选 A 股短线标的、评估某只股票是否符合「96 原则（九不买+六不卖）/ 下午 2:30 选股法（八层筛选）/ 底部 K 线形态」、或为自选股做纪律化买前/持有核查时使用。覆盖 9 类不买、6 类不卖、12 种底部形态、八层 2:30 筛选、上升趋势研判与心态纪律，并能调用腾讯财经 API 自动拉取涨跌幅/量比/换手率/流通市值等客观指标做初筛，连接 Wind 金融数据 MCP 时还可把九不买 | |
| automation browser Control Browser's kernel for web automation. Supports web navigation, element interaction, page scrolling, file/video downloading, and content extraction. | |
| my-browser-bot Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking... | |
| God-tier Webnovel Skill 专为男频玄幻小说设计的创作Skill。核心机制为‘血量越低伤害越高’的极限反杀流，结合传统修仙境界，擅长生成刀刀见血、极致打脸的爽文桥段。 | |
| weekly-report 把"只讲事的流水账周报"升级成"领导 30 秒读懂全局"的结构化周报。用户提供碎碎念式的本周工作流水账（或直接给出本周做了什么），此 skill 通过四步流程（建项目库 → 拆事归位 → 追问补缺 → 六要素组装）输出可直接发出的领导版周报。适用于：写周报/月报/工作汇报、周会材料、向上管理。关键设计：AI 只补缺的、不编没的，风险/下周计划/思考三样缺了必须追问用户，绝不编造。 | |
| ljh 打品工具箱主入口。三模式：任务前路由（你的问题该用哪个工具）+ 任务后导航（刚做完一个环节，下一步该干什么）+ 陪跑（带你从头走完整条打品链路）。 触发方式：/ljh、电商老家伙、「打品」、「帮我看看这个品」、「不知道下一步该干什么」、「带我从头打这个品」 Main entry point for the product-launch toolkit. Three modes: pre-task routing, post-task navigation, and a gui | |
| ljh-changjing 场景机会地图。带你把竞品素材拆成能算账的表，用体量乘效率的四象限定性，最后画出自己该重投哪个场景的机会地图。 触发方式：/ljh-changjing、「帮我拆场景」「场景机会地图怎么画」「这几个竞品该怎么对比场景」 Turn competitor content into a scenario opportunity map with a quantified quadrant model. Trigger: /ljh-changjing, "help me map out | |
| ljh-daren 达人选号诊断器，用六维决策表初筛达人账号，跑反作弊三查，给出可谈/压价谈/放弃的合作建议。 触发方式：/ljh-daren、「帮我看看这个达人能不能投」「这个账号数据是不是刷的」「这个号值不值得投」「达人报价合不合理」「怎么判断这个号是不是真流量」 Influencer account diagnosis tool. Screens accounts against a six-dimension scorecard and runs a three-part anti-fr | |
| ljh-dingwei 新品定位一页纸生成器。喂产品资料，产出六栏定位一页纸：定位一句话、价值四象限、必要项与差异项、竞争差异、翻译成内容、双重校验。 触发方式：/ljh-dingwei、「帮我写一份产品定位」「这个新品怎么定位」「填一下定位一页纸」「这个品的心智句怎么收」 New-product positioning one-pager generator. Feed in product materials and get a filled six-column positioning she | |
| ljh-duiqi 品·人群·内容对齐表生成器。喂产品资料，产出五块对齐表，核心是把产品语言翻译成消费者人话和画面的四列表。 触发方式：/ljh-duiqi、「帮我做一张品人群内容对齐表」「这个新品的卖点怎么翻译成人话」「帮编导团队对齐一下这个品」 Product-audience-content alignment table generator. Feed in product info, output a five-block alignment table with a selling- | |
| ljh-jiaoben 带货脚本评审器。用户贴脚本全文，按七步说服链逐段核对，指出缺哪步、哪句没配画面、表达形式和内核哪层出问题。 触发方式：/ljh-jiaoben、「帮我评审一下这个带货脚本」「这个脚本为什么转化不好」「看看我这个口播稿哪里有问题」 Selling script reviewer. Paste the full script, get a step-by-step check against the seven-step persuasion chain, with missin | |
| ljh-koc KOC 验证方案设计与验证报告生成。还没铺就帮你设计验证方案，跑完了就帮你判定结果并出报告。 触发方式：/ljh-koc、「帮我设计一个 KOC 验证方案」「KOC 数据跑完了帮我出个报告」「这个卖点该怎么验」 KOC validation plan design and validation report generation. Design a plan before launch, judge results and write a report after data | |
| ljh-liangye 见主播两页材料生成器，把产品资料压缩成一页记得住、一页开得了口的标准材料，附当面塑品六步提词。 触发方式：/ljh-liangye、「帮我做一份见主播的材料」「怎么跟主播讲这个产品」「主播资料怎么准备」「当面怎么塑品」「产品资料太长了帮我提炼」 Generates the two-page pitch material for meeting influencers or livestream hosts: one page to be remembered, one pag | |
| ljh-maidian 卖点体检器。丢一句或一组卖点文案进来，跑六道检验，判断这是独一份卖点还是随时会被抄的公共卖点，给出通过/打回结论和改法。 触发方式：/ljh-maidian、「帮我看看这个卖点行不行」「这句卖点站得住吗」「体检一下我的卖点」「这个卖点会不会被主播怼回来」 Selling-point health check. Feed in one or a batch of selling-point copy, run six checks, and get a pass/reject | |
| ljh-qianchuan 千川掉量诊断器。用户描述掉量症状，按决策树一步步走，两分钟给出第一动作。 触发方式：/ljh-qianchuan、「千川消耗掉了」「投放量突然没了」「ROI 掉了怎么办」 Douyin ad (Qianchuan) traffic-drop diagnostic tool. Walks through a decision tree one node at a time to find the first action within two minutes. Trigger: | |
| LJH 商详页说服地图 商详页说服地图。把定位、卖点、场景、人群和验证证据编排成商品详情页策略、逐屏结构与内容文档，可选输出低保真 HTML。 触发方式：/ljh-shangxiang、「商详页怎么排」「商品详情页怎么讲」「详情页信息架构」「货架转化怎么接」「帮我排一张商详页地图」 Product-detail persuasion map. Turn positioning, selling points, scenarios, audience insights, and validation | |
| ljh-suanzhang 单元经济算账器。三个动作：月度总账（判断渠道砍不砍）、盈亏平衡 ROI（1÷毛利率）、LTV 实算（敢出多高获客价）。 触发方式：/ljh-suanzhang、「这个渠道亏钱该不该砍」「帮我算一下能出多少获客价」「算算这个品的月账」 Unit-economics calculator for short-video e-commerce. Three actions: monthly full-account check, breakeven ROI (1÷gross mar | |
| ljh-xhs 小红书图文爆款拆解器。拿到一条小红书图文样本，先判断样本等级（能不能拆），再按用户链路拆封面、图文承接、爆款因子、成立机制、变量分层，最后给出受控变体迁移方案。 触发方式：/ljh-xhs、「帮我拆一条小红书爆款」「这条图文笔记为什么能卖」「小红书图文怎么复刻」「这张封面为什么点击高」 Xiaohongshu (RED) viral image-text post decomposer. Given a sample post, judge whether it is eve | |
| ljh-xuanpin 选品判断器。你报一个候选品，我按五步逐项核对，给出值不值得打的结论。 触发方式：/ljh-xuanpin、「这个品值不值得打」「帮我判断一下这个候选品」「选品怎么判断」 Product selection judgment. Give a candidate product, get a five-step go/no-go verdict. Trigger: /ljh-xuanpin, "should I pursue this product", "judge this | |
| ljh-yinzi 内容因子工具。三种模式：拆解（把一条爆款素材拆到因子级）、排序（给候选专攻课题按 EV 打分排优先级并跑完整 SOP）、建库（指导搭建因子库三张表）。 触发方式：/ljh-yinzi、「帮我拆一条爆款」「这几个方向该先做哪个」「怎么搭因子库」 Content-factor toolkit for short-video e-commerce. Three modes: decompose a viral video into factors, rank candidate f | |
| 关键指标波动诊断专家 沿指标树定位内容电商波动根因，并输出首个可验证的运营动作。 | |
| Loop Skill 面向任意 coding-agent CLI 的计划驱动、无人值守多 agent loop 编排。当用户一句话触发推进多个仓库、 需要主控通读仓库生成推进计划、再自动派发 CLI、会话可恢复、后台常驻 loop 或打开看板时使用。 触发语：「用 loop-skill 推进某目录下的项目」「后台常驻 loop」「自动... | |
| 中国专利.Skill 中国专利技能：挖掘专利点与编写交底书（发明/实用/外观），把已有交底改写成申请文件四件套，也可按材料交底申请一起做，按著录字段检索公布公告，通俗解读专利，对照审查口径出政策简报，辅助审查答复。| China patents skill: mine patent points and draft disclosures, rewrite an existing disclosure into application documents, or chain disclosure- | |
| 知乎抓取.SKILL 知乎收藏夹与文章内容抓取：API/Playwright 多级降级、Cookie 持久化与保活、批量正文与图片、断点续传、可选写入 Obsidian。| Zhihu collection scraping, batch article fetch, Obsidian export. | |
| ceo-indotrading Agent CEO IndoTrading untuk Handy. Monitor KPI bisnis (GMV, orders, revenue, active users, growth), review laporan keuangan, dan analisa operasional. Berikan... | |
| Handy01 Agent Browser Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection | |
| Handy01 Multi Search Engine Multi search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra... |
34,501–34,550 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.