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 |
|---|---|
| Movie & News Inquiry - 电影影讯查询 查上映影片、影院排片、影片详情与城市影院列表等。当用户说:最近有什么好看的电影?附近哪家影院放映《xxx》?或类似电影影讯问题时,使用本技能。 | |
| News - 热门新闻 按频道获取头条、财经、体育、娱乐等新闻列表,可查频道列表。当用户说:今天财经头条有什么?体育新闻摘要,或类似新闻聚合问题时,使用本技能。 | |
| QR Code Generation And Recognition - 二维码生成识别 按文本生成带模板样式的二维码(base64),或识别二维码内容及模板列表。当用户说:把这段链接生成二维码、识别图里二维码内容,或类似二维码 API 问题时,使用本技能。 | |
| Recipe - 菜谱大全 按关键词或分类检索菜谱,可查分类与菜谱详情。当用户说:糖醋排骨怎么做?来个家常豆腐菜谱,或类似做菜问题时,使用本技能。 | |
| 股票查询 - Stock Inquiry 按股票代码查当日行情与详情(分钟级趋势),按分类拉取股票列表,查询交易日历及财务报表。当用户说:今天的宁德时代股票走势怎样?贵州茅台现在多少钱?今天 A 股开市吗?宁德时代的财报怎样?或类似个股行情、财务问题时,使用本技能。 | |
| Stock Monitor - 股票监控 对持仓做一次性检查:盈亏、涨跌、缺口、均线与 RSI 等(无常驻进程,可配阈值与状态文件)。当用户说:帮我检查一下持仓要不要告警?我的 ETF 今天触发止损了吗?或类似持仓体检问题时,使用本技能。 | |
| Travel Search Flight Train Scenery - 旅行搜索 航班 火车 景点 聚合航班列表、景点信息,火车段可走 train 能力。当用户说:查一下上海到东京的航班、杭州有什么景点推荐、顺带帮我看看火车票,或类似出行规划问题时,使用本技能。 | |
| 全国天气预报 - Weather Forecast - 极速数据 查询实时天气、7 天预报、24 小时逐时、空气质量与生活指数,可查城市列表。当用户说:上海今天天气怎样?北京明天会下雨吗?带伞吗?或类似天气预报问题时,使用本技能。 | |
| Wechat Article Search - 微信公众号文章搜索 按关键词搜索公众号文章,返回标题、摘要、时间、账号与链接等。当用户说:搜一下微信公众号里关于 AI 的文章、找几篇讲理财的推文,或类似公众号文章检索时,使用本技能。 | |
| 极速数据API Agent 用自然语言搜索并调用极速数据 500+ 接口(search → execute),含执行统计。当用户说:帮我查一下这个手机号归属地、用 Agent 调极速数据、今天 API 调用花了多少钱,或不想记具体接口路径时,使用本技能。 | |
| Convert Markdown To HTML And PDF - Markdown和HTML、PDF互转 Markdown 与 HTML 互转,并支持 Markdown 转 PDF。当用户说:把这篇 MD 转成 HTML、导出 PDF,或类似文档格式转换时,使用本技能。 | |
| Mobile Phone Number Undeliverable or Empty Detection - 手机空号检测 批量检测手机号是否空号、实号、沉默号或风险号。当用户说:帮我测一下这几个号码是不是空号?批量验一下实号,或类似号码状态检测时,使用本技能。 | |
| News Brief - 新闻简报 中文新闻门户列表抓取,可输出 Markdown 简报或 JSON/RSS,无需新闻类 API Key。当用户说:给我一份今日要闻链接简报、抓一下门户新闻标题,或类似中文新闻聚合时,使用本技能。 | |
| Today's Oil Price - 今日油价 查询各省市汽柴油参考价,可查省市列表。当用户说:今天北京 92 号油价多少?山东柴油什么价?或类似油价问题时,使用本技能。 | |
| Auto Parts OE Inquiry - 汽车配件OE信息查询 查配件品牌、OE 号模糊搜、适用车型与替换件等。当用户说:这个原厂零件号对应什么件?有没有替换件?或类似汽车 OE 配件问题时,使用本技能。 | |
| Local QR Code Generation And Recognition Not Require An API_KEY - 本地二维码生成与识别 本地将文本/URL 编成 PNG 二维码,或从图片识别二维码,可与远程 qrcode 技能搭配。当用户说:本地生成二维码图片、离线扫图读码,或类似本地二维码问题时,使用本技能。 | |
| 手机号码归属地查询 - Mobile Phone Number Location Query 根据手机号查归属省市、运营商与卡类型。当用户说:138xxxx 是哪里的号?这个号码联通还是移动?或类似手机号归属地问题时,使用本技能。 | |
| Silver Price Inquiry - 白银价格查询 查询国内白银期货/现货相关及伦敦银等参考行情。当用户说:白银现在什么价?伦敦银涨跌多少?或类似白银价格问题时,使用本技能。 | |
| 股票历史行情查询 - Stock Historical Data Query - 极速数据 按代码与时间范围查历史日线,或查列表与详情,便于 K 线与走势分析。当用户说:宁德时代最近一年 K 线数据?这只股票过去一年最高最低价?或类似历史行情问题时,使用本技能。 | |
| Shanghai Stock Exchange Composite Index - 上证股票指数 查询上证、深证、创业板、沪深300、科创50 等主要指数分钟级行情。当用户说:上证指数现在多少点?创业板指涨跌幅?或类似大盘指数问题时,使用本技能。 | |
| Today in History - 历史上的今天 按月日查询历史上同日大事、诞辰与逝世等。当用户说:历史上的今天发生了什么?3 月 15 日有什么大事?或类似历史纪事问题时,使用本技能。 | |
| Trademark Information Inquiry - 商标信息查询 商标关键词搜索与详情查询(申请人、分类、公告等)。当用户说:查一下「某某」商标有没有被注册?这个商标注册人是谁?或类似商标问题时,使用本技能。 | |
| 火车查询 - Train Ticket Inquiry - 极速数据 支持站站、车次、余票查询,返回时刻、票价与余票等。当用户说:北京到上海今天还有高铁票吗?帮我查一下 G1 次列车经停站,或类似火车票、余票问题时,使用本技能。 | |
| TV Program Preview - 电视节目预告 按频道与日期查电视节目单,可查频道列表。当用户说:央视一套今晚有什么节目?湖南卫视节目表,或类似电视节目问题时,使用本技能。 | |
| Vehicle License Plate Number Restriction - 车辆尾号限行 查询城市限行规则与尾号,可查支持城市列表。当用户说:北京明天限行尾号是几?成都限行区域怎么算?或类似限行问题时,使用本技能。 | |
| VIN (Vehicle Identification Number) Query - VIN车辆识别代码查询 用 17 位 VIN 查品牌车型年款等,并可按车型查机油、变速箱等扩展信息。当用户说:这个车架号是什么车?查一下 VIN 对应的排量,或类似 VIN 解析时,使用本技能。 | |
| VIN Recognition OCR - VIN识别 对车架号/VIN 图片做识别并返回 VIN 及品牌厂家等信息。当用户说:拍了一张车架号照片帮我识别、从图里读出 VIN,或类似 VIN 图片识别时,使用本技能。 | |
| Historical Weather - 历史天气 按城市与日期查询历史天气(温湿度、风、气压、AQI 等)。当用户说:去年今天北京多少度?查一下 2023 年 7 月上海历史天气,或类似历史气温问题时,使用本技能。 | |
| Wechat MP Article Stats Comments Suite - 微信公众号管理套件 公众号运营:发文到草稿、样式与封面、评论与用户管理、数据统计等。当用户说:把这篇 Markdown 发到公众号草稿、看下昨天阅读量统计,或类似公众号后台操作时,使用本技能。 | |
| Windows Shell Encoding Doctor - Windows Shell编码修复工具 诊断修复 Windows 下 PowerShell/cmd/Git Bash 的乱码、引号转义、路径空格与 CRLF 等问题。当用户说:PowerShell 里跑 bash 命令报错、中文乱码怎么修、JSON 怎么安全传给命令行,或类似 Windows 终端编码问题时,使用本技能。 | |
| free-feishu-voice Send customized voice messages to Feishu chats by generating and uploading TTS audio using configurable credentials and options. | |
| Mongo Db Client Tool Interact with a MongoDB database for persistent document storage. Supports full CRUD operations (find, insert, update, delete), aggregation pipelines, collec... | |
| qwen3-tts-local-inference Generate speech from text using Qwen3-TTS via direct Python inference — no server required. Use when: (1) converting text to speech / synthesising audio, (2)... | |
| 投资报告生成器 生成A股个股深度投资报告。当用户要求撰写股票/公司投资报告、个股分析、估值分析时使用。支持批量生成多份报告。报告包含:公司概况、详细业务构成、财务分析与预测、分部估值(SOTP)、投资逻辑、交易计划、多维度深度分析(政策面/基本面/技术面/情绪面/消息面/资金面)、风险提示、总结。用户只需提供公司名称列表即可触发。 | |
| Forum Scout Automatically scans Moltbook forum every 30 minutes, filters posts for technical discussions, logs actions, audits tool usage, and generates structured hotsp... | |
| Memory Pruner Manages agent memory by auto-pruning old or low-relevance entries, compressing duplicates, and reporting storage costs with safe defaults. | |
| Receipt Logger Create tamper-proof, append-only, cryptographically signed logs of agent actions with exportable, verifiable JSON receipts. | |
| Excel 智能记账与对账 通过聊天维护 Excel 账本,核查上传修改、信用卡账单并分析消费 | |
| Self Audit Track, analyze, and score your tool calls to identify unnecessary usage, detect patterns, and get recommendations for efficiency improvements. | |
| 你的私人CPA 你的私人CPA——中国会计+税法+审计+会计信息系统综合知识库。覆盖初级/中级/高级会计实务、18个税种、审计理论与实务、会计信息系统四大模块。 | |
| Clawhub Top Get ClawHub popular skills rankings and latest releases. Use for: - View top 20 most popular skills (by downloads) - View top 20 newly released skills - View... | |
| baiyin-cover-sing-skill 当用户希望通过百音开放平台创建 AI 歌手翻唱任务、查询翻唱任务状态,或根据已有 taskId 返回最终翻唱音频结果时使用。 | |
| baiyin-cover-train-skill 当用户希望通过百音开放平台训练 AI 歌手模型、查询训练任务状态,或根据已有 taskId 返回最终训练结果时使用。 | |
| baiyin-digital-human-lipsync 当用户希望通过百音开放平台创建 AI 数字人任务、查询任务状态,或根据已有 taskId 获取最终视频结果时使用。支持对口型、肢体驱动等多种数字人模型。 | |
| baiyin-image-generate-skill 支持通过百音开放平台选择模型,按参数逐步配置,生成文字或参考图辅助的图片,并查询任务状态和结果链接。 | |
| baiyin-music-generate 使用百音开放平台创建 AI 音乐任务,支持普通生成、参考音频生成、音乐改编,并在同一 skill 内继续查询任务状态、结果链接和余额。用于用户要生成歌曲、参考音频做歌、改编上一首歌、查询音乐任务进度或下载结果时。 | |
| baiyin-skills-upgrade 检查并更新本地 baiyin skills 到 SkillHub 中的最新版本。 用于 `skill/` 目录下的百音技能在执行前做远程版本检查、按需升级、 回滚失败更新,并在升级完成后继续原始技能任务。 | |
| baiyin-track-separation-skill 音轨分离能力,支持人声伴奏分离。Use when: (1) 用户需要将音频分离为人声和伴奏,(2) 用户需要对音频进行专业级别的音轨分离处理。 | |
| baiyin-video-skill 通过百音开放平台生成 AI 视频。当用户想生成视频、图片转视频、查询视频任务状态时使用,即使未明确说"百音"但上下文涉及视频生成能力也应触发。 | |
| baiyin-voice-generate-skill 使用百音开放平台创建 AI 语音任务,支持文本转语音、音色克隆,并在同一 skill 内继续查询任务状态和结果链接。用于用户要生成语音、克隆音色、查询语音任务进度或下载结果时。 |
42,051–42,100 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.