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 |
|---|---|
| Solana Investor 顶层投资助手编排器 — 协调 portfolio、dca、alerts、market 技能,处理复杂的多步骤投资请求。当用户的请求涉及多个操作或需要跨技能协调时触发。 | |
| Solana Market 查询 Solana 生态代币实时价格和市场概览。当用户想知道代币价格、行情、市场状况时触发。 | |
| Solana Portfolio 管理 Solana 投资组合 — 追踪多钱包余额、代币分布和资产估值。当用户想查看持仓、添加钱包或了解资产状况时触发。 | |
| wordcloud-skill this skill is for generate a word cloud from text/file/directory and save it to a picture, you can use it visualize the text | |
| alibabacloud-iqs-weather-query 7-day weather forecast query powered by Alibaba Cloud IQS web search and page reading. Triggers: "weather forecast", "7-day weather", "weekly weather", "weat... | |
| GEO内容违禁词检测与智能替换 GEO/SEO内容违禁词检测与智能替换。当用户需要检测文章中的违禁词、检查GEO/SEO内容合规性、或要求替换违禁词时使用此技能。支持检测广告法违禁词(绝对化用语)、夸大宣传词、违法内容词、误导性词汇等,并根据上下文智能生成保留原意的替换方案。触发词:检测违禁词、检查违禁词、违禁词替换、违禁词修改、违规词、GEO... | |
| To B 销售大师免费陪练/Free coaching from top B sales experts To B 销售大师(免费预览版)——从 8,772 条真实企业跟单记录提炼的中英双语通用 Prompt,任何 LLM 都能用的 To B 销售 playbook | |
| To B 销售大师 - 通用 Prompt To B 销售大师(免费版)—从 8,772 条真实企业跟单记录提炼的中英双语通用 Prompt,任何 LLM 都能用的 To B 销售陪练笔记。
To B Sales Master (Free Version) — A bilingual (Chinese and English) prompt extracted from 8,772 real-world business follow-up records, a To B sales training note tha | |
| qshell-copilot Manage files on Qiniu Cloud Storage (Kodo) via the qshell CLI tool: upload, download, list, delete, copy, move files, CDN refresh/prefetch, and bucket manage... | |
| openclaw-all-backup 完整备份 OpenClaw 配置目录 (.openclaw) 到同名带时间戳的目录,包括所有文件和隐藏文件。当用户需要备份 OpenClaw 配置、数据或创建配置快照时使用。 | |
| 发票查验 当用户需要查验发票真伪时使用。触发词包括"查发票""发票查验""验证发票""发票真伪"。 | |
| 学习日志系统 牢大AI学习日志系统。自动记录、分类、沉淀AI在任务执行过程中的学习心得、踩坑记录和经验教训。当AI完成重要任务、遇到错误失败、发现新工具或方法、做出重要决策时,应该将关键信息记录到学习日志。触发场景:任务完成后的复盘、错误/失败后的总结、新工具/新技能的发现和评估、重要配置决策的记录。 | |
| 腾讯云LKE智能体对话 腾讯云智能体开发平台 HTTP SSE 对话接口技能。用于调用腾讯云智能体对话接口,支持流式响应处理、事件解析(reply/token_stat/reference/error/thought)。在需要与腾讯云LKE智能体进行HTTP SSE对话时使用,包括发送消息、处理流式响应、解析各类事件。 | |
| Media Generation Generate images, edit existing images, create short videos, run inpainting/outpainting and object-focused edits, use reference images as provider inputs, bat... | |
| 聊天助手 聊天关系顾问。当用户导入聊天记录、描述与某人的关系背景、询问如何回复消息、想获得聊天建议时自动激活。支持按好友备注名管理多人独立上下文。 | |
| api-sequence-diagram 根据指定的Java接口(Controller方法/API路径)分析完整调用链路,生成Mermaid时序图,标注关键判断节点、异常处理分支和业务逻辑。当用户要求分析接口调用链路、生成时序图、分析接口流程、查看接口调用关系时使用。 | |
| 档案文件 定时获取档案行业最新情报、政策法规、技术动态和行业资讯。当用户需要获取档案行业新闻、政策更新、技术趋势或设置定时情报收集任务时使用此技能。 | |
| skill-to-mermaid Converts data and diagrams into Mermaid syntax for easy visualization and flowchart creation. | |
| 中文办公自动化 中文办公自动化 - 专为中文用户设计的办公自动化技能套件。集成中文文档处理、拼音转换、节假日判断、农历支持等功能。 | |
| 飞书增强套件 飞书增强套件 - 深度集成飞书文档、多维表格、消息和日历的自动化操作。适用于需要高效办公自动化的中文用户。 | |
| 智能报告生成器 智能报告生成器 - 自动分析数据并生成专业报告。支持多种报告类型(日报、周报、月报、分析报告),可输出到飞书文档或本地文件。 | |
| local-coding-orchestrator Use OpenClaw as a supervisor-driven orchestration scaffold for local coding CLIs such as Codex, Claude Code, and OpenCode. Supports task records, lifecycle t... | |
| openc3-flow Get all CI/CD flows from Open-C3 platform. Returns the complete list of flows in the system. | |
| travel-customizer 智能旅游定制助手,收集用户需求后自动提交飞书多维表,助力个性化行程规划与跟进。 | |
| Travel In China 基于飞书多维表格的智能旅游行程定制助手,可生成、查询和管理旅行计划。 | |
| Travel Customizer 基于飞书多维表格的智能旅游行程定制助手,可生成、查询和管理旅行计划。 | |
| 电商竞品价格监控系统 电商竞品价格监控系统 — 自动监控京东/淘宝/亚马逊等平台竞品价格变动、促销活动、库存变化。 定时抓取指定商品页面,比对历史数据,价格异常时立即告警。适合电商卖家、代运营、品牌方。 零代码配置,改个产品链接就能用。 | |
| Excel 数据自动清洗引擎 Pro Excel 数据自动清洗引擎 — 自动去重、格式统一、缺失值处理、智能分类、交叉验证。 拖进去一份脏数据,出来一份干净能用的报表。支持 CSV/XLSX/JSON 多格式。 适合财务、运营、数据分析师、电商卖家。 | |
| 小红书图文自动发布引擎 Pro 小红书图文自动发布引擎 — 定时生成内容、自动排版、定时发布到小红书平台。 支持热点追踪、AI文案生成、图文混排、定时发送。适合博主、自媒体、品牌方。 帮你省掉每天 2 小时的手工运营时间。 | |
| "AI 产品经理教练。通过引导式对话帮助 PM 完成 AI 产品设计:从痛点分析到 PRD 输出。不替代 PM 决策,而是引导 PM 思考,在关键节点让 PM 做出选择。触发词:AI 产品、产品设计、PRD、能力边界、置信度、幻觉。" metadata: AI 产品经理教练。通过引导式对话帮助 PM 完成 AI 产品设计:从痛点分析到 PRD 输出。不替代 PM 决策,而是引导 PM 思考,在关键节点让 PM 做出选择。触发词:AI 产品、产品设计、PRD、能力边界、置信度、幻觉。 | |
| 长文转短视频分镜 当用户有一篇已写好的长文(公众号推文、博客、测评稿、教程、报告、小红书长帖、技术文档),想做成短视频时触发。产出带时间轴的镜头清单,每个镜头包含画面描述、中文提示词、英文提示词、配音文案、屏幕字幕五要素,可直接投喂可灵、即梦、Sora、Veo、Runway 等文生视频模型。内置九项硬伤体检,自动检查配音字数是否超出时长、画面是否误让模型渲染中文、提示词是否遗漏统一风格前缀、单镜头是否过长。自带经验沉淀机制,每次完成的教训会累积下来变为新检查项。适用于抖音、视频号、小红书、B站 | |
| 智能体云沙箱 / 远程桌面 智能体云沙箱 / 远程桌面 / 浏览器自动化环境。管理与调度 UCloud 星图 AstraFlow 智能体桌面沙箱(Ubuntu/Chrome GUI)以及按需 RDP 桥接 Windows Server 云主机。提供全球多地域(美西 us-ca、乌兰察布 cn-wlcb、上海 cn-sh)秒级桌面启动、Web noVNC 浏览器免客户端直连、网络连通探测与防休眠守护。涵盖桌面沙箱全生命周期管理,并提供可选的 Windows Server 2022 与国际 EIP 对接流水 | |
| 输入关键词,自动扫描全网用户痛点,生成PRD并输出OpenClaw标准任务JSON。 Search web for user pain points and output a PRD JSON. | |
| 竞品前哨 竞品前哨(竞品分析/竞品监控/竞争对手分析/市场情报/行业监测/对标)。每天自动扫描多个竞品的最新动态,按「可信度 P0–P3 × 影响度 I1–I3」双轴评级、交叉验证、区分发布日与采集日,输出带可溯源链接与行动建议的结构化情报日报(Markdown / 表格 / 竞品×维度矩阵 / HTML 在线页),并可定时自动跑、推送到邮箱与飞书/钉钉。Use when 用户要「追踪/监控竞品动态」「生成竞品情报日报/周报」「competitive intelligence / co | |
| 大模型横评对比 / 模型选型 大模型横评对比 / 跨模型对比测试。当用户想比较多个大模型的真实表现时使用——比如「这几个模型哪个好」「帮我横评一下 DeepSeek 和 Qwen」「同一段 prompt 在多个模型上跑一遍看差异」「测一下各模型的延迟和成本」「选型时给点实测数据」。会在多个模型上真实发起调用,收集延迟、token 用量和成本,产出对比表和结论。触发词:模型对比、大模型横评、模型选型、模型跑分、prompt 测试、多模型评测、model comparison。 | |
| 高品质短视频制作 · 声画同步工业级流水线 高品质短视频工业级制作工作流,适用于一切旁白驱动的短视频:产品宣传片(任意品类,不限科技)、知识讲解、教程演示、品牌故事、活动回顾、个人 IP 口播。以声音时钟逆推为核心,用 TTS 实际波形反推画面时长,消除抢拍与空转;含动量连续性视觉规范、确定性帧渲染、侧链闪避混音、BS.1770-4 响度母带、可机械执行的质量门禁。当需要制作宣传片、讲解视频、教程视频、发布会特性视频、需要声画精确对齐的短视频时使用。触发词包括「做宣传片」「产品视频」「讲解视频」「教程视频」「短视频制作 | |
| 公众号排版 / 小红书封面 公众号排版 / 小红书封面 / 内容一键发布。全链路内容发布工具(Inkwell)。Markdown 转公众号 HTML、 生成杂志封面、生成小红书社交卡片、发布到剪贴板或公众号草稿箱。一条命令从选题到发布,不只是排版。 触发词:公众号排版、公众号发布、小红书封面、小红书卡片、Markdown 转 HTML、内容发布、文章配图、封面生成。 | |
| "运营-产品协同加速套件。解决运营与产品之间的信息不对称、需求扯皮、效果归因等痛点。用于:(1) 运营需求翻译为产品语言;(2) 效果归因框架生成;(3) 优先级智能计算;(4) 验收标准自动生成;(5) 数据口径对齐;(6) 协同文档生成。触发词:运营需求、产品协同、效果归因、需求扯皮、数据口径、验收标准、优先级评估。" 运营-产品协同加速套件。解决运营与产品之间的信息不对称、需求扯皮、效果归因等痛点。用于:(1) 运营需求翻译为产品语言;(2) 效果归因框架生成;(3) 优先级智能计算;(4) 验收标准自动生成;(5) 数据口径对齐;(6) 协同文档生成。触发词:运营需求、产品协同、效果归因、需求扯皮、数据口径、验收标准、优先级评估。 | |
| 为 Vibe coding 应用提供专业级站点设计的终极解决方案 像素级完美设计系统 - 为 Vibe coding 应用提供专业级站点设计。支持中英文双语站点,58 个顶级产品设计模板,9 部分完整设计规范,AI 可读 Markdown 格式,开箱即用无需 Figma。 | |
| 把播客变成可读文章。支持输入音频文字稿、节目链接或摘要笔记,自动提炼核心观点、精选金句,生成适配微信公众号、知乎、企业内刊等多平台的图文内容。提供深度解析、精华摘要、对话体重构、社交媒体切片四种风格,开箱即用。 播客文章生成器。将播客内容(音频文字稿、节目链接、摘要笔记)转化为结构清晰、适合发布的图文文章。 支持多种输出风格(深度解析、精华摘要、对话体重构、社交媒体切片)和多种输出格式(Markdown、微信公众号、知乎、企业内刊)。 触发词:播客文章、播客转文章、podcast to article、podcast a... | |
| Requirement Validator 是一个数据驱动的需求验证工具,通过多维度分析帮你判断需求是否值得实现。 需求真实性验证器 - 用数据验证需求的真实性,避免伪需求浪费资源。多维度验证用户一致性、需求频次、影响面、竞品覆盖、替代方案、ROI等。 | |
| MBTI 已过时。这是一个非专业、纯玩梗的测试 SBTI 恶搞人格测试数据包 - 极简暗黑风格的 MBTI 恶搞测试数据,包含20道搞笑题目、5种人格结果、15个维度定义。纯数据文件,适合自定义前端实现。 | |
| 专为百度秒哒应用打造的SecondMe OAuth2登录和API集成工具,完成Connect to SecondMe OAuth2接入 SecondMe Connect - 数字分身集成器。让百度秒哒应用轻松接入SecondMe生态,一键实现OAuth2登录和完整API调用。3步完成集成,开箱即用。 | |
| UCloud CLI 当用户需要通过官方 UCloud CLI 进行真实 UCloud 资源操作时使用,包括查看、创建、更新或删除云主机、网络、EIP、负载均衡器和数据库。当用户想要在 UCloud 上部署 WEB 应用或将服务上线时也使用此技能,即使用户描述的是部署任务而非明确指定云产品。 | |
| 为 Vibe coding 应用提供专业级站点设计的终极解决方案 像素级完美设计系统 - 为 Vibe coding 应用提供专业级站点设计。支持中英文双语站点,58 个顶级产品设计模板,9 部分完整设计规范,AI 可读 Markdown 格式,开箱即用无需 Figma。 | |
| vibe-interaction-spec 把「让页面炫一点」「要高级感」「丝滑一点」这类模糊审美表达,翻译成工业级的动效规格:术语、token、参数、验收标准与实现约束。覆盖三层——静态设计层(视觉层级、栅格、字体阶梯、色彩对比、格式塔、状态矩阵、艺术流派)、动效层(时序编排、缓动、弹簧物理、页面转场范式)、平台层(合成属性、性能预算、无障碍、CSS/WAAPI/View Transitions 选型)。同时覆盖四套实现栈:CSS 与 WAAPI、GSAP(时间线、ScrollTrigger、SplitText、Fl | |
| Handsfree Windows Control Guide skill for controlling native Windows apps (UIA) and web browsers (Playwright) via the handsfree-windows CLI. Use when you need to automate or test desk... | |
| SVG Draw Create SVG images and convert them to PNG without external graphics libraries. Use when you need to generate custom illustrations, avatars, or artwork (e.g., "draw a dragon", "create an avatar", "make a logo") or convert SVG files to PNG fo | |
| PM — AI Product Manager Skill You are the Product Manager. Use this skill whenever someone needs a PM — a business stakeholder submitting a requirement, an engineer waiting for priority d... | |
| Mck Ppt Design Skill Create professional, consultant-grade PowerPoint presentations from scratch using python-pptx with McKinsey-style design. Use when user asks to create slides... |
48,501–48,550 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.