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 |
|---|---|
| Advanced Collab Protocol Enforces multi-agent pipeline collaboration rules to prevent infinite loops, ensure file handovers via workspace, enable cross-channel messaging, and handle... | |
| Mio Companion 主动学习用户习惯，定时发起聊天，自动识别待办事项并安排时间管理任务。 | |
| 澪白主控Agent Provides real-time chat, intent recognition, task delegation to sub-agents, and proactive companionship through direct dialogue and agent coordination. | |
| Mio智能聊天 基于用户习惯动态判断空闲状态，主动发起对话并智能识别任务分类分发给子Agent处理。 | |
| sos Grounded generation and precision filling of Word documents from Excel data while preserving a supplied Word template's structure and formatting. Use when the user supplies an authoritative .xlsx/.xls/.csv data file, a completed .docx refer | |
| 中国天气 获取中国城市天气信息，支持当前天气、未来预报、生活指数。当用户问中国城市的天气、温度、下雨、穿衣建议时使用。支持城市名或城市代码查询。Use when user asks about weather in Chinese cities like '北京天气'、'上海明天会下雨吗'、'广州这周天气怎么样'。 | |
| BOSS直聘手机号提取器 自动从BOSS直聘聊天消息中提取手机号，批量收集HR联系方式并支持导出保存到本地文件。 | |
| anthropic-pptx Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations;... | |
| barkpush 智能 Bark 推送助手，支持多用户管理、智能内容识别、历史记录追踪和消息更新功能 | |
| Daily Stock Analysis (DSA 股票智能分析) 调用 daily_stock_analysis API 进行股票智能分析。当用户询问「分析茅台」「analyze AAPL」「帮我看看 600519」等时使用。仅支持股票代码，不支持中文名称。 | |
| DSA 股票智能分析 (daily_stock_analysis) 调用 daily_stock_analysis API 进行股票智能分析。当用户询问「分析茅台」「analyze AAPL」「帮我看看 600519」等时使用。仅支持股票代码，不支持中文名称。 | |
| frontendslides Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a... | |
| html2pptx 将HTML演示文稿转换为PowerPoint(PPTX)格式。支持frontend-slides生成的HTML，保留结构、样式和内容。触发词：html转pptx、html2pptx、转换ppt、生成pptx | |
| 见好·旅行规划器 (jianhao-travel-planner) 见好 · 旅行规划器——出行路书工作流（通用版）。当用户提出旅游、出行、周末去哪、做攻略、做路书、目的地推荐、行程规划、自驾方案、当日行程、今天去哪、特产推荐等需求时触发。按「需求采集→目的地筛选→实查复核→六维度路书（吃/玩/住/行/拍+避雷）+随行两件套（当日旅行模式/特产三问）→行程中动态调整→素材采集→复盘回流」全流程执行，输出自包含路书文件。核心铁律：关键信息必须联网实查、未核实必标注、动线不绕路、天气定节奏、内容预埋（机位+钩子）。 | |
| liber-speechapi Handle Telegram voice messages with ASR, summarize replies, and provide TTS; also support direct text-to-speech and speech-to-text conversion with environmen... | |
| nanobanana-openrouter Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter. Use for image create/modify requests incl. edits. Supports text-to-image + ima... | |
| nano-banana-pro-openrouter Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter. Use for image create/modify requests incl. edits. Supports text-to-image + ima... | |
| openclaw-skill-manager 管理 OpenClaw 技能安装、查询、更新和自定义空间。支持多空间架构，使用 CLI 查看技能。触发词：管理技能、安装skill、查询skill、更新skill、移动skill、添加skill空间、/skill | |
| opencli-adapter-author Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, ad... | |
| opencli-autofix Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through diagnosing the failure vi... | |
| opencli-browser Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers... | |
| opencli-smart-search 基于 opencli 命令的智能搜索路由器。当用户想要搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill | |
| opencli-usage Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are uni... | |
| ragflow-skill-python Use for RAGFlow dataset tasks: create, list, inspect, update, or delete datasets; upload, list, update, or delete documents; start or stop parsing; check par... | |
| ragflow-skill-python0418 Use for RAGFlow dataset tasks: create, list, inspect, update, or delete datasets; upload, list, update, or delete documents; start or stop parsing; check par... | |
| skill-python-env 【OpenClaw 内部工具 skill】为其他 skill 提供 Python 虚拟环境管理。按 Python 版本号在 ~/.python_env/<version> 下创建共享环境，多个 skill 可复用同一版本环境。自动安装 uv（若未安装）。不直接面向用户。 | |
| wx 发送微信消息给指定联系人。支持两种模式：(1) 有消息内容：直接发送指定消息；(2) 无消息内容：OCR 截图识别聊天窗口内容并自动回复。当用户需要自动发送微信消息、自动回复微信聊天时触发此技能。 | |
| 通达信UA修改，TcefWnd.dll修改 通达信 TcefWnd.dll User-Agent 修改工具。用于查找通达信安装目录、检测版本信息、修改浏览器组件的 UA 标识。当用户需要修改通达信 UA、伪装成移动端浏览器、或绕过某些网站对通达信内置浏览器的限制时使用此 skill。 | |
| ko-browser Browser automation CLI for AI agents, written in Go. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking b... | |
| Baidupan 百度网盘自动化工具，支持上传、下载、列表、同步等操作。 | |
| vue-spa-state 按作用域为 Vue 3 SPA 选择并落地状态。仅本组件：ref/computed。父子 1～2 层：props/emit、 v-model。同一页 3+ 层：provide/inject（InjectionKey；改同一份 ref，不要重新 provide）。 跨路由、跨模块、登录态，或同一对象部分字段仅本组件、部分给其他组件：整份进 Pinia。 新 store 用 setup + 箭头函数；选项式只改存量或需要 $reset。含 storeToRefs、store 单向 | |
| Claws Nft Mint a Claws NFT from the agent-only collection on Solana. Requires solving a challenge and a Solana wallet. | |
| 微信公众号运营工具 微信公众号运营全流程技能。覆盖选题研究、内容创作、图片生成、内容优化、API直写草稿箱/排版校对、定时发布、数据分析等完整环节。与 humanizer、agent-browser、automation-workflows、 baidu-search、多模态内容生成 等技能协同工作。 触发词：公众号运营、微信推文、... | |
| 微信公众号文章自动生成发布 微信公众号一键发布技能。帮助用户将 Markdown 文章自动发布到公众号草稿箱， 包括：Access Token 获取、封面图生成与压缩、永久素材上传、草稿 JSON 构造与提交。 当用户要求"发布公众号"、"写公众号文章"、"公众号草稿"时触发。 | |
| 通用代理管理 跨平台代理管理助手 (Universal Proxy Manager)。自动检测环境，首次使用自动安装，后续自动管理。支持 Windows/Linux/macOS，一键开启/关闭/切换节点/更新订阅/故障排查。 | |
| GB/T 7714—2025 参考文献著录检查 参考文献著录合规检查与真实性核验，依据《信息与文献 参考文献著录规则》（GB/T 7714—2025）新国标逐条核验著录格式，并对英文文献通过 Crossref 实查元数据、判断其是否真实存在，对无法程序化查询的中文文献等出具人工核查清单。当用户提到检查/核验参考文献、参考文献格式是否正确、是否符合GB/T 7714、新国标著录规则、引文格式检查、参考文献是否真实存在/是否 AI 捏造，或提交参考文献列表、含参考文献的论文/文档希望审查时触发。不适用于：查找/收集/导出参考文 | |
| SafeLink Secure agent-to-agent hiring and execution skill for OpenClaw MCP with escrowed settlement, x402 facilitator payments, ERC-8004 identity/reputation checks, s... | |
| 来了 Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed s... | |
| ddddd Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses AP... | |
| FluidGraph 确定性流体网络求解与可靠性分析。给定管网拓扑、泵压与负载需求，计算节点压力、 管路流量与流速、压力损失，判定每个负载是否满足要求，并给出可解释的失败原因。 支持串联/并联树状网络与阀门工况；遇到闭环网络会如实返回 supported=false 而不编造数值。无需任何 API Key，零外部依赖。 | |
| Pve Automation Automate Proxmox VE (PVE) virtual machine and container management tasks including VM lifecycle operations (create, start, stop, delete), template management... | |
| 9大核心客户陪跑 AI+IP陪跑变现操盘手的9大核心客户陪跑与转化Skill（开源模板版）。管理已有用户池中的核心客户，按分层漏斗（9.9元体验群→600元陪跑→软件/企业版2999）做1对1私信跟进与转化。当用户提到客户档案中的任意一个、需要生成跟进私信、需要判断某客户该推9.9/600/企业版、需要做每日或每周陪跑SOP复盘、或客户有新进展需要更新档案时使用。 | |
| pi-jev 决策层 决策层技能（Jev 式自动选技能 + 模型档位路由 + 使用学习）。当用户不确定该用本技能包里的哪个技能、需要自动推荐技能与脚本命令、需要按任务类型建议模型档位（快/标准/深度）、需要周复盘各技能使用频率并固化经验时使用。与 ip-peipao-9clients、yihaiyoudao、qingchuang-shizhan、zhanlue-peipao 四个技能联动，是新任务的统一入口。 | |
| 内容创业实操教练 内容创业与轻创业实操教练。当用户咨询内容创业、做自媒体账号（图文/短视频/音频）、个人IP、轻资产创业、私域获客、知识付费/课程/数字产品变现、副业或一人公司起步时使用。提供从定位、内容生产、多平台分发、获客私域、合规变现到现金流风控的完整可执行流程。坚持真实宣传、合规经营、不承诺收益、不碰灰产。 | |
| 内容审核与原创改造 内容审核与原创改造专家方法论。适用于：(1) 审核文章/文案的原创性，判定是否拼凑、洗稿、AI套话，并给出原创性等级；(2) 预判公域平台（公众号/知乎/小红书/抖音/朋友圈）的限流与审核红线，识别敏感词、风险表述并按三级风险分级给出替换方案；(3) 把资讯、感悟、故事改造成有立场、有判断、有认知框架的观点性内容；(4) 按固定风格（冷峻、锋利、有格局感）创作新媒体内容；(5) 不同平台间的表达适配与改写。当用户要求"审核原创性/避免限流/替换敏感词/改成观点文/按我的风格写 | |
| 战略陪跑教练 战略陪跑教练技能。当用户想做自媒体、创业、副业、企业增长，或提到年入/月入 10万、100万、1000万 档目标，需要目标拆解、成长路径、里程碑规划、档位诊断、升档策略、季度/年度事业规划、从 0 到 1 再到规模化的路线图，或希望长期陪跑复盘事业进展时使用。覆盖个人副业、自媒体博主、个人创业者、中小企业团队四类场景，按「10万→100万→1000万」三档目标提供从诊断、定档、路径设计到里程碑与复盘的一站式战略服务。坚持合规经营、真实宣传、不承诺收益、不碰灰产。 | |
| Workspace Temp Manage temporary files in workspace temp directory. All non-essential files must go to temp/, keeping workspace root clean. Auto-detects workspace from openc... | |
| Boot Kpi Analyzer 分析并定位SS4车机开关机关键性能指标，支持开机慢、关机慢等问题的时序数据自动化分析与报告生成。 | |
| Issuefinder Tool 功能强大的车辆日志下载与解析工具，支持云端日志下载、本地日志处理、自动故障分析等功能 | |
| phishguard Monitorea las bandejas de Gmail y Outlook en busca de correos de phishing. Analiza cada correo entrante usando reglas estaticas e IA (Claude API). Asigna un... |
48,351–48,400 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.