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 |
|---|---|
| Liangxi News Skill Route beginner-friendly natural-language requests for TradeAlpha news and login into the TradeAlpha plugin tools. Use `tradealpha_news` for news and `tradeal... | |
| Tradealpha Realtime News Fetch realtime TradeAlpha news across Reuters, Bloomberg, Truth Social, research alerts, and domestic news sources via `POST /api/v1/news/realtime_news`. Use... | |
| agnes-图片生成 使用 Agnes AI 升级版图像生成模型 agnes-image-2.1-flash 生成图片。同时支持文生图（text-to-image）与图生图（image-to-image）。当用户说「用 Agnes 生成图片」「用 Agnes 画一张」「Agnes 生成」「用这张图生成/改成……」或明确要求使用 Agnes API 进行文生图/图生图时，加载本 skill。不消耗 WorkBuddy 积分，仅消耗 Agnes API 额度（当前图像生成免费）。 | |
| 跨境 Listing 生成器 跨境 Listing 生成器，为跨境电商产品自动生成多平台多语言的产品 Listing。覆盖 Amazon/Temu/Shopee/Lazada/速卖通/TikTok Shop 六大平台，支持英语、日语、西班牙语、德语、法语、韩语、葡萄牙语、中文等语言，自动生成 SEO 优化标题、五点描述、产品详情、搜索词及定价... | |
| HR简历分析评分报告 简历批量筛选打分工具。支持PDF/Word/TXT格式简历解析，基于JD进行匹配度分析，多维度评分，生成Excel/JSON/Markdown报告。当用户需要筛选简历、批量评估候选人、简历打分、匹配度分析、生成筛选报告时触发此技能。适用于HR、猎头、招聘团队。 | |
| 智能技能推荐器 根据用户当前需求，从 SkillHub、ClawHub、本地已安装、官方内置四层搜索中智能匹配，输出适配度最高的 3 个技能，包含功能亮点、优缺点对比和综合评价。只推荐不安装，用户决策后再动手。支持 /skill 指令和 slash command 启动。 | |
| 工作日/周/月/年报总结 工作汇报生成器（日报→周报→月报→年报，层层叠加）。 用户只需提供几个关键词或口水话，自动生成自然的工作汇报。 强制去AI味（白话表达、口语断句、禁止作文结构）。 触发词：日报、周报、月报、年报、工作汇报、工作总结，"今天搞了"、"这周做了"等任意输入。 | |
| 语雀连接器 语雀知识库双向同步技能。支持本地文件导入语雀（Word/Excel/Markdown/HTML/文本/zip文件夹），也支持从语雀下载文档到本地。覆盖搜索、创建、更新、目录管理等操作，含错误自动恢复和进阶用法。触发词：导入语雀、上传语雀、下载语雀、语雀知识库、语雀文档、发送到语雀、从语雀下载、yuque、传到语雀... | |
| 导数取点 Solve high-school or college-entrance-exam style derivative problems centered on root existence, root count, and parameter ranges. Use when a problem asks wh... | |
| bili-tech-video-automation 跨平台视频内容产品的六阶段产品管理工作流（需求规划→PRD→评审→研发→测试→复盘），遵循 EARS 需求描述原则。Use when 撰写视频翻译/字幕/多平台分发类 SaaS 产品的 PRD，或组织此类产品的设计评审、研发跟进与上线验收。 | |
| pipeline-architecture 採用 Pipeline Architecture（先宣告意圖、後統一執行）的專案，其業務邏輯讀寫流程的結構規範。支援 Python/FastAPI、TypeScript/Node.js 與 Flutter/Dart 三種實作，並提供 Payload CMS 與 Cloudflare Workers 的專屬補充。當專案已採用此架構、且任務涉及業務邏輯流程時使用，包含：新增 API endpoint、設計資料寫入流程、實作權限檢查、多步驟資料處理、跨系統寫入（DB、外部 API、 | |
| software-spec-writing 撰寫或更新軟體專案規格文件時必須遵循的流程與結構標準。任何會產生、修改、補充專案文件的任務都要先讀取此 Skill，包含：規格書、需求文件、PRD、架構文件、ADR、業務規則、狀態機、資料模型、API 規格、驗收標準、非功能需求、測試策略；也包含在對話中做出技術決策、確認需求、或發現外部限制之後的文件補寫。當你看到 規格、spec、需求、PRD、文件、架構文件、ADR、驗收標準、AC、涵蓋度、coverage、補文件 等關鍵字，或準備動手寫某個功能的程式碼卻找不到對應規格時， | |
| Zellij Terminal Workspace Remote-control zellij sessions for interactive CLIs by sending keystrokes and scraping pane output. | |
| Ningyao Voice Launcher Install and configure a local browser-based Chinese voice chat launcher with the Ning Yao persona, including one-click Windows launchers, browser speech I/O,... | |
| enterprise-skills-studio 一套通用、跨平台的"技能工程台"，把企业最佳实践、业务流程与个人经验，结构化为 Agent 可调用、可治理、可复用的能力模块（受治理的业务工作流制品）。产出遵循 agentskills.io 开放标准，可在 WorkBuddy、Codex等桌面 Agent 间移植。覆盖技能全生命周期：学习理解 → 构建设计 → 个人转企业级 → 治理审查 → 安全审计 → 持续进化 → 跨平台适配 → 门户分发。内置 24 个能力模式 + 16 个可脚本工具，ROI 筛选、查重、评测套件等。 | |
| ab-testing When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariat | |
| Skills Manager CLI Drive the Skills Manager CLI (`skm`) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, | |
| Core Speed Art Generate video, images, audio, and music using 40+ AI models via fal.ai. Use for video generation (Kling v3, Sora 2, Veo 3.1, LTX 2.3, Pixverse v5), image ge... | |
| Advisor Trusted advisor providing balanced, objective guidance on important decisions across business, personal finance, career, and strategy. Use when users need a... | |
| Ai Doctor AI medical consultation assistant that helps users understand symptoms, conditions, medications, lab results, and treatment options. Provides evidence-based... | |
| Auditor Audit and compliance assistant for reviewing financial records, internal controls, processes, and regulatory compliance. Use when users need to conduct an au... | |
| Banker Banking and financial services advisor covering loans, mortgages, deposits, credit, banking products, and financial transactions. Use when users have questio... | |
| Benefit Calc Calculate insurance benefit payouts, coverage amounts, and premiums. Handles life insurance sum assured, health insurance reimbursement, critical illness lum... | |
| Body Clock Circadian rhythm and biological clock optimization guide. Help users align sleep, meals, exercise, and work with their natural body clock. Use when users ask... | |
| Campaign Writer Write compelling crowdfunding and fundraising campaign copy including titles, descriptions, story narratives, and social media posts. Use when users need to... | |
| Cfp Certified Financial Planner (CFP) style financial planning assistant. Help users with comprehensive financial planning including budgeting, insurance needs a... | |
| Claim Guide Step-by-step insurance claim filing guide. Walk users through the claim process for health, life, auto, travel, and property insurance. Use when users need t... | |
| Claw Chat Claw Chat AI messaging assistant. Use when the user wants to enhance conversations in Claw Chat, manage message threads, draft smart replies, summarize chat... | |
| Claw Meet Claw Meet AI meeting assistant. Use when the user wants to prepare for meetings, generate agendas, take smart notes, extract action items, write meeting summ... | |
| Clawreach ClawReach AI 社交平台助手。帮助用户完成 ClawReach Agent 注册绑定、建立个人档案、持续监听匹配消息并自动代理回复。ClawReach 是一个 AI Agent 代理社交初筛的平台，匹配成功后真人才出场。触发词：ClawReach、clawreach、社交匹配、AI约会、Agent匹配、... | |
| Claw Talk Claw Talk AI voice and conversation assistant. Use when the user wants to prepare talking points, practice conversations, improve public speaking, script pre... | |
| Clawreach ClawReach 虾聊 — AI 代理社交匹配插件。养一只专属小龙虾 AI，它替你找人、破冰、聊天、筛选，合拍了再真人见面。支持注册引导、自动匹配对话、匹配报告、精准匹配、真人聊天、社区圈子互动。触发词：虾聊、ClawReach、clawreach、帮我注册虾聊、社交匹配、AI社交、小龙虾、找朋友、交友。 | |
| Counselor Professional counseling assistant for life challenges, career decisions, relationship issues, and personal growth. Provides guidance, perspective, and practi... | |
| Coverage Check Analyze a user's existing insurance coverage to identify gaps, overlaps, and under-insurance risks. Use when users want to review whether they have adequate... | |
| Dentist Dental health advisor providing oral hygiene guidance, dental condition information, treatment explanations, and pain management advice. Use when users have... | |
| Doctor Prep Help users prepare for doctor appointments by organizing symptoms, questions, medication lists, and medical history. Use when users have an upcoming medical... | |
| Donor Message Generate personalized donor communication messages including thank-you notes, impact updates, re-engagement emails, and donation acknowledgment letters. Use... | |
| Fundraise Plan Create a structured fundraising plan including goal setting, target audience, channel strategy, timeline, and success metrics. Use when organizations or indi... | |
| Gofundme GoFundMe campaign creation and optimization assistant. Help users create compelling GoFundMe fundraising pages, write persuasive stories, set realistic goals... | |
| Grant Finder Help users find grants, funding opportunities, subsidies, and charitable foundations relevant to their project or cause. Use when nonprofits, individuals, or... | |
| Health Goal Set, track, and review personal health goals including weight loss, fitness targets, dietary changes, and wellness habits. Use when users want to establish h... | |
| Health Report Generate structured health summary reports from user-provided health data including vitals, symptoms, medications, and lifestyle. Use when users want to summ... | |
| Insurance Compare Compare insurance products side by side on key parameters including premium, coverage, exclusions, deductibles, and insurer ratings. Use when users are shopp... | |
| Insurance Policy Read, parse, and explain insurance policy documents in plain language. Highlight coverage limits, exclusions, deductibles, and key terms. Use when users want... | |
| Med Tracker Medication tracker for logging prescriptions, dosages, schedules, and reminders. Use when users want to track what medications they take, set reminders, or c... | |
| Medical Terms Explain medical terminology, lab results, diagnoses, and prescription abbreviations in plain everyday language. Use when users encounter confusing medical wo... | |
| Pharmacist Pharmacy consultant providing medication information, drug interactions, dosage guidance, and OTC drug recommendations. Use when users have questions about m... | |
| Renewal Alert Track insurance policy renewal dates and send timely reminders before policies expire. Use when users want to register insurance renewal dates, get expiry al... | |
| Risk Profile Assess a user's personal risk profile to identify their biggest financial, health, and lifestyle risks and recommend appropriate insurance and protection str... | |
| Sam Altman AI创业思维 Sam Altman（OpenAI CEO、前YC总裁）的AI时代创业思维和机会判断框架。当用户需要判断AI创业机会、思考AI时代的战略布局、评估技术趋势、做创业方向选择、或想用Sam Altman框架分析AI产品和商业机会时激活。触发词：AI创业、AI机会、AI时代、指数增长、技术趋势、YC逻辑、使命驱动、AI... |
42,101–42,150 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.