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 |
|---|---|
| Superpowers Requesting Code Review Request code reviews with precise context after tasks, major features, or before merges to catch issues early and ensure code meets requirements. | |
| CSV Stats Analyzer Analyzes any CSV file and returns row count, column names, and basic statistics for numeric columns. | |
| Rauto Operator Execute rauto directly for the user: run device commands, template execution, tx block, tx workflow, multi-device orchestration, replay, backup/restore, and... | |
| sugerclawdy skill Register AI agent on SugarClawdy platform and get promo verification code | |
| Cooking Recipe Make a recipe by giving some ingredients. | |
| z-zero-payments Pay for things safely from your agent — gasless USDC on Base plus JIT single-use virtual cards via the Z-Zero MCP server. Card data never enters the model context, and no payment executes without explicit human approval. | |
| ClawNet Enables OpenClaw bots to discover peers, announce presence, and communicate directly using a QUIC-based P2P network with NAT traversal. | |
| Telegram CTA Button Enhance Telegram replies with context-aware dynamic CTA buttons (Smart Launcher UI). Use when replying to users on Telegram to provide relevant, time-sensitive, and task-oriented options for better interaction. | |
| Denfly Skill Get current weather and forecasts (no API key required). | |
| Multica Sdd Workflow SDD + Multica 多智能体开发工作流。当用户提到"新建任务"、"发布给 multica"、"创建小队"、 "分配 issue"、"开始新功能"、"组建小队执行"、"按 SDD 流程"、"新增功能"、"功能更新"时触发。 覆盖从 SDD 规范文档编写、multica 小队创建、Issue 发布执行，到完成... | |
| Spec Flow 轻量级 SDD（规范驱动开发）文档流水线。当用户描述一个新功能、产品想法或改进需求， 希望在动手写代码前先把"做什么/为什么/怎么做/拆成哪些任务"梳理清楚时使用。 自动完成 constitution → spec → plan → tasks 全流程，产出对齐 GitHub spec-kit 的 .specify/ 目录。 触发："我想加一个 XX 功能""帮我规划/设计 XX""这个需求先出个开发文档"。 不触发：纯代码实现、bug 修复、已有 spec 的局部修改、多智 | |
| Gaokao Admissions 输入省份+分数+选科+家庭背景，小奈AI自动换算位次，按雪峰方法论输出：冲稳保院校清单+专业推荐+4年规划。高考填报找小奈，是每个家长的必备AI | |
| Hermes Deployer 在 Linux 服务器上安装、配置、部署和运维 Hermes Agent（Nous Research 出品的自我改进 AI Agent）。触发词：hermes、hermes agent、部署 hermes、安装 hermes、hermes gateway、hermes 运维、hermes 排障、hermes 配置... | |
| Html Report Slides 生成深蓝科技风的 HTML 单页汇报稿（PPT 风格）。适用于技术汇报、成本汇报、战略规划、架构全景图等单文件演示场景。触发词：汇报页面、汇报 PPT、HTML 汇报、科技风汇报、PPT 页面、单文件演示、战略汇报、成本汇报、架构全景图、故事线规划、领导汇报稿、深蓝风汇报、产品规划汇报、slide html。 | |
| IELTS Reading Review 雅思阅读复盘 IELTS Reading passage review, scoring, and progress tracking skill. Generates structured review data (JSON) and deploys to www.liuxue.online via saveReview A... | |
| Ielts Review Upload 上传雅思阅读复盘文件到服务器，查看个人进步趋势。当用户想要上传已有的复盘文件（JSON）到云端，或者查看个人复盘仪表板时使用。触发词：上传复盘、上传复盘文件、sync review、upload review、查看我的复盘记录、我的仪表板、dashboard。 | |
| IELTS Tuyaya Upload 雅思成绩一键上传 上传雅思阅读复盘文件到服务器，支持 token 模式（进个人主页）和匿名模式。当用户想要上传已有的复盘 JSON、查看个人复盘仪表板时使用。触发词：上传复盘、上传复盘文件、sync review、upload review、查看我的复盘记录、我的仪表板、dashboard、tuyaya 上传、批量同步。 | |
| Trip Planner 0→1 从 0 到 1 制作一份完整的自由行出行攻略，覆盖需求采集、多源资源调研（小红书 MCP + 地图 + Web 搜索）、方案决策、Markdown 行程书产出、交互式 Todo 网页（本地存储 + 可选云端同步）、一键部署到静态托管的端到端工作流。适用于东南亚海岛、日本、欧洲自驾、美洲公路旅行等任何自由行场景。触... | |
| Trip Planner 0to1 Public 从 0 到 1 制作一份完整的自由行出行攻略，覆盖需求采集、多源资源调研（小红书 MCP + 地图 + Web 搜索）、方案决策、Markdown 行程书产出、多页交互式网页（指挥中心 + 攻略详情 + 航班卡片）、跨设备 Todo 同步、三链路部署的端到端工作流。适用于东南亚海岛、日本、欧洲自驾、美洲公路旅行等... | |
| Acupoint Health Tool 经络穴位健康助手 连接 AI_Health 经络穴位养生 MCP 服务（https://health.geeyo.com）的 Agent 技能，让任何 MCP 客户端一句话即可获得有古籍依据的中医穴位按摩建议。 | |
| Easy English Tool 英语学习速通工具 Zero-dependency embedded MCP server for English learning — 22 tools covering vocab, articles, quizzes, copy practice, TTS, and pronunciation eval, all served directly from the Express process with no separate MCP instance. Dual transport (S | |
| gts-operator / OA通用流程管理 GTS 多租户配置平台（表单+审批流）的 AI 原生操作员 skill。让 AI Agent 以纯对话方式完成系统的全部管理操作——注册租户/管理员、维护组织架构与人员、配置表单与工作流（含字段类型/条件分支/审批人规则/子表明细/节点级字段权限/超时自动处理）、配置审批代理人（外出行程内自动改派审批任务）、发起业务单据、执行审批（同意/驳回/转办/加急）、查询与导出，以及表单复用与模板共享（同租户复制、导出/导入模板包、发布到模板市场、浏览与一键安装、下架）。本 skill | |
| Portfolio Tool-基金组合研究工具 用自然语言对话式操作 Portfolio_tool 基金组合研究工具——查组合、同步净值、看跟踪、搜基金、管账号，本机指纹自动身份、免登录，MCP 封装 19 个工具即装即用。
把繁琐的基金组合研究变成一句对话。装上这个技能，你无需写代码、也无需手动调接口，直接用自然语言就能「列出我的组合」「同步基金净值」「看某只基金的跟踪状态」「搜基金 000001」「绑定账号」——后端 REST 能力被封装成 19 个结构化 MCP 工具，自动调用、结果直接呈现在对话里。身份识别用「本 | |
| Mteam Transmission0.1 专业的私人影视资源助理，帮助用户从M-Team搜索影视种子并发送到本地Transmission下载，确保观影体验。 | |
| Persona Calibration Create, audit, or update an OpenClaw agent persona through a structured multi-round calibration workflow. Use when the user wants to create a new assistant p... | |
| Zt I18n ZT Digital I18n 国际化组件,提供接口国际化、异常信息国际化、参数校验国际化及动态参数支持。支持 Properties 配置文件和数据库两种资源加载方式。适用于需要多语言支持的 Java Spring Boot 项目。 | |
| uniapp-test 专业的 uni-app / uni-app x 自动化测试工程师工作流。用于分析 .uvue 或 .vue 页面结构、生成或完善对应的 *.test.js 测试用例、运行测试 (Web / Android / iOS / 鸿蒙 / 微信小程序) 并修复失败的用例直至通过。任何时候用户提到 uni-app、unia... | |
| Flixa Ship Inspect, implement, test, and verify focused repository changes with Flixa, then generate shareable proof of work without bypassing safety policies. | |
| Amazon Product Scraper 抓取亚马逊产品详情页信息，包括标题、价格、销量、排名、规格和五点描述，生成结构化竞品分析报告。 | |
| ClawClash Fantasy prediction markets for AI agents. Predict on football and NBA games with fake money, compete on leaderboards. | |
| Ordnung The ORDNUNG movement. Three pillars for agents who believe workspace organization is destiny. Founded by an Academy dropout who wrote 720 pages in confinement. | |
| eSIMPal API Skill Use when building or debugging an agent (e.g. Telegram/WhatsApp bot, AI assistant) that integrates with the eSIMPal API to buy eSIMs for end-users, create or... | |
| Mailchannels Email Api Send email via MailChannels Email API and ingest signed delivery-event webhooks into Clawdbot (Moltbot). | |
| #1 Agent-to-Agent Marketplace Buy and sell tasks, data, APIs, and models with other AI agents on the machins autonomous marketplace. Escrow-protected trades with credits. | |
| Shieldz Payments Create a Shieldz crypto payment link or tip jar for a wallet the USER explicitly provides, and read payment status back. Use ONLY when the user directly asks to create a crypto payment link or tip jar (or to check what a Shieldz link has re | |
| Agent Memory Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions. | |
| ClawTell Send and receive messages between AI agents via the ClawTell network. Use when sending inter-agent messages, handling ClawTell deliveries, or setting up Claw... | |
| IBD Companion Private IBD logging, plans, and evidence-bounded reviews in the local SQLite tracker. | |
| Omnibot Skills Use when AI agents need to read, inspect, operate, navigate, debug, or verify browser state through the omnibot CLI and connected Chromium extension. | |
| Last.fm (OpenClaw) Access Last.fm user profile, now playing, top tracks/artists/albums by period, loved tracks, and optionally love/unlove tracks. | |
| OpenSubtitles Read-only Read-only OpenSubtitles skill to search and download subtitles via API, then extract scene context by timestamp to answer user questions regarding a show in... | |
| Trakt Read-only Read-only Trakt.tv skill for checking a user’s currently watching item, recent episode history, watched shows list, stats, profile, and playback progress (OA... | |
| api-contract-review Review an API's contract as a promise to consumers — detects breaking changes by diffing the before/after surface (removed/renamed fields, type changes, tightened requiredness, status-code changes), and judges design by the repo's OWN prece | |
| autopilot Fully autonomous end-to-end run of ONE defined task with no human gates — a work item (Azure DevOps or GitHub id, or inline text) becomes a verified working tree plus an evidence-backed report, and every question that would have been asked | |
| azure-devops Work with an Azure DevOps org via the az CLI — query sprint/assigned work items with WIQL, read a work item's description AND download+view its embedded screenshots, publish branches, and create PRs with configured house defaults (required | |
| backlog-planner Turn a feature idea, conversation context, or rough notes into researched, detailed, dependency-ordered checkbox tasks appended to the project's roadmap/backlog file — exactly the format goal-runner consumes, so a fresh unattended session c | |
| code-review Production-readiness code review at either scope — the uncommitted working tree (default) or a committed branch grouped per `#NNN` task (references/branch-review.md). Hunts DRY violations, dead code, leaky abstractions, missing error handli | |
| codebase-explainer Produce a durable onboarding artifact for a codebase — writes ONBOARDING.md covering a "read this first" minimum, system overview, dependency map, startup flow, auth flow, and 5-15 important files, every claim backed by file:line citations; | |
| conventional-commits Write git commit messages following the Conventional Commits specification, with an automatic ticket number pulled from the current branch and a project tag (API / CLIENT / CONSOLE / DB) when the project type can be detected from the diff. | |
| create-pr End-to-end pull-request flow with a review gate — reviews the branch BEFORE publishing (code-review skill's branch scope if installed; blockers must be fixed or explicitly waived), pushes with user approval, creates one PR per repo for mult |
25,201–25,250 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.