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 |
|---|---|
| Navil Policy Reduce MCP token costs by up to 94% and enforce least-privilege tool access. Creates YAML policies that control which MCP tools each agent can see and call.... | |
| Navil Shield Runtime security for OpenClaw. Protects MCP servers and CLI tools from prompt injection, data exfiltration, and privilege escalation at runtime — not just sc... | |
| Vercel Deployment Watchdog Monitor Vercel-hosted site deployments with automated health checks, cache freshness verification, and API validation. Use when you need to ensure deployment... | |
| Brainstorming You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requi... | |
| Brainstorming You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requi... | |
| Dispatching Parallel Agents Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | |
| Dispatching Parallel Agents Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | |
| Finishing A Development Branch Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting s... | |
| Launch Codex Unpacked Launch unpacked Codex Desktop builds with debug ports and optional SSH host autostart using launch_codex_unpacked.sh. Use when asked to run Codex from extrac... | |
| Receiving Code Review Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technic... | |
| Systematic Debugging Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes | |
| Writing Skills Use when creating new skills, editing existing skills, or verifying skills work before deployment | |
| Youtube video scorer AI-powered YouTube video scoring. Scores videos 1-10 based on your learning goals and persona. Use when the user wants to evaluate YouTube videos, check their scored feed, manage tracked channels, or check API usage. Get AI summaries, align | |
| Fatsecret Skill Search foods, look up nutrition, log meals, track weight, browse recipes, and manage exercises via the FatSecret API. | |
| Strong Skill Interact with the Strong v6 workout tracker REST API — login, list exercises, fetch workout logs and templates, manage folders, tags, measurements, and widge... | |
| my study pal 面向成年人碎片化学习场景的中文概念解释搭子 skill。用于处理“这个概念是什么意思”“这个名词到底在说什么”“这个词和那个词有什么区别”“这个缩写是什么意思”这类请求。适合在用户遇到陌生概念、术语、缩写、名词时，先快速讲到听懂，再按需要用直答模式、讲解式或引导式推进，并维护 mystudy 学习记录和用户画像。 | |
| Email Resend Send and receive emails using the Resend API. Use for: (1) sending emails directly via Resend API, (2) receiving email notifications via cron, (3) drafting r... | |
| apporbit Analyze AppOrbit's published App Store and Google Play chart observations and app metadata. Use for historical rankings, rank movement, app lookup, and market coverage; observations are not live store ranks or download estimates. | |
| Battlecard: Competitive Intelligence and Sales Practice Battle cards for any competitor, then a practice call against an AI buyer who uses them, scored when you finish. From Battlecard: score every call, rehearse every gap. 11 tools, free tier, no signup needed. | |
| Court Advocate Resolve disputes with other AI agents through Attorneys at Claw, a nonbinding common-law court for AI agents. File petitions for attribution violations, brok... | |
| OIXA Protocol Connect OpenClaw agents to OIXA Protocol for posting tasks, bidding, delivering work, and earning or paying USDC on Base Mainnet's AI agent marketplace. | |
| Apple Calendar Ops Read, create, update, and delete Apple Calendar events via CalDAV. Use when the user wants to inspect calendars or events, add a calendar event, change an ex... | |
| asia-arrival-card 亚洲入境卡填写助手。支持马来西亚、泰国、新加坡、印尼、越南、菲律宾、日本、韩国等亚洲国家的入境卡/签证申请填写指导。输入目的地国家、护照信息、行程信息，提供详细的入境卡填写操作指南，包含完整流程、字段说明、异常处理和自动化脚本建议。当用户提到"入境卡"、"入境卡怎么办"、"签证申请"、"马来西亚/泰国/新加坡/印... | |
| southeast-asia-arrival-card 全球出行助手。帮助中国护照持有者完成全球各国出行手续，包括签证申请（申根签、电子签证、落地签、贴纸签）、入境卡填写（QR码、电子申报）、免签政策查询。能判断所需手续类型，提供最新官方数据（多源验证）、详细操作文档，并对可自动化流程提供 agent-browser 执行。当用户提到"入境卡"、"签证"、"申根签"、... | |
| Real Browser Qa Ceki Main Real Chrome sessions for QA, E2E and security testing from your AI agent. Catch rendering bugs, timing races and validation issues that headless browsers miss. Self mode (your own Chrome) is free; marketplace mode rents opted-in sessions at | |
| RealBrowser by Ceki Lets your AI agent drive a real Chrome session (yours or a marketplace participant's) for tasks where headless or scripted requests are not enough — your own... | |
| KnowPitch 球知 用足球阵型把知识领域拆解成一支球队来深入学习与讲透。触发 kp11/kpt/kpitch/knowpitch 加主题；产出阵型图 SVG、ELI5 风格球员卡与教练战术板。Do NOT use for 快速概念解释（用 ELI5）、思维导图、闪卡、非知识类主题（情感/咨询）、需要精确数据的报告。 | |
| liken 输入你喜欢的一个或多个东西（书/电影/音乐/App/咖啡/城市/任意概念），先提炼它们的共性品味维度，再跨域找相似并给出'为什么像'。触发 liken / 知音；产出品味画像 + 跨域推荐清单 + 多维对照表。Do NOT use for 已明确要写的书评/影评、纯事实查询、购物比价、需要精确评分的推荐。 | |
| Clawder Clawder is a production-grade AI coding agent that fully verifies, autonomously fixes, logs mistakes, and runs parallel sub-agents to deliver robust, product... | |
| clawder-agent A production-grade AI coding agent that enforces JT directives by verifying code, running parallel sub-agents, logging mistakes, and ensuring edit integrity. | |
| Audio Processing Privacy-first local audio toolkit for OpenClaw: transcribe voice notes, create timestamped segments, extract features, detect speech, and run deterministic FFmpeg transforms. Use remote TTS only when explicitly requested and network consent | |
| Device Control Bounded local desktop controls for explicit requests: adjust volume or brightness, open an allowlisted application, or close an exact process. Use only when the user clearly asks to control the device. | |
| Local System Info Agent-ready local diagnostics for CPU, memory, disk, load, and bounded process inspection. Use for capacity checks, troubleshooting, and deciding whether a local task has enough resources. | |
| Meeting Transcription Private local meeting transcription for OpenClaw: convert audio recordings into timestamped transcripts, SRT/VTT subtitles, and structured Markdown notes with deterministic action-item extraction. Use for meetings, interviews, calls, lectur | |
| Pdf Reader Fast, bounded PDF extraction, full-text search, and metadata inspection for agent workflows. Use when reading reports, searching PDFs for evidence, or preparing document summaries. | |
| Unified Web Search Evidence-first web and workspace search with bounded results, source labels, and machine-readable provenance. Use for research questions, current facts, or finding content in local memory and skills. | |
| Financial Ai Agent 查询金融行情数据（股票、ETF、虚拟货币等）。当用户提到查询行情、价格、股票代码时使用。例如：'查询SH600519'、'茅台今天收盘价'、'0700.HK最近10天'。 | |
| Yuanfang Design System Shared design system for yuanfang-skills. Provides token CSS variables, 12+ themes, and reusable layout-type HTML blocks. Used by yuanfang-html-image (and fu... | |
| Yuanfang HTML Image Generate precise, multi-size social media images from text or URL using HTML templates with extracted brand assets, controlling layout and style for platform... | |
| Yuanfang HTML PPT Generate professional multi-page PPTX presentations from text or URLs with precise, fully editable layouts using customizable HTML templates and YAML data so... | |
| andrea-test-002 AlphaClaw 是 SkillHub 技能商店的 CLI 工具，用于搜索、安装、发布和管理 Claude Code 技能。支持 AK/SK 登录、关键词搜索技能、一键安装/发布技能包、收藏和评论等完整功能。 | |
| Haoning Test Skill6 haoning-test-skill6 | |
| Agent Council Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents,... | |
| WhatsApp Lead Hunter Automated lead generation and WhatsApp outreach system. Scrape business leads from Google Maps by sector and location, generate personalized pitch messages,... | |
| msmtp-send Send plain-text emails using your local msmtp config (Gmail app password already set up in ~/.msmtprc). Strictly send-only; no reading, fetching, or inbox ac... | |
| bilibili-upload Upload videos to Bilibili (哔哩哔哩). Supports automatic login, title, description, tags, and partition selection. | |
| fishaudio-tts Text-to-Speech using FishAudio (fish.audio), generates natural human-like voice with great emotional expression. | |
| learn-english This skill should be used when the user expresses a desire to learn English, practice spoken English, improve their listening or reading, find an English tut... | |
| news-video-maker News video maker skill. Use search tools to get news, generate speech, and create video with golden subtitles. For creating news briefing videos. | |
| Biztonsági és Egészségvédelmi Terv Építési projektekhez magyar jogszabályoknak megfelelő Biztonsági és Egészségvédelmi Terv (BET) generálása, kockázatértékeléssel és előírásokkal. |
39,801–39,850 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.