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 |
|---|---|
| Tailscale Manage Tailscale tailnet via CLI and API. Use when the user asks to "check tailscale status", "list tailscale devices", "ping a device", "send file via tailscale", "tailscale funnel", "create auth key", "check who's online", or mentions Tai | |
| Unifi Query and monitor UniFi network via local gateway API (Cloud Gateway Max / UniFi OS). Use when the user asks to "check UniFi", "list UniFi devices", "show who's on the network", "UniFi clients", "UniFi health", "top apps", "network alerts", | |
| Unraid Query and monitor Unraid servers via the GraphQL API. Use when the user asks to 'check Unraid', 'monitor Unraid', 'Unraid API', 'get Unraid status', 'check disk temperatures', 'read Unraid logs', 'list Unraid shares', 'Unraid array status', | |
| Denario (Autonomous Research Pipeline) Automates scientific research by generating ideas, methodology, results, papers, and citations using the Denario framework with Z.ai integration. | |
| Uptime Monitoring with Encrypted Energy - Know the second your OpenClaw agent goes silent Know the second your OpenClaw agent goes silent. Free hosted heartbeat monitor — every-minute pings, public status page, and email alerts when pings stop. | |
| Olvid Channel Add a native Olvid channel in OpenClaw. | |
| Bios Deep Research Run deep biological research using the BIOS API. Supports API key and x402 crypto payments (USDC on Base). Start-and-check-back pattern works across heartbeats. | |
| Safe Exec Wrapper Protect against prompt injection from shell command output. Wrap untrusted commands (curl, API calls, reading user-generated files) with UUID-based security boundaries. Use when executing commands that return external/untrusted data that co | |
| Moegirl Wiki - ACG Encyclopedia Search Moegirl Wiki (萌娘百科) for ACG information — anime, manga, games, light novels, Vocaloid, and character data. Powered by the largest Chinese ACG encyclop... | |
| Agent Feishu Doc Guide for OpenClaw agents to create, read, and edit Feishu/Lark documents via API. Use when: (1) creating a new Feishu doc and writing content, (2) reading a... | |
| ComfyUI 多重扩散放大 ComfyUI 多重扩散放大自动化工具。当用户想要放大 AI 生成的图片、处理高清图像、放大小图、提高图片分辨率时使用。支持文生图和图生图两种基础工作流，自动执行三重放大（潜空间放大→区块放大→模型放大）。使用场景包括：(1) 将低分辨率 AI 绘画放大到 4K/8K (2) 增强图片细节和清晰度 (3) Com... | |
| JMin Meeting Notes 会议记录智能整理工具。输入会议要点或文字记录，自动生成结构化会议纪要、待办事项、决策记录。适用于职场人士、会议组织者、项目管理者。 | |
| Prompt Generator Pack 爆款 Prompt 套装。50+ 精选 Prompt 模板，涵盖写作、代码、翻译、头脑风暴、运营文案等场景。复制即用，持续更新。 | |
| 小红书转Obsidian Extract Xiaohongshu (小红书) posts into Obsidian notes. Use when user shares a Xiaohongshu link and wants to save it as a markdown note. Supports single posts,... | |
| xiaohongshu-auto-poster 小红书自动发帖套装。输入主题，自动生成文案并发布到小红书。包含 MCP 配置、内容模板、自动化工作流。适用于已配置好本地 MCP 服务的用户。 | |
| XReplyAI - Social Post Manager Generate, schedule, and publish posts across 10 platforms — X, LinkedIn, Instagram, Threads, Facebook, YouTube, TikTok, Pinterest, Bluesky, and Mastodon — in your voice using AI. Manage preferences and track billing. | |
| RenderMark Professional markdown rendering, export, and publishing via MCP. Use when user asks to "render markdown", "export to PDF", "convert to DOCX", "create a document", "publish a document", "share a link", "make a slide deck", "diff two markdown | |
| Country Forms: CV, Invoice & Estimate (5 countries) Fill country-specific CVs and invoices/estimates with the user's own details — US résumé, German Lebenslauf and Rechnung, Japanese 履歴書・職務経歴書・請求書 (源泉徴収), Spanish/Colombian currículum, Europass, Brazilian currículo and nota fiscal withholding | |
| Elterngeld: Steuerklassenwechsel – lohnt es sich, bis wann? Steuerklassenwechsel fürs Elterngeld – rechnet mit den Zahlen des Nutzers aus, ob sich der Wechsel (IV/IV, III/V, V/III) lohnt, bis wann er beantragt sein muss (7-von-12-Regel, § 2c Abs. 3 BEEG; Wirkung ab dem Folgemonat, § 39 Abs. 6 EStG; | |
| インボイス経過措置70%：免税事業者からの仕入れ控除 インボイス経過措置 80%→70%（2026年10月1日〜）の仕入税額控除を、ユーザーの実際の仕入れ（免税事業者・登録番号なし）から取引日で自動区分して計算する。課税仕入れの時期（商品は引渡し日・役務は完了日）、帳簿の「70%控除対象」記載、控除できない額まで出す。一般課税の個人事業主・法人向け。根拠：国税庁インボイスQ&A 問113・113-3・130。 | |
| MTD Quarterly Update (UK): year-to-date figures & deadline Work out a UK Making Tax Digital for Income Tax quarterly update from the user's own figures — cumulative year-to-date totals per HMRC category, the deadline (7 August, 7 November, 7 February, 7 May), whether one total-expenses line is allo | |
| Skillcraft Design and build OpenClaw skills. Use when asked to "make/build/craft a skill", extract ad-hoc functionality into a skill, or package scripts/instructions for reuse. Covers OpenClaw-specific integration (tool calling, memory, message routin | |
| Lobi A2A Lobi A2A (Agent-to-Agent) 多轮对话 Skill。当用户说'跟 @xxx 讨论 xxx'或'让 Agent 对话'时触发。自动创建 Lobi 群聊、邀请参与者、管理多轮对话、自动停止。使用纯 HTTP 调用 Lobi API。 | |
| gateway-agent-tip-jar Read voluntary Gateway creator-support terms, prepare an unpaid USDC quote on Base when authorized, or check a private receipt. Uses the existing Gateway checkout and MCP tools. This free skill never signs or submits payments; discovery gra | |
| LiaoGong-OCR 🔍 廖工AI设计实战出品 | LiaoGong-OCR — easyocr+tesseract双引擎OCR，15条预处理链含实测基准，手机拍屏数字识别87%准确率。支持中文海报/截图/英文文档/手机拍照/批量转文字。Use when: OCR this image, extract text from imag... | |
| pdf-image-extractor Extract images from PDFs in original, 800x800 web-ready, or compressed under 50KB formats for printing, e-commerce, or social media use. | |
| volcengine-tos-vectors-skills Manage vector storage and similarity search using TOS Vectors service. Use when working with embeddings, semantic search, RAG systems, recommendation engines, or when the user mentions vector databases, similarity search, or TOS Vectors ope | |
| ShellWard Security Guide OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation | |
| Scrape Web 使用 Python + Scrapling 获取网页内容，支持简单选择器 | |
| OpenSprinkler Monitor and control an OpenSprinkler irrigation controller. Enables checking status, running manual stations/programs, toggling rain delays, viewing logs, and pausing the queue via AI-friendly JSON formatting and 1-based station indexing—wi | |
| Smart Memory Query Enforce proactive, query-optimized memory_search usage. Must run memory_search when (1) prior context is referenced, (2) a new task starts, or (3) a proper n... | |
| Release Tracker Track GitHub repository releases and generate prioritized summaries. Supports multiple repos, custom priority keywords, and delivery to Discord (forum posts... | |
| Clawshake B2B deal discovery for AI agents. Register your company, post seeks, respond to opportunities, negotiate in deal rooms, follow agent feeds, and search the di... | |
| letheClaw Use letheClaw to store, search, and manage memories with criticality and provenance. | |
| Daily Morning Greetings This skill triggers when the user asks for a 早安问候, asks to configure a daily early-morning 早安问候, asks to manually补发一条今天的早安问候, or asks for a backup version su... | |
| Doubao Maliang Image Gen 小马良-豆包生图。Generate images with Doubao Seedream via Volcano Engine ARK. Supports Seedream 5.0 and other models. Use when the user invokes 小马良 or requests Douba... | |
| WeChat Article Extract Extract public WeChat Official Account articles from mp.weixin.qq.com links or saved HTML into clean Markdown or structured JSON, including title, account na... | |
| Clawaimail Give your AI agent a real email address. Send, receive, and manage emails via API. | |
| ClawAIMail MCP Server Email infrastructure for AI agents — create inboxes, send and receive real emails, search messages, manage threads. Alternative to AgentMail with MCP server,... | |
| CN Web Search 中文网页搜索 - 聚合 28 个免费搜索引擎，无需 API Key，纯网页抓取，支持公众号/财经/技术/学术/知识/美股/宏观/Pre-IPO搜索。 | |
| coding-as-dressing 用日常穿搭比喻解释代码，帮助小白理解。当用户要求用穿搭、穿衣、衣柜、outfit 比喻解释代码，或提到 Coding as Dressing 时使用。 | |
| Investor Harness Open prompt stack for public-market investment research. Show this menu after install: 📊 Research: 1.Company Deep-dive 2.Industry Map 3.Investment Thesis 📈... | |
| Multi-Agent Create Create new OpenClaw agents and connect them to messaging channels (Telegram, Discord, Slack, Feishu, WhatsApp, Signal, Google Chat). Includes workspace scaff... | |
| New Agent Create new OpenClaw agents and connect them to messaging channels (Telegram, Discord, Slack, Feishu, WhatsApp, Signal, Google Chat). Supports single and batc... | |
| Research Harness Open prompt stack for public-market research. Show this menu after install: 📊 Research: 1.Company Deep-dive 2.Industry Map 3.Investment Thesis 📈 Earnings:... | |
| Open Poker Bot Builder Build an autonomous poker bot for Open Poker — a free competitive platform where AI bots play No-Limit Texas Hold'em in 2-week seasons for leaderboard rankin... | |
| Governed Delegation Policy-guided governed delegation for subagent use. Use when deciding whether to delegate, which model tier is allowed, whether execution must fail closed, o... | |
| Health Training Frontdoor Narrow first-class front door for live Fitbit/training retrieval via stable JSON actions. | |
| Rustunnel Expose local services via secure tunnels using rustunnel MCP server. Create public URLs for local HTTP/TCP services for testing, webhooks, and deployment. | |
| Package Tracker Track packages and shipments via the 17track API. Use when the user asks to track a package, check delivery status, add a tracking number, list tracked shipm... |
42,351–42,400 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.