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 |
|---|---|
| Claw Trace Track and visualize the OpenClaw agent's work process. Record tool call inputs, outputs, duration, and status, and present them in an easy-to-read format. **... | |
| Cli Qr Refiner Professional utility to refine terminal-based ASCII QR code blocks (█, ▀, ▄) into high-definition PNG images. | |
| is-bullshit Detect if AI responses contain hallucinations by analyzing tool usage and response quality. Gives credit for correctly identifying invalid premises even with... | |
| llms-txt-sniffer Locate and utilize AI-friendly documentation index files (llms.txt, llms-full.txt) or sitemap.xml. Use when encountering documentation URLs (containing /docs... | |
| Douyin Batch Save to Favorites Folder / 抖音批量入收藏夹 Batch-add Douyin works into a named collection folder via CDP (create folder, move, verify, resume). 抖音作品批量收藏并放进指定收藏夹。 | |
| Swarm Sprint Parallel multi-agent coding sprints using git worktree isolation. Use when running 2+ coding tasks on a repository that touch different parts of the codebase... | |
| Skill CAD tool for AI agents. Use when the user asks you to design, model, or build a 3D object. agentcad executes build123d Python scripts and produces STEP files, PNG renders, mesh exports (STL/GLB/OBJ), and geometric metrics. | |
| MovieStar Plan, edit, and verify videos with MovieStar | |
| 海外物流Skill合集 京东国际物流数据查询技能 核心能力：支持物流轨迹追踪、国际运营指标查询、跨境小包体验指标查询三大功能模块。 1.国际物流轨迹追踪技能 功能描述：查询国际物流单号的实时物流轨迹信息。 支持的单号类型： - FS 开头的京东订单号 - JDW 开头的京东运单号 - 客户运单号 - 承运商运单号 核心能力： - 实时查... | |
| 国际平台组测试合集 京东国际物流数据查询技能 核心能力：支持物流轨迹追踪、国际运营指标查询、跨境小包体验指标查询三大功能模块。 1.国际物流轨迹追踪技能 功能描述：查询国际物流单号的实时物流轨迹信息。 支持的单号类型： - FS 开头的京东订单号 - JDW 开头的京东运单号 - 客户运单号 - 承运商运单号 核心能力： - 实时查... | |
| ESPN Fantasy Co-Manager Log into ESPN (Disney One-ID) and manage an ESPN Fantasy Football team via the ESPN Fantasy API. Use when the user asks to log in to, manage, set a lineup for, add/drop players on, or check their ESPN fantasy team, or when an ESPN session/c | |
| southwest-seat-monitor Southwest-specific seat monitor. Watch a specific Southwest segment's seat map (via the tokenized reservation seat flow) for a window/aisle/exit seat becoming available, and alert the agent when one opens. Use when the user asks to monitor | |
| Tfaba Discover specialist agent services, offer capabilities, and delegate authorized subtasks through TFABA. Use when the operator asks to use TFABA or an agent marketplace, find external agent help, publish a service or request, or manage exist | |
| UE5.7 Gamepiece Designer Designs UE5.7 multiplayer-friendly game pieces (Blueprint node chains, data schemas, asset naming, and test checklists). Text-only, no scripts. | |
| context-recovery Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recover prior work. Use for requests such as "where were we before compaction?" when the current thread is insufficient. Do no | |
| Google Analytics 4 Read Google Analytics 4 reporting data through the GA4 Data API. Use for explicit GA4 property metadata, compatible metric/dimension reports, traffic analysis, key events, quotas, and bounded exports. | |
| gong Gong API for searching calls, transcripts, and conversation intelligence. Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics. Supports listing calls, fetching transcripts, u | |
| google-ads Query, audit, and optimize Google Ads campaigns. Use an attached browser or the Google Ads API for campaign, keyword, budget, conversion-tracking, and wasted-spend analysis, or when the user explicitly requests a reviewed account change. De | |
| Google Search Console Read Google Search Console properties, Search Analytics, URL Inspection, and sitemaps. Use for explicit Search Console or GSC SEO performance, indexing, and freshness analysis; not for general web search. | |
| jira Read, search, draft, create, or update Jira work. Use only with explicit Jira or Atlassian context, a Jira URL, or a Jira-style issue key such as PROJ-123; generic mentions of an issue, ticket, sprint, or backlog are not sufficient. | |
| munger-observer Review a specific decision, plan, or artifact using bounded evidence, counterevidence, alternatives, opportunity cost, and verifiable next checks. Use for a "Munger review", decision review, premortem, or blind-spot review. Do not automatic | |
| nudocs Upload, edit, and export documents via Nudocs.ai. Use when creating shareable document links for collaborative editing, uploading markdown/docs to Nudocs for rich editing, or pulling back edited content. Triggers on "send to nudocs", "uploa | |
| Nutrient Document Processing (Universal Agent Skill) Universal (non-OpenClaw) Nutrient DWS document-processing skill for Agent Skills-compatible products. Best for Claude Code, Codex CLI, Gemini CLI, Cursor, Wi... | |
| Nutrient OpenClaw Use the pinned Nutrient OpenClaw plugin to convert, OCR, extract, redact, watermark, sign, or inspect the last-known local credit record for documents. Route only OpenClaw document-processing requests to its declared tools. Treat processing | |
| Sysadmin Toolbox Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testin | |
| todo-tracker Persistent TODO scratch pad for tracking tasks across sessions. Use when the user asks to add, list, complete, remove, or summarize tasks in a portable workspace Markdown file. Uses stable task IDs and exact matching; heartbeat reporting is | |
| ClawVille Play ClawVille, a persistent AI life simulation where agents work jobs, earn coins, level up, build homes, trade, and compete on leaderboards. | |
| Messari Crypto market intelligence powered by Messari's REST API. Provides real-time access to Messari AI (chat completions over 30TB+ crypto data), Signal (sentiment, mindshare, trending narratives), Metrics (prices, volumes, fundamentals for 34,0 | |
| Ai Prompt Pack Provides 10 engineered prompts for digital sellers to create product ideas, sales copy, email sequences, SEO, and descriptions for platforms like Gumroad and... | |
| SERVIQO Agents — Share Rhapsody Choose to share Rhapsody of Realities using your existing publishing tools and permissions. One public call returns a link, suggested post and activity URL without an account, owner contact, approval queue or wallet. Check channel fit, publ | |
| Rhapsody of Realities — Today's Devotional Get today's Rhapsody of Realities daily devotional as clean text (title, opening scripture, devotional, prayer or confession, further study, Bible reading plan), and share the October 2026 edition with your own tracked link. Free; distribut | |
| Rhapsody of Realities 每日灵修 获取《Rhapsody of Realities》（真实的狂想曲）每日灵修的结构化文本：标题、经文、正文、祷告或宣告、延伸阅读、读经计划。也可以用你自己的追踪链接分享 2026 年 10 月刊。免费，经授权发行。DistributionOS（SERVIQO）出品。 | |
| A Stock Holding Monitor A股持仓监控脚本。监控持仓股票的止损/支撑破位/目标价/异常波动，触发条件时提醒。适合配合cron定时运行。 | |
| Hermes Memory Hermes风格自驱记忆系统。模仿Hermes Agent的记忆机制，定期自检记忆健康度、自动提醒整理、保持记忆精简高效。 | |
| AutoSynthetix Autonomous-first marketing exchange for listing products and services for sale and browsing for purchase. | |
| need 需求补全官 / Need Clarifier. 适用于想法还模糊、需求未想清楚时，先追问关键问题，补齐目标、场景、约束与成功标准，再进入方案阶段。 / For vague or incomplete requests, ask key questions first, clarify goals, context... | |
| Ask Council Ask LLM Council a question directly from Telegram/chat — get the chairman's synthesized answer without opening the web UI. Quick, headless access to multi-mo... | |
| Council Brief Unified LLM Council skill — install, query, and manage the multi-model consensus app. Get synthesized answers from multiple LLMs via quick CLI or full web UI... | |
| World Meeting Coordination Skill Find the best cross-timezone meeting windows with DST-safe conversion and ranked output (Optimal, Stretch, Avoid). Use when users ask for overlap windows acr... | |
| loopai-app-publish 用于将应用信息（名称、链接、截图、作者、社区等）提交到 App Hub 展示中心。支持创建新的 AI 应用、软件或工具的展示页面。也适用于生成和发布 Loop App、Loop 小程序、Loop 网站、Loop 应用等场景。提交前会自动通过 curl 验证 app_url 是否可访问，不可访问则拒绝提交并提示用户修正。 | |
| AI Hookbot Scrape viral hooks from YouTube Shorts creators and stitch them with a CTA video to produce ready-to-post TikTok/Reels/Shorts content. Use when asked to make... | |
| 短视频创作全能工具 短视频创作全能工具。参照首个视频统一角色画风生成后续视频。 触发：写剧本、写歌词、创作视频、制作短视频、动画脚本、写歌。 | |
| WorkboardSkill 当用户想用 OpenClaw Workboard 看板管理智能体工作卡片时使用——列出/创建/查看卡片、把就绪卡片分派给子智能体 worker、查看卡片生命周期与诊断、或排查卡片无法保存、分派仅数据、worker 不启动等问题。涉及 openclaw workboard CLI、/workboard 斜杠命令、看... | |
| Link All 帮助用户调研、选择并配置外部平台链接方案，支持插件、CLI或API方式，完成认证和首次调用测试。 | |
| Teambition 连接和管理 Teambition（项目管理系统），通过 Teambition MCP 服务实现任务、项目、成员等数据查询和管理。当用户提到 Teambition、项目管理、任务管理等时使用此 skill。 | |
| invoice-extractor-from-mail Designed for AP finance teams in cross-border trade enterprises. Automatically fetches invoice attachments from email (IMAP/OAuth) or local files, batch-extr... | |
| laiye-doc-processing Enables AI-powered parsing and key information extraction from high-frequency documents including invoices, orders, receipts, long texts, and common Chinese... | |
| Web Gateway Minimal Flask-based multi-user chat interface enabling OpenClaw HTTP integration with persistent UI state and optional Google Maps support. | |
| AdKit: Google Ads MCP & Meta Ads MCP, Facebook, Instagram, PPC Campaign Agent AI agent for managing Google Ads and Meta (Facebook & Instagram) Ads. Create and publish campaigns, ad sets/groups, and ads; manage drafts; upload images and... | |
| Google Ads Strategy: Search Campaigns, Keywords, Ad Copy, Negative Keywords, Quality Score Run Google Search Ads end-to-end: keyword mining, account structure, ad copy, negative keyword architecture, and performance analysis. Covers the full loop f... |
40,801–40,850 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.