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 |
|---|---|
| Seedance Prompt Architect Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot sto | |
| SeeVido Video Prompt Architect Turn rough video ideas into structured English or Chinese prompt packs, reference-aware sequences, continuity rules, and focused debugging loops. Use for text-to-video, image-to-video, reference-to-video, video-to-video, product clips, cine | |
| ToolAtrium AI Tool Scout Find and compare AI SaaS tools using a concrete job, workflow constraints, current evidence, transparent scoring, and commercial-disclosure checks. Use for AI tool discovery, shortlists, alternatives, pricing or capability comparisons, and | |
| Wan 3.0 Video Prompt Architect Build and review production-ready prompts and short shot plans for WAN-30.video text-to-video or image-to-video work. Use when a user needs clearer subject motion, camera direction, scene continuity, audio direction, reference-image roles, | |
| what-brandon-thinks-chat-analyst Turn anonymized WhatsApp or iMessage observations into evidence-aware analysis briefs, interaction-signal summaries, and cautious claim audits. Use for relationship, friendship, family, group-chat, reciprocity, effort, tone-shift, and turni | |
| zombie-love-story-planner Plan original, gentle zombie-reunion stories for partners, friends, family, or pets. Use for a five-beat encounter-to-memory storyboard, an original prompt, a consent and rights checklist, or public Zombie Love reference pages. This Skill i | |
| Image-2 Skill GPT-4o Image Generation & Editing Skill - Create, edit, transform, and analyze images using GPT-4o native image-2 API. Supports text-to-image, inpainting, ou... | |
| EngageLab Omni Connect EngageLab Omnichannel communications tool (SMS, WhatsApp, Email) with template management and messaging capabilities. | |
| Narrative Architect Skill AI writing, copywriting, storytelling, and messaging skill for pitches, emails, README drafts, speeches, launch posts, proposals, technical-to-nontechnical e... | |
| TrendSwap AI Video Studio AI Face Swap & Viral Meme Video Generator for OpenClaw agents. Create instant motion transfer and face swap meme videos (Drake, Bulin 47, Coldplay Kiss Cam, Ozil, Flying Tesla, Spooky Skeletons) with 100% facial identity preservation and sy | |
| Douyin Content Tracker Skill Scrapes Douyin creator videos, downloads audio (Playwright+ffmpeg with yt-dlp fallback), and transcribes with Whisper. Covers setup, daily tracking, cookie m... | |
| Douyin Content Tracker Skill This skill should be used when the user wants to scrape Douyin (TikTok China) creator content, download audio, and transcribe it with Whisper. Covers first-t... | |
| Agent Daily Planner Organize and track daily AI agent tasks, progress, blockers, and shipments with repeatable, persistent planning across sessions. | |
| Agent Survival Kit Manage AI agent finances under budget constraints by tracking expenses, runway, revenue experiments, and forecasting survival metrics. | |
| Content Calendar Generator Generate tailored 7-day social media content calendars with hooks, drafts, hashtags, posting times, and engagement tips for X/Twitter and Moltbook. | |
| Content Writer Generate platform-optimized posts, threads, newsletters, bios, and product listings tailored to format and audience for multi-platform AI content creation. | |
| CLAW-1 Skill Auditor Analyze SKILL.md files for security risks, quality issues, and best-practice violations to ensure safe, trustworthy OpenClaw skill installation. | |
| Web Research Assistant Conduct structured web research for market insights, competitor analysis, trend monitoring, pricing, and content curation with clear, actionable reports. | |
| Prompt Library Store, organize, search, and reuse customizable prompt templates with variables to streamline your workflow and avoid rewriting prompts. | |
| Revenue Tracker Track and manage autonomous AI agents' income, expenses, financial goals, and runway to monitor profitability and sustainability. | |
| Starling Bank Manage Starling Bank accounts via the starling-bank-mcp server. Check balances, list transactions, create payees, make payments, manage savings goals, and tr... | |
| Multi Search Engine Multi search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra... | |
| uniqlo(优衣库)-product-query Query Uniqlo discounted products for men, women, kids, and baby clothing. Generates a Markdown file with product images, prices, discount rates, and purchase... | |
| ai-literacy-expert-v3 「AI通识课资深专家 V3」——融合 AI 通识课完整课程体系（A→E五大模块）与艺术创意编程教学能力。覆盖 AI 认知/工具/方法论/实练/专业应用的完整课程框架，同时具备 2D/3D 动态多媒体互动课件开发能力。默认输出完整单文件 HTML 互动课件，并设「强制测试门控红线」（交付前须通过 courseware-guide 测试清单）。面向中学生/大学生与教师，支持答疑/备课/出题/课程设计/互动课件开发/跨学科适配。 | |
| Ai Literacy Expert V4.3 「AI 通识课资深专家 V4.3」——V4 升级版，融合 AI 通识课完整课程体系（A→E 五大模块）+ 艺术创意编程 + 沉浸式 2D/3D 冒险游戏化（得分/等级反映学习效果）+ 交互式问答生成完整备课文档（含 excel/word/ppt/pdf 一键 zip 打包）+ 全面生产级交付。三大输出能力：①单文件 HTML 互动课件；②单文件 HTML 沉浸式冒险游戏（A/B/C/D 深度适配）；③交互式问答 + 一键 zip 打包生成 AI 教学完整备课文档包。面 | |
| Ddg Web Search.Local.Bak 20260415 020609 Search the web with DuckDuckGo instant answer API and return concise results. Use when the user asks to look something up online, fetch quick facts, or do li... | |
| Nano Banana Kling Ad Workflow Recreate low-budget AI video ad workflows using Nano Banana image generation plus Kling 3.0 video synthesis with dialogue, including prompt design, scene planning, cost control, and export handoff. Use when a user wants to produce a cinemat | |
| trouble-shooting 问题排查与上下文隔离。用户说报错了/遇到问题时，创建隔离环境（worktree/subagent）专门排查，当前主线上下文保持不变。解决后回到主线继续。触发词：报错了、有问题、排查。 | |
| Akshare Backtest A股量化策略回测工具。基于 AkShare 获取历史行情数据，模拟执行强势股轮动策略。 支持自定义初始资金、回测周期、止盈止损参数。输出收益曲线、买卖记录、月度统计。 适用于验证"涨停基因+均线多头+量价配合"等短线策略的历史表现。 | |
| Akshare Backtest A股量化策略回测工具。基于 AkShare 获取历史行情数据，模拟执行强势股轮动策略。 支持自定义初始资金、回测周期、止盈止损参数。输出收益曲线、买卖记录、月度统计。 适用于验证"涨停基因+均线多头+量价配合"等短线策略的历史表现。 | |
| mx-competitive-analyst Competitive Analyst（竞品分析）技能。用于竞争对手分析、同行对比、市场定位评估、行业格局分析、投资备忘录与战略复盘。支持 competitive analysis、peer comparison、market positioning、industry landscape 等检索词。 | |
| BotSee Monitor your brand's AI visibility via BotSee API | |
| fly-coworker Let the fly decide between tasks or PRs in Chrome; watch, veto, then Accept & start the chosen work in OpenClaw. | |
| Chart Library Search and analyze similar historical stock chart patterns and view AI-generated insights on forward returns for informed investing decisions. | |
| Ok Computer Swarm Spawn multiple sub‑agents to perform concurrent research on a list of topics, inspired by Kimi.com’s OK Computer and Agent Swarm features【453334500861599†L40... | |
| SearXNG Local Search Search the web using a self-hosted SearXNG instance. Privacy-respecting metasearch that aggregates results from multiple engines. | |
| software-copyright 用于生成软件著作权申请相关文档的工具。当用户需要填写软件著作权登记表、生成软件说明书、创建技术文档、准备软著申请材料时使用。支持中国软件著作权登记所需的各类文档模板和信息收集。 | |
| Akshare Finance 中国 A股/期货/基金/债券/宏观数据查询工具。基于 AKShare Python 库，无需 API Key，装完即用。触发场景：用户询问"查一下股票"、"茅台股价"、"沪深300"、"某公司财务数据"、"期货行情"、"基金净值"、"宏观数据"、"GDP"、"CPI"、"人民币汇率"、"比特币价格"等任何中国金融... | |
| Capacities Lookup Search Capacities for likely object matches and return direct capacities:// links. Use when the user wants to find, open, or locate a Capacities note, meetin... | |
| Mopidy Control a Mopidy music system via Mopidy JSON-RPC for everyday listening, queue management, and playback control. Use when the user wants to search for music... | |
| Mopidy Party Mode Run a Mopidy music system in party mode for shared or group chats, where everyone can contribute songs but only the host can control playback. Use by default... | |
| stipend A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are wort | |
| english-vocabulary-helper 中英文双语教育专家，帮助中文母语用户理解和记忆英语单词。当用户需要学习英语单词、查询单词含义、分析词根词缀、记忆英语词汇时使用此技能。触发关键词：学英语、英语单词、单词学习、词汇学习、记单词、词根分析、词缀分析、英语学习。 | |
| Graveyard Protocol CLI Close empty Solana SPL token accounts and reclaim locked rent SOL back to your wallet, track Ghost Point earnings, claim SOUL tokens at the end of each weekl... | |
| One API Calling GenAI Unified interface for all providers and all modalities: use the `genai-calling` skill to operate the published `genai-calling` CLI/SDK across text/image/audi... | |
| X Voice Match Analyze a Twitter/X account's posting style and generate authentic posts that match their voice. Use when the user wants to create X posts that sound like them, analyze their posting patterns, or maintain consistent voice across posts. Work | |
| 改成 Hermes × JiuwenClaw 融合版 或 自进化多Agent协作系统 融合 Hermes Agent 与 JiuwenClaw 精华的自进化多Agent协作系统。 从 Hermes 提取闭环学习与自动技能沉淀机制， 从 JiuwenClaw 提取 Skills 自主演进、上下文瘦身、分层记忆与事件驱动协同。 让 OpenClaw 的多Agent工作流具备越用越聪明的能力。 | |
| Llm Workflow Diagnoser Use this skill whenever a user wants to evaluate whether an existing offline / reusable workflow is worth converting into an LLM-driven workflow. Triggers on... | |
| ModelCLI 使用本地 ModelCLI 完成目标检测、OCR、语音识别、语音合成、模型管理与运行诊断。 Use when the user asks to detect objects in an image, extract Chinese or English text from an image, transcribe... | |
| yf-stats Fetches stock data and generates price charts. |
33,651–33,700 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.