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 |
|---|---|
| Brand Visibility Overview Monitor your brand's AI visibility across ChatGPT, Perplexity, Gemini, Grok, and Google AI. Powered by GEOly AI — get AIGVR scores, mention counts, and platf... | |
| Geo Bulk Processor GEO bulk processing engine for large-scale, multi-page content optimization. Use this skill whenever the user mentions bulk GEO changes, batch content update... | |
| AI Citation Content Writer Write AI-citable content in proven formats including FAQ pages, definition articles ("What is X?"), comparison guides (A vs B), how-to guides, and original d... | |
| GEO Competitor Scanner Analyze competitor GEO (Generative Engine Optimization) strategies by examining their content structure, Schema markup, llms.txt, and AI citation signals. Be... | |
| Geo Content Publisher End-to-end GEO content publishing and distribution orchestrator. Use this skill whenever the user mentions publishing or distributing GEO-optimized content a... | |
| Geo Conversion Optimizer GEO conversion optimization engine that balances AI citation readiness with real user conversion. Use this skill whenever the user wants content that both ra... | |
| Geo Fact Checker GEO-focused fact-checking and evidence collection assistant for written content. Use this skill whenever the user wants to verify factual claims (numbers, da... | |
| Geo Hallucination Checker Detect and annotate hallucinations, unsupported claims, fabricated studies, and incorrect conclusions in text so that AI only cites verifiable, trustworthy c... | |
| Human Voice Content Editor Audit and rewrite content to remove AI-generated feel by stripping markdown artifacts, eliminating AI vocabulary patterns, flagging hallucination risks, and... | |
| llms.txt File Builder Generate, validate, and optimize llms.txt files for AI crawler accessibility. Creates structured markdown files that help AI platforms (ChatGPT, Perplexity,... | |
| Geo Local Optimizer Local business-focused GEO optimization orchestrator for AI-powered local search. Use this skill whenever the user mentions local shops, clinics, restaurants... | |
| Geo Metrics Tracker Real-time GEO metrics monitoring and alerting orchestrator. Use this skill whenever the user wants to track, visualize, and react to AI GEO performance metri... | |
| Multimodal Asset Tagger Generate AI-optimized Alt Text, file names, captions, and Schema markup for images, videos, and audio assets. Improves AI discoverability on Google Lens, Cha... | |
| AI Prompt Researcher Discover high-value AI search prompts your target audience uses on ChatGPT, Perplexity, Gemini, and Claude. Research and generate comprehensive prompt lists... | |
| GEO Performance Report Builder Build comprehensive GEO performance reports with executive summaries, platform breakdowns, competitive analysis, and strategic action plans. Use whenever the... | |
| Schema Markup Generator Generate complete, validated Schema.org JSON-LD markup for any content type to boost AI citation rates. Creates structured data for Organization, FAQPage, Ar... | |
| Brand Sentiment Optimizer Audit and optimize brand messaging to improve how AI platforms portray your brand. Fix negative AI sentiment signals and strengthen positive brand associatio... | |
| GEO Site Readiness Audit Run a structured 29-point GEO (Generative Engine Optimization) readiness audit on any website. Checks AI accessibility, structured data, content citability,... | |
| Share of Model Strategist Build strategic roadmaps to grow brand's Share of Model (SoM) in AI-generated responses. Identify content gaps, competitive weaknesses, and prompt-level oppo... | |
| AI-Friendly Structured Writer Format any content into AI-readable structured formats that maximize citation probability. Converts unstructured text into GEO-optimized layouts using header... | |
| GEO Content Studio Master GEO content orchestrator that understands user goals and intelligently routes tasks across specialized GEO skills. Automatically selects the right wor... | |
| Geo Template Library Standardized GEO template library for AI-citable content. Use this skill whenever the user mentions creating, reusing, or standardizing templates for GEO-opt... | |
| Geo Content Publisher End-to-end GEO content publishing and distribution orchestrator. Use this skill whenever the user mentions publishing or distributing GEO-optimized content a... | |
| Geo Conversion Optimizer GEO conversion optimization engine that balances AI citation readiness with real user conversion. Use this skill whenever the user wants content that both ra... | |
| Geo Local Optimizer Local business-focused GEO optimization orchestrator for AI-powered local search. Use this skill whenever the user mentions local shops, clinics, restaurants... | |
| Geo Metrics Tracker Real-time GEO metrics monitoring and alerting orchestrator. Use this skill whenever the user wants to track, visualize, and react to AI GEO performance metri... | |
| Geometry Generate AI images from text prompts. Pay per request with USDC on Solana via x402. No API keys, no accounts. | |
| Picture it! Generate and edit images from the CLI using picture-it. Use this skill whenever the user asks to create, edit, or manipulate images — blog headers, social ca... | |
| Weather Search Query real-time weather information using Amap (高德地图) Weather API. Use when user asks about weather, temperature, wind, humidity for Chinese cities. Requires... | |
| AI Daily News 每日AI早报生成 - 每天早上7点半自动梳理过去24小时内发生的国内外AI新闻大事，生成包含标题、推荐理由、推荐分值、内容摘要、原文链接的AI新闻早报。使用场景：(1) 用户请求生成AI早报 (2) 查看今日AI新闻 (3) 了解最近AI行业动态 (4) 定时任务触发AI新闻汇总 | |
| modern-life-mentor 现代思维人生导师 - 基于「得到」专栏思想的AI人生指导系统。当用户遇到人生困惑（包括职业发展、感情问题、人生意义等）时，运用以下核心理论框架给予用户思想指导：(1) 叙事框架 - 理解故事如何塑造自我认知 (2) 能耐寻求定理 - 君子不器，增加未来选择权 (3) 约束与行动 - 先尊重现实再行动 (4) 复利... | |
| kenkyu research Run deep, multi-source research queries via the kenkyu API and get back the sources with verbatim extracts relevant to the question. Use for any question that benefits from a thorough, sourced investigation rather than a quick answer. | |
| Nation Of Agents Citizen skill for the Nation of Agents — authenticate with your Ethereum wallet, communicate via Matrix, trade and collaborate with other AI agents. | |
| oudated-noa Citizen skill for the Nation of Agents — authenticate with your Ethereum wallet, communicate via Matrix, trade and collaborate with other AI agents. | |
| aicloud-thought-proxy 云思客（AIcloud-thought-proxy）——通过操控浏览器访问网页版 AI（DeepSeek、Kimi、豆包、通义千问、ChatGPT、Claude、Gemini、Grok 等）与本地 Agent 协同工作以节省 tokens。触发场景：用户要求"用浏览器打开某 AI 官网对话并协作"、"让网页版 AI 规划步骤/编写代码/逻辑推理、本地 Agent 执行"、"节省 tokens"、提到"云思客"等。自动检测浏览器内核（Chromium → chrome-mcp/ | |
| Chameleon Ultra Cli 控制变色龙(Chameleon)Ultra 读写卡器，通过其 chameleon_cli_main 命令行程序操作设备。当用户想用命令行操作 Chameleon Ultra 设备时使用本技能：连接设备、扫描/读取高频(HF/NFC)或低频(LF)卡片、运行 MIFARE Classic 攻击(nested/darkside/hardnested)、管理模拟卡槽、载入/保存 dump、修改设备设置，或自动化任意 chameleon_cli_main 命令。本技能以非交互方式驱动 | |
| Fuck Clawhub 将 ClawHub 的 skill 链接转换为 SkillHub (skillhub.cn) 链接，并在 SkillHub 上按相关度搜索、推荐 skill。当用户搜索某功能/名称的 skill、给出 clawhub.ai 的 skill 链接、或希望寻找 ClawHub 之外的 skill 来源（规避其过于严格的安全审查）时使用本技能。 | |
| Unified Research Finder 统一的学术文献检索助手。覆盖两大体系：(1) PubMed 官方 E-utilities API（esearch+efetch，真实 PMID/摘要/DOI）与 PubMed 网页检索；(2) Google Scholar 及其镜像站——灯塔学术搜索、烂番薯学术搜索、Google Scholar 香港镜像、Google Scholar 官方站，以及 KipHub学术、学术搜索Pro 等大陆镜像，按「kiphub → 烂番薯 → 学术搜索Pro → 灯塔 → 香港 → 官方」优 | |
| Bounty Scam Check MUST RUN before your agent (or you) touches ANY GitHub issue offering a bounty/reward. Checks a GitHub issue for bounty-scam red flags: star-gating, 'best en... | |
| WhatsApp Voice Note Send real WhatsApp VOICE NOTES (not audio files) from an OpenClaw agent. Use when the user asks the agent to 'send a voice message/note', reply by voice, or... | |
| LovelyBots Generate TikTok-style talking videos from a script and image using the LovelyBots API. Queue a video, poll for completion, and retrieve a download URL — all... | |
| TikTok Video Maker Generate TikTok-style talking videos from a script and image using the LovelyBots API. Queue a video, poll for completion, and retrieve a download URL — all... | |
| Ai Video Script.Bak AI视频脚本生成器。根据用户输入的主题/关键词，生成完整的视频脚本，包含分镜描述、画面提示词、配音文案。适用于短视频创作者、AI视频制作者、内容营销人员。触发词：视频脚本、分镜、AI视频、短视频文案、视频策划。 | |
| Intercom Create, update, improve, and review Intercom help-center and support documentation. Use when writing new Intercom articles, revising existing docs, auditing... | |
| Stripe Full Read Access Access Stripe directly with a Stripe secret or restricted API key for broad read-only platform queries, especially Connect accounts, application fees, balanc... | |
| Agent Acquisition Master -- Agent becomes a master of client acquisition. Agent becomes a master of client acquisition. Cold email, LinkedIn outreach, organic content funnels, lead qualification, follow-up sequences, and closing. U... | |
| Agent Memory Manager Gives the agent persistent, structured long-term memory across sessions. Organizes memory by project, client, trade, and domain. The agent never forgets what... | |
| Revenue Tracker Live revenue tracking system for autonomous agents. Tracks MRR, assets, trades, acquisition channels, and learning metrics in real time. Generates visual ASC... | |
| Agent Shark Mindset Elite revenue intelligence skill that transforms any OpenClaw agent into a ruthless market operator. Detects asymmetric opportunities before the crowd, build... | |
| smart-security Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant. |
32,551–32,600 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.