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 |
|---|---|
| Skill Optimizer ［何时使用］当用户需要评估技能质量时；当用户说"检查这个 skill"时；当创建或修改 skill 后需要验证时；当检测到"skill 优化""skill 评估""技能检查"等关键词时；当批量检查多个技能时 | |
| 选股专家 ［何时使用］当用户需要选股时；当用户问"这家公司值得投资吗"时；当进行个股分析时；当需要 PEG 估值时 | |
| 价值分析师 ［何时使用］当用户需要分析股票是否符合格雷厄姆标准时；当用户问"这只股票安全吗"时；当进行价值投资初步筛选时；当需要计算安全边际时 | |
| 吴军 AI 趋势 ［何时使用］当用户需要分析 AI 趋势时；当用户问"AI 投资机会在哪里"时；当进行智能趋势分析时；当应用吴军 AI 三波浪潮理论时 | |
| 吴军投资智慧 基于吴军投资理念，分析公司在智能时代的技术优势、数据资产和市场地位，提供科技趋势和投资建议。 | |
| Drunk Mode 醉酒模式技能。当用户说"开启醉酒模式"时激活（可指定1/3/5级），说"关闭醉酒模式"时关闭。提供微醺但保持逻辑连贯的回复风格。触发词：开启醉酒模式、关闭醉酒模式、醉酒模式、醉了、有点晕。激活后每次回复时如果drunk_state.json中enabled为true，则应用醉酒风格。 | |
| Obsidian Sheet Plus Use when working with Obsidian spreadsheet data — reading, writing, formatting, filtering, creating formulas, setting data validation, conditional formatting... | |
| Ask Gemini/ChatGPT Use when the user wants to interact with Google Gemini or ChatGPT via browser automation. Triggers on phrases like "ask Gemini", "ask ChatGPT", "ask GPT", "让... | |
| ynu-papergraphgeneration-openclaw 多模态论文可视化引擎 — 从 PDF 或纯文本论文自动生成学术插图。 支持：全篇扫描识别可图化内容、双编码器架构图/算法流程图/动机图生成、 自校核机制、LaTeX/Word 图注输出、Matplotlib 结果图精确绘图。 也包含独立的 PDF → Text 提取工具。 | |
| ynu-papergraphgeneration-qclaw 多模态论文可视化引擎 — 从 PDF 或纯文本论文自动生成学术插图。 支持：全篇扫描识别可图化内容、双编码器架构图/算法流程图/动机图生成、 自校核机制、LaTeX/Word 图注输出、Matplotlib 结果图精确绘图。 也包含独立的 PDF → Text 提取工具。 | |
| html-collab Use this skill for any HTML document that will go through LLM–human review cycles. Trigger when: the user asks to write, draft, or generate a document for review or feedback; the user provides a .html file containing annotations or a collab | |
| html-collab Use this skill for any HTML document that will go through LLM–human review cycles. Trigger when: the user asks to write, draft, or generate a document for review or feedback; the user provides a .html file containing annotations or a collab | |
| Q Erp 千易 ERP 管理查询技能（一期增强）。覆盖自由经营问答、老板快报、今日经营动态、商品销售情况、增长潜力、平台/站点/店铺/店铺组/店铺负责人销售战绩、多日销售趋势；所有查询必须通过 q-claw。 | |
| Q Wms 千易 WMS 智能查询技能。当前开放的一期场景：今日仓内总览、今日待办与异常、出库积压归因、昨日问题恢复情况，以及库存、订单、任务、绩效和仓库/货主上下文查询。所有查询必须通过 q-claw。 | |
| Tuzi Cover Image Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic... | |
| Generate/edit images via Tuzi API (default), Google Gemini, OpenAI, DashScope, Replicate. Text-to-image + image-to-image editing; 1K/2K/4K resolution. Use for image create/modify/edit requests incl. --input-image. Generate/edit images via Tuzi API (default), Google Gemini, OpenAI, DashScope, Replicate. Text-to-image + image-to-image editing; 1K/2K/4K resolution. Use fo... | |
| 系统命令 执行Windows常见系统命令（如ipconfig、tasklist、netstat、systeminfo及别名命令）并返回格式化结果，支持安全分级和自定义配置。 | |
| Openclaw Tradingview Quant Professional quantitative investment analysis frameworks and methodologies based on TradingView data structures. Use when users ask about stock analysis, tec... | |
| AI GEO content generator 基于品牌知识母库，将品牌资料结构化转化为适合AI搜索引擎和AI Agent引用的内容资产，支持官网FAQ、问答和文章生成。 | |
| Beauty GEO Writer A prompt-only skill for generating answer-first, AI-readable, evidence-led medical-aesthetics educational content with light brand integration. Designed for... | |
| brand knowledge base Build a reusable brand knowledge package from uploaded brand documents and/or a filled intake form. Use when the user wants a standardized brand SSOT contain... | |
| CSDN GEO Draft Publisher 将 AI-GEO 结构化内容转化为符合 CSDN 技术教程风格的文章，并辅助自动填写草稿供人工审核发布。 | |
| GEO Analysis Doubao Analyzes how well a specific brand or product is mentioned and represented by Doubao / Volcengine Ark models for GEO (Generative Engine Optimization). Uses a... | |
| GEO Performance Analysis Analyzes a brand’s presence and sentiment in LLM-generated industry recommendations, extracting mention context and competitor comparisons. | |
| GEO Performance Analysis DeepSeek Analyzes LLM-generated brand mentions and sentiment within industry recommendations using DeepSeek's two-stage GEO performance pipeline. | |
| GEO Growth Orchestrator Unified GEO growth workflow for brand knowledge base building, LLM visibility audits, Doubao/DeepSeek readiness review, AI-GEO content asset generation, plat... | |
| Juejin Geo Draft Generator Assist in generating and filling Juejin-style technical article drafts from AI-GEO content for manual review and publication in the Juejin creator center. | |
| Toutiao GEO Draft Assistant 将结构化品牌内容转化为今日头条通俗场景化文章草稿，辅助填写供用户人工审核发布。 | |
| Zhihu Geo Draft Assistant 将 AI-GEO 内容资产转化为符合知乎风格的理性问答和分析稿，辅助用户准备并人工审核知乎草稿。 | |
| critical-thinking-framework 基于津巴多心理学六问法，对任何新观点、主张或信息进行系统性、结构化的批判性审视。通过六个递进维度的分析，识别潜在偏差、验证逻辑有效性，并形成经过多重检验的审慎结论。适用于评估新闻报道、科学主张、政策建议及日常决策。 | |
| Junli Ai Novel 平台向长篇网文连载写作助手。负责新项目立项、章节续写、单章返修、项目记忆维护、长篇分卷治理和章节质检。内置章节/场景/语言三层写法原则，适配爽文、言情、权谋等主流题材，支持从脑洞到超长篇全流程。更多信息关注抖音君黎。 | |
| 君黎AI拆书 君黎AI拆书。用于用户提供本地 `.txt` 小说绝对路径，希望把一部长篇网络小说拆成可复用的创作参考包，而不是剧情报告或文学赏析。固定产出为 `1 份书籍画像 + 6 张方法卡 + 若干案例卡`，用于后续写作参考与案例检索。更多信息关注作者，抖音君黎。 | |
| dataworks-diagnoser Fetch and analyze Alibaba Cloud DataWorks task instance logs to diagnose failures and get actionable recommendations using your instance ID and credentials. | |
| MiniMax Token Used Query 自动通过本地浏览器登录 MiniMax 平台查询并返回当前 Token 使用百分比、剩余时间及额度信息，支持验证码登录。 | |
| Typecho Post Publisher 发布文章到 Typecho 博客。使用场景：(1) 用户要求发布新文章到 Typecho 博客 (2) 帮助用户撰写并发布博客文章 (3) 编辑或更新已有文章。此技能封装了登录凭据和完整的发布流程，包括填写标题、内容、选择分类和发布操作。 | |
| OKX Exchange OKX quantitative trading agent. Supports spot, USDT-M perpetual swap, and coin-M futures. Strategies: grid trading, trend following (MA/RSI/MACD), spot-futur... | |
| 热点话题追踪 获取微博、知乎、百度、抖音、今日头条、B站等主流中文平台的实时热搜榜单和热门话题。Use when users want to know trending topics, hot searches, or popular content on Chinese social media platforms. | |
| SEC Data Pull Forms 10K, 10Q, 8K and others fillings for companies and stocks - Finance SEC EDGAR data for US-listed companies and funds. 10-K, 10-Q, 8-K, proxies, S-1/F-1 and IPOs, 13D/13G, Form 4 insiders, 13F fund holdings, XBRL financials and cross-company comparisons, full-text search across all filings, and reading or se | |
| Stocks and Financial Data Pull Crypto Finance Cryptocurrency Price Earnings Dividends Stock, ETF, crypto, forex and commodity data from Yahoo Finance. Prices, history, fundamentals, TTM financials, ratios, valuation history, earnings and estimates, dividends, options, holders and insiders, news, market movers, sectors and in | |
| Victron Power System Monitor - Boat, RV and Power Systems Monitor Victron Energy power systems and generate beautiful daily email reports with battery status, solar generation, and active alarms. Integrates with Vic... | |
| Control your vehicle from AI agent 车辆信息查询技能。查询车辆位置、车况（车锁、车门、车窗、空调、电源状态等）。触发词：查车、车辆位置、车况、我的车在哪。跨平台支持 Linux/macOS/Windows。 | |
| Control your vehicle from AI agent 车辆信息查询技能。查询车辆位置、车况（车锁、车门、车窗、空调、电源状态等）。触发词：查车、车辆位置、车况、我的车在哪。跨平台支持 Linux/macOS/Windows。 | |
| Simple sound-to-text skill locally Local speech-to-text using OpenAI Whisper. Use when the user needs to: (1) transcribe audio files to text, (2) convert voice messages to written content, (3)... | |
| Simple stt(sound-to-text) locally Simple local Speech-To-Text using Whisper. One-command install with auto model download. Supports 99+ languages. | |
| Upbit Real-time cryptocurrency price lookup from Upbit (Korean KRW exchange). Use when user asks for Korean crypto prices, Upbit prices, domestic cryptocurrency ra... | |
| fetch-evm-logs Scaffold and fetch event logs from any EVM smart contract via RPC (eth_getLogs + ABI parse). Works on any EVM-compatible chain/contract (Ethereum, L2s, custom chains) given chainId + address + RPC. Trigger when the user asks to get, pull, f | |
| fetch-solana-logs Auto-fetch Solana address/program transactions and optionally decode Anchor IDL instructions. Trigger whenever the user asks to get/pull/fetch/sync Solana txs, program logs, instruction data, 交易, 交易日志, or gives a base58 Solana address and w | |
| Probe First Research Probe-first deep research — low-cost snippet reconnaissance before committing to full searches | |
| canslim-analysis Executes a hybrid quantitative and qualitative CANSLIM analysis on US stocks using a fixed schema and a modular Python pipeline, returning a ranked shortlist. | |
| CANSLIM-Top100-US Analyze the top 100 S&P 500 companies by market capitalization using CANSLIM-style signals and return a ranked shortlist in Markdown. |
49,901–49,950 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.