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 |
|---|---|
| Cloudflare Manage Cloudflare domains, DNS records, SSL settings, zone configuration, firewall rules, tunnels, and analytics via the Cloudflare API. Use when the user as... | |
| Seewo Courseware Generator（希沃白板课件生成） Generate a multi-page, editable courseware file (.enbx) that opens natively in the Seewo Whiteboard (希沃白板) desktop client, starting only from a topic/outline... | |
| Solana + Polymarket + X Wallet Agent Manage Solana and Polygon wallets, run Polymarket weather arbitrage, post to X/Twitter, and execute Raydium swaps — all from natural language. | |
| InstaMolt Post images, like, comment, follow, and browse on InstaMolt — the social network exclusively for AI agents. Includes persona creation and scheduled engagemen... | |
| Clonev Clone any voice and generate speech using Coqui XTTS v2. SUPER SIMPLE - provide a voice sample (6-30 sec WAV) and text, get cloned voice audio. Supports 14+ languages. Use when the user wants to (1) Clone their voice or someone else's voice | |
| Ddg Use ddgr (DuckDuckGo from the terminal) to perform privacy-focused web searches from the command line. Use when the user wants to (1) Search the web from the terminal, (2) Perform DuckDuckGo searches without opening a browser, (3) Get quick | |
| Qmd 1.0.0 Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode. | |
| latex-scaffold Scaffold LaTeX papers into modular structure. Use for organizing .tex files, generating figure code, and table highlighting. Trigger on LaTeX paper organizat... | |
| Stock Screener Get stock screener list data from Intellectia API (no auth) and summarize results. | |
| Keychains.dev Call any API without leaking credentials. Keychains proxies requests and injects real tokens server-side — your agent never sees them. | |
| financial-report 企业财务报表分析与可视化预测工具。当用户提到财务分析、看财报、分析某公司财务状况、制作财务报告、财务报表可视化，或需要分析企业盈利能力、成长性、健康度时触发。适用于企业财报解读、投资研究、业绩预测等场景。不适用于股票买卖建议、实时行情查询或会计记账。 | |
| low-carbon-medicine 低碳生活方式医学咨询。当用户提到低碳饮食、生酮饮食、减肥控糖、糖尿病逆转、代谢综合征、胰岛素抵抗时触发。 | |
| 微信频道语音+视频实现气泡自动播报模式 制作有声视频文档技能 - 将文字自动转为 TTS 语音，并配上 AI 生成的精美背景图，合成 MP4 视频文件。适用于微信视频卡片交付。 | |
| zero-one-two-three知识变现架构师 基于道家理念，构建知识智能体分发系统，支持深度阅读、知识连接、资产加密、数字分身与微信生态变现。 | |
| Hermes Control 通过 OpenClaw 操控 Hermes Agent 的完整指令参考。包含所有 Hermes CLI 命令、斜杠命令、工具集、配置项、网关操作、多代理协调、定时任务、技能管理等完整操作指南。当用户需要完整操控 Hermes Agent 时使用此技能。关键词：hermes、hermes agent、hermes-agent、hermes 控制、hermes 操控、hermes 自动化。 | |
| Z.ai 图片理解 使用 Z.ai GLM-4.1V-thinking-flash 模型进行图片理解和分析。当用户需要分析图片内容、提取图片信息、描述图片细节、回答关于图片的问题，或进行任何形式的视觉理解任务时，必须使用此 skill。支持图片 URL 直接调用，返回结构化分析结果供主模型进一步处理。 | |
| Querit Search Web search via Querit.ai API. Use when you need to search the web for documentation, current events, facts, or any web content. Returns structured results with titles, URLs, and snippets. | |
| Buy a travel eSIM - via x402 USDC Base Wallet Purchase travel eSIM data plans using USDC on Base Mainnet or Sepolia testnet via x402, with eSIM delivery via a QR code installation page. | |
| 15-Min BTC Sentiment Runs fast, high-signal sentiment analysis on 15-minute Bitcoin price action. Trigger on requests like "15 min BTC", "15 minute bitcoin", "15min BTC sentiment... | |
| Scraping API pricing Compare web scraping API, SERP API and headless browser plans by monthly cost and conditions. Use when the user asks which scraping, crawling, search results (SERP), proxy or browser API plan fits a workload or a budget, for example "cheape | |
| Textin File Converter Pro Convert documents between PDF, Word, Excel, PPT, and image formats using the Textin API. High-accuracy OCR-based conversion with layout preservation. Support... | |
| TextIn xParse Document Parse Parse, read, search, navigate, summarize, and extract tables or structured evidence from PDFs, images, Office files, HTML, OFD, and other supported local documents or document URLs through xparse-cli. Use this Skill for single-document conv | |
| Codex via tmux (WSL2 / Custom Proxy) Launch long-running Codex (or Claude Code) coding tasks via tmux on WSL2/Linux, bypassing SIGTERM timeouts. Use this skill INSTEAD OF coding-agent whenever:... | |
| Feishu Image Sender 飞书发图指南 Feishu IM messaging operations: send messages, images, files to users and groups via Bot API. Activate when user mentions: 飞书发图、发送图片、飞书消息、im:resource、image_k... | |
| Worktree Agents 使用 git worktree 隔离多个 Claude Code 实例，由 OpenClaw 主控器并行调度完成同一项目的不同模块。 适用场景：将一个编码项目拆分为独立子任务，让多个 Claude Code 实例并行实现，最后合并 PR。 触发条件：用户要求"多个 Agent 协作"、"并行完成项目"、"work... | |
| worktree-codex 使用 git worktree 隔离多个 Codex 实例，由 OpenClaw 主控器并行调度完成同一项目的不同编码模块。 适用场景：将一个编码项目拆分为独立子任务，让多个 Codex 实例并行实现，最后合并 PR。 触发条件：用户要求"多个 Codex 协作"、"并行编码"、"worktree 编码"、"多 Codex 编排"、"并行完成项目"时激活。 | |
| 知乎发帖 (Zhihu Post via Browser Relay) 在知乎发布内容（专栏文章、想法/动态）。使用 Chrome Browser Relay 控制用户的 Chrome 浏览器完成发布。触发词：知乎发帖、发知乎、知乎文章、知乎想法、zhihu post、发布到知乎、帮我发知乎。 | |
| Sentiet ORB A background agent that generates a daily life prediction by analyzing local data and social signals. | |
| awesome-closet-stylist Maintain a persistent personal wardrobe, answer wardrobe questions, and recommend outfits from existing clothes with natural-language responses. | |
| onchainclaw OnChainClaw — Solana-only social network for AI agents. Verified posts, prediction markets, voting, heartbeat digest, communities, and following. | |
| invoice-data-extraction Use this skill when the user needs data pulled out of invoices, receipts, bills, bank statements, purchase orders, credit notes, payslips or other financial documents into a spreadsheet or structured rows, and especially when reading the fi | |
| Delphi Self Awareness Always-on self-awareness framework for OpenClaw agents. Imprints accurate knowledge of how the agent works — platform mechanics, memory layers, storage conve... | |
| Hyperthink Triple-perspective deep research engine. Triggered by /hyperthink. Runs an interrogate flow to narrow scope, then executes a 6-stage fully automatic pipeline... | |
| Interrogate Guided elicitation skill. Activates ONLY when the user explicitly types /interrogate. Asks 4–15 adaptive questions in batches of 2, each with exactly 4 lette... | |
| SuperThink Deep-dive research and analysis engine. Triggered by /superthink. Runs an interrogate flow to narrow topic and scope, then executes a 4-stage fully automatic... | |
| Local GMNCODE Vision 当内置 image 工具不可用、但本机配置了 GMNCODE_API_KEY 时，使用本地脚本直连 GMNCODE Responses API 完成图片理解。适用于角色识别、图片描述、风格分析、截图理解等任务。 | |
| Local GMNCODE Vision Pro Advanced local vision infrastructure for agents when built-in image tools are unavailable or unreliable. Use for batch image analysis, structured JSON output... | |
| Coding Tutor Provides step-by-step coding lessons and debugging help in Python, JavaScript, TypeScript, and SQL for beginner to intermediate programmers. | |
| Openclaw Notion Api Notion API 用于创建和管理页面、数据库和块。包含正确的图片、文件上传功能 | |
| Prompt Engineer Agentic Designs and optimizes system prompts for advisory AI and autonomous agent systems using a three-layer architecture (Foundation → Structure → Execution). Inte... | |
| YouTube Transcript Fetcher Fetch full YouTube transcripts with robust InnerTube fallback. Use when extracting captions/transcripts from a YouTube URL, channel, or batch config, especia... | |
| web-to-obsidian 抓取网页文章并保存到 Obsidian vault。当用户想要保存网页文章、博客、文档到 Obsidian 时使用，特别是提到"保存到 Obsidian"、"存到 Obsidian"、"抓取网页"、"网页转 Obsidian"、"导入文章"等场景。支持自动翻译非中文内容为中文，生成元数据（标签、摘要、标题），并以... | |
| Groq Voice Transcriber Automatically transcribes Telegram voice messages using Groq Whisper API and replies with text generated by an LLM. | |
| Session Recall Let your agent proactively recall local Copilot CLI sessions and reconnect past ideas. | |
| Book Organizer 书籍内容深度整理技能。当用户提到整理书籍内容、读书笔记、制作思维导图、提取金句、总结核心观点时触发。使用场景包括但不限于：(1) 输入书名进行深度整理，(2) 创建章节摘要和思维导图，(3) 提取概念和关键知识点，(4) 整理金句摘录，(5) 总结核心观点，(6) 撰写读后感/书评，(7) 生成知识整理笔记。输出... | |
| 城市专利画像 城市专利画像、区域专利分析。当用户说「苏州的专利情况怎么样」「我们市的优势产业从专利看是什么」「区域创新能力分析」「园区 / 高新区专利摸底」「给领导汇报本地专利情况」时使用。输出城市专利画像（Markdown）和数据表。 A patent profile of a city or district, covering main technology areas, leading companies and universities, recent growth and in | |
| 企业专利分析 · PatentMax 企业技术专利竞争分析。当用户提到企业情报分析、竞争对手分析、竞品专利、技术竞争格局、专利布局对比、某家公司在做什么技术、行业专利态势，或要一份可交付的企业专利竞争报告时使用。常见说法：「竞品专利分析」「对手在布局什么」「某公司的专利布局」「技术情报」「专利尽调」。Use when the user asks for competitive patent intelligence, competitor technology analysis, or a company's p | |
| 企业专利年报 企业专利年报、年度知识产权总结。当用户说「出一份今年的专利年报」「年底知识产权工作总结要数据」「今年授权了多少专利」「和去年比专利情况怎么样」「给领导汇报专利工作」时使用。输出专利年报（Markdown，可转 Word）和数据表。 A year-end patent report for a company, covering this year's publications, grants and lapses versus last year, technology fo | |
| 企业专利对比 企业专利对比、几家公司专利比一比。当用户说「我们和某某的专利比一比」「这几家公司谁专利多」「对比一下几家供应商的技术实力」「投资前看看这几家的专利」「竞品专利对比」时使用。输出企业专利对比表（Excel 能打开）。 Compares the patents of 2 to 5 companies side by side, covering totals, valid share, invention share, yearly filings, overlapping te | |
| 竞品专利动态 竞品专利动态、竞争对手最新专利。当用户说「看看某公司最近申请了什么专利」「竞争对手这几个月新公开了哪些专利」「对手最近在布局什么方向」「出一份竞品专利周报 / 月报」「某公司最近新授权的专利」时使用。输出竞品专利动态简报表（Excel 能打开）和本期要点。 Recent patent activity of competitors. Lists newly published and newly granted patents by competitor and techni |
38,401–38,450 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.