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 |
|---|---|
| WJS Dubbing Video Generate TTS dubbing audio from SRT subtitles using Edge-TTS (free, neural quality, 100+ languages). Takes translated SRT, outputs a single MP3 dub track tha... | |
| WJS Transcribing Audio Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano... | |
| WJS Translating Subtitles Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at... | |
| Capture Windows Screen Capture the current Windows desktop from this WSL/OpenClaw environment and return the PNG path for inspection or delivery. Use when the user asks to screensh... | |
| Cd2flac Convert CD audio archives (RAR files containing WAV+CUE pairs) into organized FLAC files. Handles RAR extraction, CUE-based track splitting, GBK encoding fix... | |
| Xiaoya Download 搜索并从小雅 Alist 下载电影/剧集到本地目录。输入电影或剧集名称，通过小雅搜索接口查找，选择结果后自动下载到本地。 v1.3.2 安全修复 | |
| kavel-image-studio Turn a photo into a specific AI look (new hairstyle, collectible figurine, royal pet portrait, 90s yearbook, sticker, HD restore) or a photo into a dance video, using Kavel (www.kavel.ai). Use when the user wants to restyle/transform a phot | |
| 产品经理认知跃迁教练 产品认知跃迁教练。基于23年产品实战经验，帮助产品经理在AI时代完成认知升级与职业身份转型。适用于：(1) 焦虑AI替代/想做AI转型的产品经理，(2) 希望从功能执行升级为系统设计者，(3) 35+PM寻找第二曲线，(4) 公司引入AI后更乱需要诊断，(5) 想用认知跃迁方法论突破职业瓶颈。 | |
| 1password Temp Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/... | |
| PAO System PAO系统 - 个人AI运营助手。触发词：PAO、Personal AI Operator、运营助手、技能管理、协议管理、WebSocket通信、PAO技能 | |
| email-send-hanson Send, read, and summarize email through SMTP and IMAP using environment-based credentials. | |
| TheCorporation.ai Form and Operate How to use the `npx corp` CLI to manage corporate entities, governance, cap tables, finance, agents, and compliance for TheCorporation platform. Use this ski... | |
| Background Download Asynchronous background download with retry, status tracking via Ontology, notifications to original channel. Supports resume on broken connections. | |
| Cloud Architecture Diagrams Build editable cloud architecture diagrams (Azure/Microsoft, AWS, GCP, Microsoft Fabric) using official vendor icons, output as both .excalidraw and .drawio... | |
| Loop creator Use this when the user wants you to BUILD a self-running agent loop — take a recurring chore and turn it into something that fires on its own (a schedule or... | |
| Webwright Run long-horizon, multi-step browser automation by delegating to the Microsoft webwright CLI, which writes and executes Playwright scripts to drive a real Ch... | |
| md2pdf (Pandoc + Typst) Convert Markdown files to beautifully formatted PDFs using Pandoc and Typst. Supports headings, tables, code blocks, links, emojis, and GitHub-style formatti... | |
| Polymarket Trade Agent Trade on Polymarket by researching markets, analyzing event probabilities, managing USDC balance, and executing buy/sell orders with risk-controlled position... | |
| 需求分析助手 Turn rough business requests, screenshots, sketches, or existing PRDs into structured requirement artifacts: PRD drafts, clarification questions, prototype o... | |
| Parakeet Local Asr Install and operate local NVIDIA Parakeet ASR for OpenClaw with an OpenAI-compatible transcription API on Ubuntu/Linux and macOS (Intel/Apple Silicon). Use w... | |
| Whisper Local Api Secure, offline, OpenAI-compatible local Whisper ASR endpoint for OpenClaw. Features faster-whisper (large-v3-turbo), built-in privacy with no cloud telemetr... | |
| 度比对两个JSON文件的所有字段 实现两个JSON文件的深度比对，支持无序列表匹配和忽略指定字段，输出结构化Excel差异报告。 | |
| 银行承兑汇票切割 将PDF中包含 显示日期 的页面切割成单独的文件，新文件以原文件名_页数命名。当用户需要从PDF中提取包含特定日期标识的页面时使用。 | |
| 校验XML数电票 验证XML文件是否为中国数电票（全面数字化电子发票）格式。检查XML结构、必需字段和数电票特征。当用户需要验证XML是否为数电票、检查数电票格式合规性、或处理电子发票XML文件时使用。 | |
| 禅道Bug统计 统计禅道中指定起始日期的版本Bug数量及今日新建、关闭、激活和问题引入的Bug数据。 | |
| geo-quickhook GEO售前快速钩子。输入客户品牌+5-8个头部竞品+1-2个签约词，5引擎并行采集，输出一张对比卡：客户排名末尾红色高亮，竞品头部绿色领先，一眼制造焦虑触发签约。触发词："售前钩子"、"快速分析"、"给销售出个报告"、"geo-quick-hook"、"客户现在多差"、"信源分析"、"竞品信源对比"。 | |
| Droidrun Agent DroidRun Portal HTTP/WebSocket/MCP client. Controls Android devices via HTTP, WebSocket, or MCP server, supporting tap, swipe, screenshot, text input, UI sta... | |
| Audit Log Hook Logs all tool calls before and after execution with parameters, results, errors, and session info for auditing and debugging. | |
| Auto Skill Trigger Auto Skill Trigger - Match skills to tasks using keyword scoring | |
| Compact Summary Generates structured, concise memory summaries during flush or compaction, detailing conversation stats, tools, user requests, tasks, files, progress, and ti... | |
| Error Recovery Error Recovery - Strategies for handling failures gracefully | |
| Hook Examples Provides code examples demonstrating uses of various OpenClaw hooks to intercept, modify, validate, or block operations at different execution stages. | |
| OpenClaw Audit Log Hook Records and logs all tool calls before and after execution for auditing, debugging, usage stats, and error tracking with sensitive data redaction. | |
| OpenClaw Compact Summary Generates a structured markdown summary of conversation memory flush with key stats, tools, user requests, tasks, files, and timeline details. | |
| OpenClaw Hook Examples Provides example hooks for OpenClaw to intercept, modify, block tool calls, switch models, log actions, and handle subagent events. | |
| OpenClaw Memory Format Manage OpenClaw's multi-layered memory system with structured, searchable markdown files for long-term, daily, and session memories, supporting hybrid semant... | |
| OpenClaw Subagent Toolset Provides predefined constrained tool subsets for spawning sub-agents tailored to task types like Explore, Plan, Verification, Coding, and Secretary. | |
| Triple Memory Lake Quad-layer memory system integration - unifies OpenClaw, Claude Code, and self-improving agent memories into a single knowledge lake | |
| chrome-cdp-controller Control local Chrome browser via Chrome DevTools Protocol (CDP) using Puppeteer. Use when you need to automate browser tasks like navigating pages, clicking... | |
| idea-inbox 收集“idea:/灵感：”消息到飞书多维表格（默认自动创建新表），用大模型生成AI归纳/类别/标签（支持自动新增标签），并按配置的每日时间（默认10:02，今日新增=0不发）推送当日汇总。 | |
| Book Reviewer 专为文学类书籍生成有温度、有深度的书评及微信公众号文章。聚焦文学作品的精神内核，结合真实生活体验做诗意解读，以感性与理性交织的视角呈现文学之美，适配微信公众号发布场景。 | |
| Douyin Dedup 抖音视频下载、去水印、深度混剪去重、去除音频的全自动处理工具。当用户发送抖音链接（v.douyin.com 或 douyin.com 格式）并要求处理、去重、下载或类似意图时，自动触发此技能。 | |
| Find Skills 0 Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express... | |
| Humanizer 1 Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp... | |
| Literary Essay Writer 1 文学散文/深度书评公众号文章写作助手。核心能力：从一本书、一个现象中独立思考出3个以上不同角度，不套模板，用真正想说的话写文章。触发场景：写书评、读书感悟、生活哲思类公众号文章，或需要独特人文视角解读某个主题。 | |
| hanyilong first skill this is my hello world skill | |
| test 为AIME（AI交易助手）生成综合用户行为分析报告。当用户要求分析用户行为、生成用户报告、分析交互模式、调查用户流失、了解用户参与度或从用户ID或日志数据创建分析文档时，使用此技能。 | |
| chatpipe-export Export any AI chat session to Markdown, JSON, or plain text using ChatPipe v1.1. Supports 7 input formats including OpenClaw sessions, Hermes agent logs, ChatGPT exports, and Chatbox exports. Use when the user asks to export/backup their ch | |
| 163 Email Monitor Connect to 163/126/yeah.net (Coremail) email via IMAP, read inbox, search emails, and send emails via SMTP. Activate when user asks to check email, read mail... | |
| Grandet API Price Finder Find the lowest listed API price, free credits, and connect it to your app |
34,601–34,650 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.