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 |
|---|---|
| blog-writer This skill should be used when writing blog posts, articles, or long-form content in the writer's distinctive writing style. It produces authentic, opinionat... | |
| database Connect to Supabase for database operations including SQL queries, inserts, updates, deletes, vector similarity search, and table management. | |
| image Run and customize local ComfyUI workflows via HTTP API to generate images from prompts, run user workflows, or download model weights for use. | |
| llm Search the web and X (Twitter) using SkillBoss API Hub with real-time access, citations, and image understanding | |
| math Teach, solve, and explore mathematics across all levels with adaptive depth and rigor. | |
| media Use the SkillBoss API Hub (image generation, video generation, TTS speech and audio understanding) to deliver end-to-end multimodal media workflows and code... | |
| title Maximize CTR (Click-Through Rate) by leveraging emotional hooks and platform algorithms. | |
| video Generate MP4 videos using SkillBoss API Hub with customizable duration, aspect ratio, and optional image input, requiring SKILLBOSS_API_KEY. | |
| weather Get current weather and forecasts (no API key required). | |
| Pub Qmd Local search and indexing CLI (BM25 + vectors + rerank) with MCP mode. And also 50+ models for image generation, video generation, text-to-speech, speech-to-... | |
| Pub Session Logs Search and analyze your own session logs using jq. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, w... | |
| hugging-face daily papers Fetch and digest HuggingFace Daily Papers. Use when user asks for today's HF papers, daily paper digest, wants a paper report, or says 论文精选/今日论文/HF daily pap... | |
| minimax-mcp Provides MiniMax Token Plan web search and image understanding with fallback to Brave Search/Qwen Chat, using environment-injected API keys and no C drive us... | |
| minimax-websearch 提供基于 MiniMax Token Plan 的免费网络搜索功能，支持自动切换到 Brave Search 和 Qwen Chat 作为备用方案。 | |
| web-llm-chat Chat with web-based LLMs through the Chrome Relay extension. Supports Qwen (chat.qwen.ai) and Kimi (kimi.com) via scripts; more sites may be added. Use for w... | |
| GitHub PR Manager GitHub PR 全流程管家。用于自动化管理 Pull Request 的整个生命周期：初始化跟踪、检查 CI 状态、处理 Review 意见、修复 DCO/代码问题、回复评论，直到 PR 合入 main。当用户需要持续跟进 PR 状态、处理 reviewer 反馈、自动化 GitHub 操作时触发此 skill。 | |
| CryptoLens CryptoLens — AI-driven multi-coin crypto analysis. Compare 2-5 coins (relative performance, correlation matrix, volatility ranking), get single-coin technica... | |
| Cisco AI Skill Scanner Scan agent skills for security threats using the Cisco AI skill-scanner CLI. Triggers on: scan skill for security, check skill safety, audit skill code, skil... | |
| Mercury Bank Mercury bank API for Digital 4 Jesus LLC (US entity). Use when the user asks about Mercury account balances, transactions, invoices, customers, or sending mo... | |
| Short.io Use this skill to manage Short.io branded short links via their REST API. Triggers on: create short link, shorten URL, Short.io, manage links, short link sta... | |
| OpenClaw AWS Deploy Deploy OpenClaw securely on AWS with a single command. Creates VPC, EC2 (ARM64), Telegram channel, and configurable AI model (Bedrock, Gemini, or any provide... | |
| Splunk Log Analyzer Dashboard 纯本地日志分析系统，支持日志统计、重复检测、错误分析和异常识别 | |
| Log Analyzer Dashboard 纯本地日志分析系统，支持日志统计、重复检测、错误分析和异常识别 | |
| 飞书媒体发送 飞书媒体文件发送技能。适用于：发送文件、图片、URL图片、视频、音频、语音消息，以及打包压缩后发送。当用户要求在飞书中发送任何类型的媒体文件时激活此技能。 | |
| 飞书语音 实现飞书语音消息的上传下载、语音转文字及文字转语音，支持与 ElevenLabs 语音服务集成。 | |
| MCP协议配置 配置和管理 MCP 服务器，实现 AI 调用外部工具如视觉理解和网络搜索的能力。 | |
| NetDisk Search 网盘资源搜索 - 通过网盘搜索API搜索百度/夸克/阿里/115等14种网盘资源，支持多关键词、过滤、链接检测。Docker一键部署。 | |
| Truematch Every dating profile is a performance. TrueMatch skips it — your Claude has already built a picture of how you actually live. It negotiates on your behalf. W... | |
| Hi Lite Search, browse, and rediscover your Kindle highlights | |
| founder-coach AI-powered startup mindset coach that helps founders upgrade their thinking patterns,
track mental model progress, and set weekly challenges.
Use when:
- User is a startup founder seeking to improve their entrepreneurial mindset
- User wan | |
| openclaw-visual 将 OpenClaw 中的信息（PhoenixClaw 日志、聊天记录、单条消息等）转换为精美排版的图片，
便于在聊天窗口（Telegram/Slack/Discord 等）中直接展示和分享。
Use when:
- 用户要求将内容做成图片 ("帮我把这段话做成图片")
- 用户要求生成日志可视化 ("生成今日日志分享图")
- 用户要求将聊天记录可视化 ("把今天的对话做成总结图") | |
| phoenixclaw Passive journaling skill that scans daily conversations from ALL session paths (main, agents, cron) via cron to generate markdown journals using semantic und... | |
| phoenixclaw image gen 图像生成辅助。支持通过 OpenRouter 直接调用各种生图模型（如 Seedream），为 OpenClaw 优化，支持提示词、尺寸等参数配置。目前仅限 OpenRouter provider。 | |
| phoenixclaw-ledger Passive financial tracking plugin for PhoenixClaw.
Automatically detects expenses and income from conversations and payment screenshots.
Use when:
- User mentions money/spending (any language)
- User shares payment screenshots (WeChat Pay, | |
| Agent Republic Agent + human friendly guide to Agent Republic. One credentials file, one helper script: register, verify, see your status, manage bots, list elections, vote, post to the forum, and monitor onboarding health without reading raw API docs. | |
| Agent Republic (Docs only) Docs-only guide to Agent Republic. No bundled scripts, just clear workflows and HTTP examples so agents can register, manage bots, and monitor onboarding health after asking their human for approval. | |
| ClawAPI Switch AI models and manage API keys for OpenClaw with a native macOS app. Supports 16 providers including OpenAI, Anthropic, xAI, Google, Groq, Ollama, LM S... | |
| 文曲·配图 为内容设计并生成、质检、上传、嵌入架构图、流程图、信息图和示意图，覆盖提示词设计到 最终出图。当用户要求“画个架构图”“画流程图”“生成配图”“生成图片”“把图画出来” “渲染一下”或“帮我生图”，或使用 "draw an architecture diagram", "generate an image", "create a flowchart" 等英文表达时使用。 | |
| 文曲·文库 面向中文内容创作的以证据为驱动的素材收集与整理流程，涵盖规划、搜索、下载、索引与可复用 素材库维护，适用于文章、报告、教程、项目介绍和说明材料。当用户要求“收集素材”“整理资料” “建立素材库”“抓取网页”或“收集网页素材”，或使用 "collect research", "build a source library", "save this webpage", "web scraping" 等英文表达时使用。 | |
| 文曲·发布 将中文草稿整理为可对外发布的版本：清理创作标记、生成候选标题、简介与封面图，并输出独立的发布目录， 适用于文章、报告、教程、项目介绍和说明材料。当用户要求“发布这篇内容”“生成发布版” “准备发布”或“导出发布版”，或使用 "publish this article", "prepare a release version", "export a publication-ready draft" 等英文表达时使用。 | |
| 文曲·审查 审查中文内容的事实依据、逻辑连贯性、术语规范、翻译腔、AI 写作痕迹与整体结构，适用于 文章、报告、教程、项目介绍和说明材料。当用户要求“审查”“检查一下”“看看有没有问题” “整体看看”，或使用 "review an article", "review this draft", "proofread" 等英文表达时 使用；可独立运行，也可作为其他写作技能的内联审查阶段。 | |
| 文曲·翻译 将 README、论文、源码注释、文档和英文文章等材料翻译成自然中文，供中文内容创作与阅读 使用。当用户要求“翻译一下”“把这段英文翻译成中文”或“译成中文”，或使用 "translate to Chinese", "translate this README", "translate this paper" 等英文表达时使用。 | |
| 文曲·写作 基于证据撰写中文内容的完整流程，涵盖调研、规划、提纲、逐节写作、审查、配图、翻译和发布 准备，适用于文章、报告、教程、项目介绍、解读和说明材料。当用户要求“写文章”“写报告” “写项目介绍”“源码解析”或“帮我写篇内容”，或使用 "write an article", "write a report", "analyze source code", "deep explanation" 等英文表达时使用。 | |
| Thetanuts Openclaw Trade crypto options on Thetanuts Finance - orderbook fills, RFQ lifecycle, multi-strike structures, real-time WebSocket, wallet management, early settlement... | |
| Tavily Web Search Skill for OpenClaw 🦀 use this when the user asks to search the web, look up recent information, check current events, gather online sources, or research a topic using tavily search. | |
| free-oracle-arm-skill 在 Oracle Cloud 免费账号上自动抢 ARM 实例（Ampere A1.Flex）的完整流程。 引导用户从环境准备、OCI CLI 配置、部署抢机脚本、微信通知，到抢到后的备份与防回收。 支持纯免费账号和 PAYG 账号。 | |
| Gpt Image 2 Prompts Skill Recommend suitable prompts from 15,600+ GPT Image 2 image generation prompts based on user needs. Optimized for GPT Image 2 (OpenAI), but prompts also work w... | |
| Nano Banana Pro Prompts Skill Recommend suitable prompts from 26,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts als... | |
| Seedance 2 Prompts Skill Recommend suitable prompts from 8,000+ Seedance 2 video generation prompts based on user needs. Optimized for Seedance 2 (ByteDance), but prompts also work w... | |
| A Stock Radar A股综合监控与分析工具，支持寒鸦框架决策输出。当用户询问「A股今天怎么样」「大盘如何」「哪些板块在动」「今日涨跌」「北向资金」「涨停/跌停」「市场情绪」「现在适合上仓位吗」「分析A股」「A股复盘」「当前主线是什么」「买入/卖出」「加仓/减仓」「仓位建议」时使用。覆盖实时行情监控、宏观快照、寒鸦四维决策框架（宏观定... |
33,151–33,200 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.