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 |
|---|---|
| Node Connect Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when manual connect fails, local Wi-Fi works but VPS/t... | |
| OpenClaw Memory Canonical Lightweight file-based memory system for single-user AI agents. Uses markdown files only: HOT/WARM/COLD/BUFFER plus SCRATCH learnings, with tiered loading, W... | |
| Qwen Orchestrator Qwen Chat (chat.qwen.ai) access via Puppeteer browser automation with CDP interceptor. Persistent daemon (~35ms startup), health checks, graceful shutdown, P... | |
| Qwen Web Reviewer [GPT] GPT-only reviewer workflow for Qwen Web using the authenticated ChatGPT Work/Codex Cloud Browser. Requires GPT browser-control; not an OpenClaw-native integration. | |
| skill-creator-canonical Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch, restructuring an existing skill, auditing skill quality, or making a... | |
| ClawHub Skill Manager [GPT] Inspect, publish, and adapt ClawHub skills | |
| super-memori Local-first hybrid memory skill for OpenClaw agents. Use when the agent needs to find, recall, search, or reuse past knowledge across episodic, semantic, pro... | |
| Super Memori GPT [GPT-specific] Recover and maintain project continuity across ChatGPT Work and Codex using available history and file tools. Use to resume work, resolve time/version conflicts, checkpoint a project, or prevent context loss. Requires GPT pla | |
| Text to Audio GPT GPT-only: озвучивает текст и документы выразительным голосом и собирает проверенный MP3; подходит для чтения вслух, аудиокниг и озвучки. Требует GPT browser control и FFmpeg/FFprobe, не нативен для OpenClaw; Android ChatGPT требует отдельно | |
| Video Table Transcriber GPT [GPT] Таблицы и журналы событий из видео: разметка по линиям строк, проверка ячеек на кадрах, сохранение доказательств и сравнение логов SCADA. Для ChatGPT Work/Codex с Python, NumPy, Pillow и FFmpeg; OCR Tesseract необязателен. | |
| Facture Make Génère et prépare une facture professionnelle, affiche un résumé pour confirmation, puis envoie la facture validée vers Make.com. | |
| ClawShorts Block YouTube Shorts on Fire TV. Use when asked to check, manage, or configure YouTube Shorts limiting on Buck's Fire TV devices. Triggers on requests like "... | |
| Clawshorts Pkg Block YouTube Shorts on Fire TV. Use when asked to check, manage, or configure YouTube Shorts limiting on Buck's Fire TV devices. Triggers on requests like "... | |
| NextSteps Append context-aware next-step suggestions after agent responses. Generates actionable follow-ups, surfaces unfinished tasks from memory, and includes creati... | |
| deepevidence循证医学AI助手 Use DeepEvidence for evidence-based clinical questions, including guideline interpretation, drug safety and interactions, dose adjustment, clinical-trial evidence, medical literature, and supported medical-image analysis. | |
| Agent Browser A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co... | |
| Apple Design 苹果设计原则与流体交互动效知识库，源自 WWDC 设计演讲，为 Web 平台翻译的 17 条交互设计原则 | |
| Auto Updater Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of w... | |
| Baidu Search Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics. | |
| Baoyu Infographic Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publicati... | |
| Baoyu Seedream Ppt 基于宝玉baoyu-infographic布局框架 + 豆包Seedream 5.0文生图，智能生成图片PPT。支持21种布局 × 21种风格自由组合，根据用户内容自动生成每页一张图片的完整PPT。 | |
| 豆包视频创作助手 基于火山引擎豆包视频生成模型，辅助用户配置项目并分场景确认提示词，逐步生成并合成专业短视频。 | |
| 飞书消息文件下载 从飞书消息中下载文件（视频、图片、文档等）到本地 | |
| HappyHorse 视频创作助手 使用阿里云百炼 HappyHorse 模型生成视频，支持图生视频（首帧/尾帧控制）和文生视频。 | |
| Hermes Feishu Guide Hermes Agent 飞书 Bot 本地部署指南（WebSocket 模式）。包含 Kimi API 配置、WebSocket vs Webhook 对比、环境变量配置等完整步骤。适合本地机器部署，不需要公网域名。 | |
| Harness Engineering Harness Engineering — Generator/Evaluator 双 Agent 编码工作流。用于任何需要规划、编码、评审、质量门禁的编程任务。将做事的 Agent 和评判的 Agent 分开，每个阶段通过质量门禁才能进入下一阶段。 | |
| Qqbot Voice Transcribe QQ Bot 语音消息自动识别 v2.0。自动解码 QQ Silk V3 格式，Whisper medium 模型识别，Gateway 集成，用户确认流程。 | |
| Seedream Ppt Maker Seedream图片PPT制作器 - 宝玉布局框架 + Seedream 5.0文生图，自动生成图片PPT。支持交互式分步确认流程，减少反复修改节省API配额。 | |
| 火山引擎豆包语音播客 生成火山引擎豆包语音播客（PodcastTTS）。输入主题文本，自动生成双人对话式播客音频。 | |
| OSINT Investigator Deep OSINT (Open Source Intelligence) investigations. Use when the user wants to research, find, or investigate any person, place, organisation, username, do... | |
| Alibaba Cloud AI Audio ASR Transcribe non-realtime speech with Alibaba Cloud Model Studio Qwen ASR models (`qwen3-asr-flash`, `qwen-audio-asr`, `qwen3-asr-flash-filetrans`). Use when c... | |
| Alibaba Cloud AI Audio ASR Realtime Use when low-latency realtime speech recognition is needed with Alibaba Cloud Model Studio Qwen ASR Realtime models, including streaming microphone input, li... | |
| Alibaba Cloud AI Audio CosyVoice Voice Clone Use when creating cloned voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from... | |
| Alibaba Cloud AI Audio CosyVoice Voice Design Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from... | |
| Alibaba Cloud AI Audio LiveTranslate Use when live speech translation is needed with Alibaba Cloud Model Studio Qwen LiveTranslate models, including bilingual meetings, realtime interpretation,... | |
| Alibaba Cloud AI Audio TTS Generate human-like speech audio with Model Studio DashScope Qwen TTS models (qwen3-tts-flash, qwen3-tts-instruct-flash). Use when converting text to speech,... | |
| Alibaba Cloud AI Audio TTS Realtime Real-time speech synthesis with Alibaba Cloud Model Studio Qwen TTS Realtime models. Use when low-latency interactive speech is required, including instructi... | |
| Alibaba Cloud AI Audio TTS Voice Clone Voice cloning workflows with Alibaba Cloud Model Studio Qwen TTS VC models. Use when creating cloned voices from sample audio and synthesizing text with clon... | |
| Alibaba Cloud AI Audio TTS Voice Design Voice design workflows with Alibaba Cloud Model Studio Qwen TTS VD models. Use when creating custom synthetic voices from text descriptions and using them fo... | |
| Alibaba Cloud AI Chatbot Manage Alibaba Cloud beebot (Chatbot) via OpenAPI/SDK. Use whenever the user asks to configure, query, or troubleshoot Alibaba Cloud chatbot resources, inclu... | |
| Alibaba Cloud AI Cloud Call Center Manage Alibaba Cloud Cloud Call Center (CCC) via OpenAPI/SDK. Use whenever the user is working on CCC operations such as instance/resource management, config... | |
| Alibaba Cloud AI Contactcenter AI Manage Alibaba Cloud Contact Center AI (ContactCenterAI) via OpenAPI/SDK. Use whenever the task involves Contact Center AI resource lifecycle operations, con... | |
| Alibaba Cloud AI Content Aicontent Manage Alibaba Cloud AIContent (AiContent) via OpenAPI/SDK. Use whenever the user needs AI content generation or content workflow operations in Alibaba Cloud... | |
| Alibaba Cloud AI Content Aimiaobi Manage Alibaba Cloud Quan Miao (AiMiaoBi) via OpenAPI/SDK. Use whenever the user asks for Alibaba Cloud MiaoBi content operations, including listing resource... | |
| Alibaba Cloud AI Entry Modelstudio Route Alibaba Cloud Model Studio requests to the right local skill (Qwen Image, Qwen Image Edit, Wan Video, Wan R2V, Qwen TTS, Qwen ASR and advanced TTS vari... | |
| Alibaba Cloud AI Entry Modelstudio Test Run a minimal test matrix for the Model Studio skills that exist in this repo, including image/video/audio, realtime speech, omni, visual reasoning, embeddin... | |
| Alibaba Cloud AI Image Qwen Image Generate images with Model Studio DashScope SDK using Qwen Image generation models (qwen-image, qwen-image-plus, qwen-image-max and snapshots). Use when impl... | |
| Alibaba Cloud AI Image Qwen Image Edit Edit images with Alibaba Cloud Model Studio Qwen Image Edit models (qwen-image-edit, qwen-image-edit-plus, qwen-image-edit-max and snapshots). Use when modif... | |
| Alibaba Cloud AI Image Zimage Turbo Generate images with Alibaba Cloud Model Studio Z-Image Turbo (z-image-turbo) via DashScope multimodal-generation API. Use when creating text-to-image output... | |
| Alibaba Cloud AI Misc Crawl And Skill Model discovery and skill refresh workflows |
20,801–20,850 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.