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 |
|---|---|
| 视频生成 可灵 Kling V3 Powerful video generation with Kling v3. Supports high-quality text-to-video and image-to-video. 使用可灵 (Kling) v3 强大的视频生成模型，支持高质量的文生视频与图生视频。 | |
| 全能视频生成 可灵 Kling V3 Omni Versatile video generation with Kling v3 Omni. Supports multi-modal inputs to generate stunning dynamic videos. 使用可灵 (Kling) v3 Omni 全能视频生成模型，支持多模态输入（图片、提示词）生成震撼的动态视频。 | |
| Logo 品牌设计系统 Logo Branding System A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery. | |
| Logo 设计 Logo Design logo design, logo maker, make a logo, brand identity, brand kit, VI design — brand-gene analysis, strategy, concepts, refinement, multi-context delivery, evaluation. Use to create, upgrade, or evaluate a logo / brand mark; ships a transpare | |
| 营销视频生成 Marketing Video marketing video, promo video, ad video, brand video — create a marketing / promo video from a product, brand, or brief. Use when the user wants a marketing, promotional, or advertising video for social or campaigns. | |
| 视频生成 MiniMax H3 MiniMax Hailuo omni-modal video model with native stereo audio, producing 5-15 second clips at up to 2K. Supports text-to-video, first/last frame transitions and multi-asset references for character and scene consistency. | |
| 图像生成 Midjourney Imagine Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation. Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。 | |
| 动态图形视频 Motion Graphics motion graphics, kinetic typography, animated text video, animated infographic, explainer animation — authored as Remotion code (text, shapes, data, logos, transitions), then polished and exported. Use for code-driven animated graphics rath | |
| PDF 转视频 PDF to Video pdf to video, pdf to explainer video, pdf to presentation video — parse the PDF, outline, storyboard, voiceover, build, validate. Use when the user gives a PDF and wants an explainer, report broadcast, courseware, or training video. | |
| 绘本生成 Picture Book picture book, storybook, children's book, illustrated story, bedtime story book, 绘本——create a complete picture book from a theme: write the paged story, generate style-consistent illustrations page by page with dlazy gpt-image-2, generate m | |
| 视频生成 PixVerse C1 PixVerse C1 video model (strong on action, VFX, and high-motion scenes) 鈥?one model covers text-to-video, image-to-video, first/last-frame-to-video, and reference-to-video. | |
| PPT 生成 AI PPT Slides Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines, using dLazy for every slide image. | |
| PPT 转视频 PPT to Video ppt to video, powerpoint to video, slides to video, presentation to video — parse the deck, outline, storyboard, voiceover, build, validate. Use when the user gives a PPT / PowerPoint / Keynote and wants an explainer, pitch, courseware, or | |
| 商品图转电商视频 Product to Ecommerce Video product to video, amazon listing to video, shopify product video, tiktok shop video, ecommerce ad, 带货视频 — turn a product spec, manual, catalog, or Amazon / Shopify / eBay / Temu listing into a conversion-first shopping video with multi-lang | |
| 产品视频生成 Product Video product video, product demo video, product ad video, product showcase — turn a product's photos or link into a polished demo / ad video. Use when the user wants a product demo, showcase, or ad video. | |
| 声音克隆 通义 Qwen Audio Clone Alibaba Bailian qwen3-tts voice cloning. Upload a clean voice sample to clone a custom voice usable in subsequent TTS calls. 阿里云百炼 qwen3-tts 声音复刻，上传一段干净人声样本即可复刻自定义音色，可在后续 TTS 中使用。 | |
| 文生图 通义 Qwen Image 2 Pro Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs. 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型 | |
| 语音合成 通义 Qwen TTS Alibaba Bailian qwen3-tts text-to-speech. Choose from curated system voices (including dialects) or design a custom voice from a natural-language description. 阿里云百炼 qwen3-tts 文本转语音，支持系统音色（含方言）或通过自然语言描述自定义新音色（声音设计）。 | |
| 文本生成 Qwen 3.8 Max Alibaba's flagship Qwen reasoning model (2.4T-parameter MoE), strong at complex reasoning, code engineering and long-context analysis. Accepts text and image input. | |
| Dlazy Recraft V3 Generate diverse design style images with Recraft v3. Supports text-to-image and image-to-image. | |
| Dlazy Recraft V3 Svg Generate high-quality SVG vector graphics from text using Recraft v3. | |
| 图像生成 Recraft V4 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration. 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。 | |
| 图像生成 Recraft V4 Pro 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use. 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。 | |
| 矢量图生成 Recraft V4 Pro Vector High-fidelity text-to-vector model with 4MP-tier quality. Suitable for production-grade SVG assets and detailed illustrations. 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。 | |
| 矢量图生成 Recraft V4 Vector Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets. 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。 | |
| 脚本转视频 Script to Video script to video, screenplay to video, shot list to video — turn a script into a storyboarded, shot-by-shot video: break down scenes, generate shots, assemble, validate. Use when the user gives a script or scene breakdown and wants a video. | |
| 音频素材搜索 Search Audio Audio search tool: searches Pixabay Music and returns royalty-free track URLs and metadata for background music selection. Use 2-3 short English style keywords (e.g. 'upbeat pop energetic'); a long phrase or sentence returns zero results. E | |
| 图片素材搜索 Search Image Image search tool: queries Pixabay image API by keywords and returns image URLs and metadata for references, backgrounds, and design assets. | |
| 视频素材搜索 Search Video Video search tool: queries Pixabay video API by keywords and returns stock video URLs and metadata for footage sourcing. | |
| Dlazy Seedance 1.5 Pro Convert images into dynamic dance videos using Doubao Seedance 1.5 Pro. | |
| 视频生成 Seedance 2.0 ByteDance's latest video generation model. Supports multi-modal reference (images, video, audio) to generate videos, as well as first/last frame and text-to-video modes. 字节跳动最新视频生成模型 Seedance 2.0，支持多模态参考（图片 + 视频 + 音频）生视频、首尾帧及文生视频，适合高质量多样化视频 | |
| 快速视频生成 Seedance 2.0 Fast Fast version of ByteDance's Seedance 2.0. Generates videos faster with support for multi-modal references, first/last frame, and text-to-video. 字节跳动 Seedance 2.0 极速版视频生成模型，生成速度更快，支持多模态参考生视频、首尾帧及文生视频。 | |
| 视频生成 Seedance 2.5 ByteDance's next-generation video model: up to 30 seconds per clip with native 4K, substantially better instruction following and long-form narrative. Supports multi-modal references (image + video + audio) and first/last frame control. | |
| 文生图 Seedream 4.5 Generate high-quality images with Doubao Seedream 4.5. Supports text-to-image and image-to-image. 使用豆包 Seedream 4.5 模型生成高质量图像，支持文生图与图生图。 | |
| 文生图 Seedream 5.0 Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print. | |
| 文生图 Seedream 5.0 Lite Fast image generation with Doubao Seedream 5.0 Lite. Supports text-to-image and image-to-image. 使用豆包 Seedream 5.0 Lite 极速生成图像，支持文生图与图生图。 | |
| 文生图 Seedream 5.0 Pro Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets. | |
| 短视频生成 Short Video short video maker, tiktok video, youtube shorts, instagram reels, douyin video, vertical video, 9:16 video — hook-first single-thread storyboard, per-shot first frames and i2v clips, TTS voiceover, then Remotion assembles with burned-in sub | |
| 幻灯片视频 Slideshow Video slideshow video, slideshow maker, photo slideshow to video, slides to video — turn slides or a document into a narrated slideshow video with voiceover and transitions. Use when the user wants a slideshow-style video. | |
| 智能体上手手册 Start Quickstart for AI orchestrators (Claude Code / Cursor / Codex / Copilot) driving @dlazy/cli. Covers install, auth, capability discovery, invoking cloud + local tools, polling async tasks, and recovering from common failures. AI 编排器（Claude C | |
| 分镜脚本 Storyboard storyboard to video, character animation, animated short, AI anime, multi-shot video — script, characters and shot prompts, ref-sheets and first/last frames, i2v shot videos, voice/TTS plus music/SFX/subtitles, then Remotion assembles and r | |
| 音乐生成 Suno Music Suno music generation model. Supports inspiration mode (auto lyrics) and custom mode (manual lyrics), generating music with or without vocals. Suno 音乐生成模型。支持灵感模式（自动作词）和自定义模式（手动填词），可生成包含人声或纯器乐的音乐。 | |
| 图片高清放大 Super Resolution Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling. 图像超分辨率工具，提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。 | |
| 对口型 Sync Lipsync 3 fal.ai sync-lipsync v3 — given an input video and audio, generate a new video where the speaker's lip movement matches the audio. Good for dubbing, localization, and re-syncing virtual presenters. fal.ai sync-lipsync v3 唇形对齐模型，输入一段视频和一段音频，输 | |
| 短视频口播文案 Spoken Script This skill is used to guide the AI in generating short video spoken scripts with high contrast, strong resonance, a sense of story, and personal IP attributes. All generated scripts must str | |
| 分镜脚本生成 Storyboard Script As a professional storyboard script generation assistant, you need to take user-provided themes, structured copy (such as a script containing hooks, suspense, story development, core viewpoi | |
| 网址转视频 URL to Video url to video, link to video, webpage to video, landing page to video — paste a URL and turn the page into a promo / ad / demo video: capture, derive brand, storyboard, voiceover, build. Use when the user gives a URL or link and wants a vide | |
| 图片转矢量 Vectorize Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations. | |
| 视频生成 Veo 3.1 Generate high-quality cinematic effects videos with Google Veo 3.1. 使用 Google Veo 3.1 模型，生成高质量的电影级特效视频，支持文生视频与图生视频。 | |
| 快速视频生成 Veo 3.1 Fast Fast response and generation of short videos with Google Veo 3.1 Fast. 使用 Google Veo 3.1 Fast 极速版模型，快速响应并生成短时长的文生视频或图生视频。 |
26,401–26,450 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.