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 |
|---|---|
| 人身损害赔偿计算 当用户需要计算人身损害赔偿、交通事故赔偿、伤残赔偿金、死亡赔偿金、丧葬费、误工费、护理费、营养费、被扶养人生活费，或需要导出赔偿明细表时使用。优先调用 scripts/personal_injury_compensation.py 完成计算；references 仅用于脚本依赖的数据校验、法条引用和缺失数据补录，... | |
| 民间借贷利息计算 当用户需要计算中国民间借贷案件中的借期内利息、逾期利息、违约金合并审查、砍头息、复利、还款冲抵、LPR四倍上限或生成正式利息计算书时使用。适用于 1991 年旧民间借贷意见、2015 年《民间借贷规定》的 24%/36% 规则，以及 2020 年后合同成立时 1 年期 LPR 四倍规则。典型触发词包括：民间借贷利... | |
| Video Creator 产品介绍视频自动生成技能。当用户需要生成产品介绍视频、宣传视频、演示视频时、复刻声音时触发。支持：(1) 声音合成——若用户明确指定"我的"声音，则复刻声音并用于下次合成；否则自动使用edge-tts合成语音（支持男声/女声选择）；(2) 基于用户提供的图片素材生成静态幻灯片视频（无需大模型生成视频）；(3) 自动生成对应语言的SRT字幕（软字幕/硬字幕/无字幕可选）并与音频同步。（4）复刻声音。（5）口播引导视频：当脚本首段以"口播："开头时，使用真人照片+TTS音频 并生 | |
| BIMWing 三维模型在线浏览 把本地 BIM / 三维模型或图纸（.rvt/.nwd/.ifc/.dwg/.skp/.obj/.fbx 等）上传到 BIMWing（垒知翼）做在线轻量化转换，生成可在浏览器直接在线浏览三维模型的分享链接。除上传外，还支持列出账号下全部模型、查看转码状态、为已有模型生成链接。需要 BIMWing 账号，会将账号密码以明文保存在本机 config.local.json（仅本机、gitignore）以便复用，且仅在你主动提供时保存。支持 API 直连（主）与 Playwright | |
| tensorlake Tensorlake SDK — sandboxes for AI agents and applications. Use when the user mentions tensorlake or sandboxes, or asks about Tensorlake APIs/docs/capabilitie... | |
| Cmd Helper 命令快捷助手 - 通过 /c 触发命令菜单，快速执行常用操作（新建会话、切换模型、查看状态等）。当用户输入 /c、/cmd 或类似命令时使用。 | |
| Investment Daily Report 每日投研日报自动生成器。当用户需要生成每日金融市场投资研究报告、投研日报、市场复盘、行情总结时使用此 Skill。 覆盖 A 股、港股、美股三大市场，自动采集行情、资金流向、板块轮动、重要公告、技术面分析等维度， 生成结构化 Markdown 日报，适合个人投资者、投资小组日常使用。 | |
| Liurun Fetcher Automatically fetches Liu Run's latest WeChat public articles daily, extracts full text, and generates structured summaries with key insights and trend analy... | |
| Pc Health Check Windows PC一键健康体检工具。覆盖CPU/内存/磁盘/网络/进程/驱动/系统事件/启动项/端口/安全更新， 自动生成结构化Markdown报告，标注风险等级与处理建议。 触发词：PC体检、电脑巡检、健康检查、系统检查、PC health check。 支持两种模式： - 快速模式（--quick）：5项核... | |
| Hailuo2 Use PoYo AI Hailuo 02 for prompt-optimized video generation and image-to-video workflows through the `https://api.poyo.ai/api/generate/submit` endpoint. Use... | |
| Kling 3 Kling 3.0 video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `kling-3.0/standard`, `kling-3.0/pro`, text-to-video, ima... | |
| Poyo Add Instrumental Add instrumental accompaniment to uploaded audio on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `add-instrumental`, backing tracks,... | |
| Poyo Add Vocals Add AI-generated vocals to uploaded instrumental audio on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `add-vocals`, lyrics or vocal... | |
| Poyo Boost Music Style Expand concise music-style ideas on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `boost-music-style`, music prompt enhancement, genr... | |
| Poyo Claude 4 5 Api Claude 4.5 Series Messages API on PoYo / poyo.ai via `https://api.poyo.ai/v1/messages`; use for `claude-opus-4-5-20251101`, `claude-sonnet-4-5-20250929`, `cl... | |
| Poyo Claude 4 6 Api Claude 4.6 Series Messages API on PoYo / poyo.ai via `https://api.poyo.ai/v1/messages`; use for `claude-sonnet-4-6`, `claude-opus-4-6`, Claude-compatible mes... | |
| Poyo Claude Fable 5 Claude Fable 5 Messages API integration on PoYo / poyo.ai via `https://api.poyo.ai/v1/messages`; use when the user explicitly requests PoYo, `claude-fable-5`... | |
| Poyo Claude Opus 4 7 Claude Opus 4.7 Messages API on PoYo / poyo.ai via `https://api.poyo.ai/v1/messages`; use for `claude-opus-4-7`, Claude-compatible messages, system prompts,... | |
| Poyo Claude Opus 4 8 Claude Opus 4.8 Messages API on PoYo / poyo.ai via `https://api.poyo.ai/v1/messages`; use for `claude-opus-4-8`, Claude-compatible messages, system prompts,... | |
| Poyo Claude Sonnet 5 Claude Sonnet 5 chat on PoYo / poyo.ai via `https://api.poyo.ai/v1/messages`; use for `claude-sonnet-5`, Claude-compatible messages, coding agents, long-cont... | |
| Poyo Convert To Wav Convert generated music tracks to WAV on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `convert-to-wav`, WAV export from a completed... | |
| Poyo Create Music Video Create music videos on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `create-music-video`, AI Music Video, visualized music videos, t... | |
| Poyo Deepseek V4 Chat DeepSeek V4 chat on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions`; use for `deepseek-v4-flash`, `deepseek-v4-pro`, OpenAI-compatible chat payl... | |
| Poyo Elevenlabs Music Generate music on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `elevenlabs-music`, text-to-music, instrumental music, structured com... | |
| Poyo Elevenlabs Tts Turbo 2 5 Generate speech on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `elevenlabs-tts-turbo-2-5`, text-to-speech, voice selection, speech... | |
| Poyo Elevenlabs V3 Tts Generate speech on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `elevenlabs-v3-tts`, text-to-speech, voice selection, stability, tim... | |
| Poyo Extend Music Extend existing music on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `extend-music`, music continuation, audio_id based extension,... | |
| Poyo Flux 2 Api Use PoYo AI Flux 2 through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants to generate or edit media with this model family, pr... | |
| Poyo Flux Dev FLUX Dev image generation and single-image editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use when the user explicitly requests PoY... | |
| Poyo Flux Kontext Flux Kontext image generation and editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `flux-kontext-pro`, `flux-kontext-pro-edit... | |
| Poyo Flux Schnell FLUX Schnell text-to-image generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use when the user explicitly requests PoYo or `flux-sc... | |
| Poyo Gemini 3 1 Flash Tts Generate speech on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `gemini-3-1-flash-tts`, Gemini text-to-speech, style instructions, v... | |
| Poyo Gemini 3 5 Flash Gemini 3.5 Flash chat on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions` and Gemini Native Format; use for `gemini-3.5-flash`, chat completions,... | |
| Poyo Gemini 3 Api Gemini 3 Series chat on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions` and Gemini Native Format; use for `gemini-3-flash-preview`, `gemini-3-pr... | |
| Poyo Generate Lyrics Generate song lyrics on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `generate-lyrics`, lyric drafts, verses and choruses, theme-bas... | |
| Poyo Generate Music Generate Music on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `generate-music`, AI music generation, background tracks, soundtrack... | |
| Poyo Generate Music Cover Generate music cover versions on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `generate-music-cover`, cover generation from a comple... | |
| Poyo Generate Persona Create a reusable music persona on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `generate-persona`, completed music task ids, audio... | |
| Poyo Get Timestamped Lyrics Retrieve timestamped lyrics on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `get-timestamped-lyrics`, synchronized lyrics, word timi... | |
| Poyo Gpt 4o Image Use PoYo AI GPT-4o Image through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants to generate or edit media with this model fami... | |
| Poyo Gpt 5 2 Chat GPT-5.2 chat completions on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions`; use for `gpt-5.2`, OpenAI-compatible chat payloads, system prompts,... | |
| Poyo Gpt 5 4 GPT-5.4 chat completions on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions`; use for `gpt-5.4`, OpenAI-compatible chat payloads, coding help, re... | |
| Poyo Gpt 5 5 GPT-5.5 chat completions on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions`; use for `gpt-5.5`, OpenAI-compatible chat payloads, coding help, re... | |
| Poyo Gpt 5 6 GPT-5.6 Responses API integration on PoYo / poyo.ai via `https://api.poyo.ai/v1/responses`; use for `gpt-5-6-sol`, `gpt-5-6-terra`, `gpt-5-6-luna`, text and... | |
| Poyo Gpt Image 1 5 Use PoYo AI GPT Image 1.5 through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants to generate or edit media with this model fam... | |
| Poyo Gpt Image 2 GPT Image 2 generation and editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `gpt-image-2`, `gpt-image-2-edit`, text-to-image,... | |
| Poyo Grok Imageine Grok Imagine video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `grok-imagine`, text-to-video, image-to-video, 6s/10s... | |
| Poyo Grok Imagine Use PoYo AI Grok Imagine Video for short text-to-video and image-to-video generation with motion-style controls through the `https://api.poyo.ai/api/generate... | |
| Poyo Grok Imagine Image Quality Grok Imagine Image Quality generation and editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use when the user explicitly requests PoYo... | |
| Poyo Grok Imagine Video 1 5 Grok Imagine Video 1.5 image-to-video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `grok-imagine-video-1.5`, one sourc... |
22,451–22,500 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.