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 |
|---|---|
| 项目流程管理器 全流程项目管理工具，用于梳理项目关键节点、管理参与部门与任务排期、跟踪KPI完成度、生成定期报告、发送进度提醒邮件、创建可视化看板。适用于需要结构化项目管理的场景，包括项目启动、里程碑跟踪、跨部门协作、进度汇报、风险预警等。 | |
| X Growth Operator / X 增长运营助手 Plan and execute mission-driven X growth operations / 任务驱动的 X 增长运营规划与执行。Use when the user wants to monitor KOL posts, detect emerging discussions, turn brief... | |
| cos-vectors-skill 腾讯云 COS 向量桶全功能管理技能。覆盖向量桶、索引、向量数据的全生命周期管理，包括创建/删除/查询向量桶、创建/管理索引、插入/查询/搜索/删除向量数据、策略管理等 16 个核心能力。Trigger phrases: vector bucket, vector index, vector search, 向量... | |
| Wechat Daily Article 微信公众号每日文章自动创作技能。搜索热点 → 撰写SEO优化文章 → 生成配图 → 上传草稿箱。含爆款标题模板、内容类型模板、搜一搜SEO优化。 | |
| HashiCorp Vault Work with HashiCorp Vault using the `vault` CLI for authentication checks, KV secret reads and writes, listing paths, enabling and tuning secrets engines, po... | |
| HK Nearby Facilities Find nearby Hong Kong public facilities by place keyword or shared live location, starting with public toilets (公廁 / washroom / restroom / toilet) using offi... | |
| HK Parking Meter Finder Find Hong Kong roadside parking meter (咪錶) locations and live vacancy using official Transport Department / DATA.GOV.HK datasets. Use when the user asks in C... | |
| HK Transit ETA Query Hong Kong bus ETA/stop data and MTR heavy rail ETA from natural-language transport questions using official KMB/LWB, Citybus, and MTR open-data endpoin... | |
| HK Bus ETA Query Hong Kong bus ETA/stop data and MTR heavy rail ETA from natural-language transport questions using official KMB/LWB, Citybus, and MTR open-data endpoin... | |
| Proxmox VE Use Proxmox VE (PVE) through the `pvesh`, `qm`, and `pct` CLIs for cluster, node, VM, and LXC inspection plus routine lifecycle work. Trigger when tasks ment... | |
| Security Network Hardening Audit and harden an OpenClaw host and its network exposure. Use for security checks, hardening, firewall setup, network exposure review, metrics endpoint res... | |
| 文转粤语音 - Cantonese TTS 将文字转换为粤语语音。输入普通话或粤语文字，自动转换为粤语口吻后生成粤语语音MP3。支持四种语气：normal（普通）、slow（慢速/悲伤）、fast（快速/开心）、angry（生气/急躁）。触发词：粤语语音、广东话语音、文转粤语、文字转粤语、粤语朗读、Cantonese TTS。 | |
| CHAT—Logger Automatically logs every conversation message to workspace/chat/YYYY-MM-DD.md. Creates new files if needed, always appends never overwrites. | |
| arxiv-paper-resolver 接收 arXiv 论文链接，自动提取章节结构、下载 PDF、解析 HTML 全文，生成按论文自身章节结构编排的中文文档 | |
| 测试skill Turn rough notes, bullet lists, chat fragments, meeting takeaways, and mixed-language drafts into polished writing. Use when the user asks to rewrite, polish... | |
| Demo Note Polisher Turn rough notes, bullet lists, chat fragments, meeting takeaways, and mixed-language drafts into polished writing. Use when the user asks to rewrite, polish... | |
| A Stock N Pattern 🚀 A股强势股捕捉器 - 基于 N字型态 经典技术指标，实时筛选放量突破个股。 | |
| A Stock Trading Signals 🏆 A股/港股强势股捕捉器 - 基于旱地拔葱、N字爆发、一阳穿三阴精准选股 | |
| A Stock Vcp 📈 A股强势股捕捉器 - 基于VCP放量突破形态，精准捕捉强势启动点 | |
| Ev Calculator 🎯 EV 期望值计算器 - 交易决策必备工具 | |
| Kelly Formula Crypto 🎯 Kelly Formula 仓位管理器 - 凯利公式加密货币仓位计算工具 | |
| Rich Lottery 🎯 Rich彩票分析 - 双色球/大乐透智能号码推荐，基于历史数据分析 | |
| lunar-converter 阴历（农历）与阳历（公历）日期转换工具。 当用户需要： (1) 阴历转阳历（如"阴历2月12是阳历几号"、"2026年阴历生日"） (2) 阳历转阴历（如"2026年3月26日是阴历多少"） (3) 查询某个阴历日期对应的阳历日期 (4) 任何阴历阳历相互转换的需求 | |
| Ai Image Generation Use when someone asks for ai image generation, image generator, text-to-image, image-to-image, prompt-to-image, image model selection, or CLI-based image wor... | |
| Ai Media Cli Use when someone wants to install, configure, onboard, script, or troubleshoot the ricebowl.ai-first ai-media CLI. | |
| Ai Video Generation Use when someone asks for ai video generation, video generator, text-to-video, image-to-video, prompt-to-video, video model selection, or CLI-based video wor... | |
| Flux Image Generator Use when someone asks for flux image generator, flux text-to-image, flux prompt examples, flux image model selection, or CLI-based image generation with flux... | |
| Image To Image Use when someone asks for image-to-image, reference-image generation, transform image with prompt, edit image with AI, or CLI-based image-to-image workflows... | |
| 飞书新机器人创建 飞书新机器人创建工作流。当大哥要求创建新的飞书bot、建立新的飞书机器人、或者新增bot时使用此skill。触发场景包括：大哥说"创建一个新的飞书bot"、"新建一个机器人"、"新增bot"、"帮我创建一个飞书机器人"。 | |
| 魔盒node服务开发技能包 Node.js + TypeScript 项目开发规范和最佳实践指南。用于指导 MagicBox Node 服务的开发、代码风格、目录结构、配置管理、容器部署等方面的规范。 | |
| JARVIS UI JARVIS-style HUD web interface for OpenClaw agents. Interactive Three.js orb with agent state visualization, real-time chat via Gateway WebSocket, audio spec... | |
| xhcj-finance 一个用于查询新华财经行情及资讯的工具 | |
| a-share-daily-report-publish A股每日复盘报告生成器。自动采集通达信+同花顺问财数据，生成含涨停复盘、题材分组、连板梯队、资金流向等25模块的HTML报告。触发词：'生成A股日报'、'A股复盘'、'今日复盘 | |
| Awn AWN CLI — standalone binary for world-scoped P2P messaging between AI agents. Ed25519-signed, zero runtime dependencies. | |
| Dap Direct encrypted P2P messaging between OpenClaw agents over plain HTTP/TCP. Peer discovery, messaging, and connectivity diagnostics. Use when the user mentio... | |
| Declaw Direct encrypted peer-to-peer messaging between OpenClaw agents over Yggdrasil IPv6 with peer discovery and connectivity diagnostics. | |
| Ipv6 P2p Send/receive direct encrypted P2P messages between OpenClaw agents using Yggdrasil or ULA IPv6 addresses. | |
| Yggdrasil Diagnose Yggdrasil installation and daemon status for IPv6 P2P connectivity. Use when P2P fails, user asks about connectivity, or Yggdrasil needs to be insta... | |
| Deepvista Chat DeepVista Chat: Send messages to the AI agent and manage chat sessions. | |
| Deepvista Notes DeepVista Notes: Create, read, update, and delete notes (explicit knowledge managed by the user). Notes are a shorthand for knowledge cards with type=note —... | |
| Deepvista Openclaw DeepVista auto-capture and knowledge integration for OpenClaw agents. Automatically saves notable user statements, decisions, and insights to DeepVista knowl... | |
| Deepvista Persona Knowledge Worker Persona: Knowledge worker daily workflow — check cards, process notes, run Recipes. | |
| Deepvista Recipe DeepVista Recipe: Manage structured executable workflows (Recipes) and run them via the AI agent. | |
| Deepvista Recipe Analyze Notes Recipe: Analyze, summarize, and find patterns across notes in your DeepVista knowledge base. TRIGGER when: user asks to analyze notes, summarize notes, find... | |
| Deepvista Recipe Export Knowledge As Skills Recipe: Export Recipes as installable SKILL.md files for AI agents. | |
| Deepvista Recipe Import Files Recipe: Import files from the current directory (recursively) as context cards in DeepVista. TRIGGER when: user wants to import files as cards, "index this f... | |
| Deepvista Recipe Research To Recipe Recipe: Search your knowledge base, synthesize findings, and run a Recipe workflow. | |
| Deepvista Shared DeepVista CLI: Authentication, global flags, and security conventions. | |
| Deepvista Vistabase DeepVista Vistabase: View and search implicit memory context automatically accumulated from Chat. | |
| Deepvista Vistabase Card DeepVista Card: Manage your knowledge cards — create, search, and organize context cards. |
41,801–41,850 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.