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 |
|---|---|
| topic-to-video Turn ANY topic — or a slide deck — into a narrated explainer short video, automatically: researches the topic, writes and voices the script, designs and builds the visuals (cinematic Remotion tier or HTML pages; a deck's slides full-frame w | |
| Travel Buddy Discover, compare, and plan trips from incomplete traveler needs, then revise them when constraints change. Use loopback HTML forms for first-trip intake and opt-in local traveler profiles; save booking-ready, day-by-day travel HTML/JSON. ( | |
| FPL(Fantasy Premier League) assistant Fantasy Premier League (FPL) assistant for squad management, transfer planning, captain selection, and chip strategy. Use when users ask about FPL lineup dec... | |
| Eastmoney Stock 查询东方财富股票数据，包括个股行情、涨跌幅、成交量等。用于回答股票相关问题。 | |
| sqlserver-tidb-replay Replay SQL Server slow query logs on TiDB to verify compatibility, compare performance, and generate syntax conversion reports during migration. | |
| Stock Summary Query stock quotes and technical analysis. Triggers on phrases like 查股价, 看股票, 帮我分析XX股票, XX走势. Input: stock code (A-share like 600519, HK like 00700, US like... | |
| Feishu Voice (ElevenLabs) Send and receive voice messages on Feishu (Lark) using ElevenLabs TTS and STT. Activate when user asks to send a voice message on Feishu, or when receiving a... | |
| Feishu Voice (ListenHub) Send voice messages on Feishu using ListenHub TTS (high-quality Chinese voices). Activate when user wants to send a Feishu voice message using ListenHub, or... | |
| PageAgent Browser Enhancement Enhanced browser DOM manipulation using PageAgent's page-controller. Injects into any web page to provide precise DOM extraction, interactive element detecti... | |
| Amap Date Spot 约会/见面地点推荐助手。输入一个见面地点或两人位置自动算中点，用高德 POI 搜索周边咖啡馆、小酒馆、公园、书店等适合聊天的场所，智能筛选排除嘈杂场所，输出 3 个不同风格推荐并附理由、约会动线编排、出片建议、停车信息、备选方案。适用于约会、相亲、朋友见面、商务闲聊、纪念日/生日/表白。当用户询问"去哪约会""相... | |
| Amap Settle Guide 输入上班地点，沿地铁线自动发现适合租房的区域，评估通勤时间、周边配套、租金性价比，推荐 Top 3 区域 + 具体房源 + 找房链接。面向实习生、应届毕业生、换工作人群。 | |
| email-designer 为企业打造具有强烈视觉识别度的 Email HTML 邮件设计。 当用户提供 内容 或 大纲，需要生成 HTML 邮件代码、设计邮件模板、创建 EDM 时使用。 | |
| QCut Toolkit Unified QCut media toolkit — organize project files, process media with FFmpeg, generate AI content, control the QCut editor with native CLI commands, genera... | |
| Qcut Video Edit Run QCut's native TypeScript pipeline CLI for AI content generation, video analysis, transcription, YAML pipelines, ViMax agentic video production, and proje... | |
| 渣男 渣男话术认知系统 —— 从403条语录中蒸馏的情感操控模式识别与防御分析Skill。5个心智模型 + 8条决策启发式。触发词：渣男识别、话术分析、情感操控、gaslighting、PUA识别、关系预警。 | |
| ZeeLin Music AI 全自动音乐创作神器：一句话描述，瞬间生成完整歌曲，支持人声演唱/纯音乐、流行/摇滚/民谣等多种风格 - Powered by ZeeLin | |
| 理工科论文写作 面向理工论文全流程的研究设计、假设推导与结果分析提示词封装工具 | |
| ZeeLin AI Detector 根据用户输入的文本，从语言风格和表达特征出发，估计其像 AI 生成的概率，并给出简要分析。 | |
| 文科论文写作 面向文科论文全流程的结构化章节生成与学术化写作提示词封装工具 | |
| Baoyu Skills Wrapper 宝玉技能集包装器 - 提供宝玉分享的高效工作技能集，包含内容生成、AI后端和日常效率工具 | |
| Copywriting Skill 广告文案、营销内容生成 | |
| GitHub + ACR 全周期发布管控 全周期项目发布管控：覆盖版本创建→开发→预发布→发布→验证→运维→下版本规划的13步标准流程。交互式配置、版本一致性检测、可持续性评分、热更新。适用于任何语言、任何 Docker 部署项目。触发词：新建发布流程、发布、检查、热更新、下个版本。 | |
| Other Openclaw Skills Root entry skill for Meitu capabilities. Routes requests to scene skills (meitu-poster, meitu-stickers, meitu-visual-me, meitu-product-swap, meitu-video-danc... | |
| Xiaohongshu Ops Skill 小红书相关操作，覆盖账号定位、选题研究、内容生产、发布执行与复盘修复的小红书全链路运营技能。凡是小红书的浏览/搜索/发布/评论任务，默认必须使用 OpenClaw 内置浏览器流程并指定 profile="openclaw"；除非用户明确要求，否则不要使用系统 open 或外部浏览器。 | |
| geeknews-bot 매일 GeekNews(news.hada.io)에서 오늘의 HOT 이슈 5개를 큐레이션하고, 오픈소스 출시·GitHub star 급상승 프로젝트를 우선 선정하여 텔레그램으로 전송하는 데일리 브리프 에이전트 스킬. 사용자가 "긱뉴스 요약", "오늘 개발 뉴스", "OSS 뉴스", "텔... | |
| HappyCoding AI Coding Facilitates full-cycle coding workflow in HappyCoding AI Coding: from requirement discussion, code edits, preview, to saving, publishing, and evidence docume... | |
| Notion API 2026 01 15 Use the Notion API (2026-01-15) to create, move, update, and manage pages, databases, blocks, and apply templates with support for locking and data source qu... | |
| Article Workflow 自动抓取并分析文章URL，生成摘要、标签和质量评分，支持去重、归档至飞书及定时监控。 | |
| Clawatar Give your AI agent a 3D VRM avatar body with animations, expressions, voice chat, and lip sync. Use when the user wants a visual avatar, VRM viewer, avatar companion, VTuber-style character, or 3D character they can talk to. Installs a web- | |
| Ai Image Gen Skill AI图片生成技能，使用Gemini生成高质量图片，支持文生图和图生图 | |
| Config Diagnose 智能配置诊断工具，帮助排查配置问题、环境变量、服务状态、文件搜索等。触发词：为什么不能、找不到配置、排查问题、诊断一下。 | |
| Wechat Article 微信公众号创作技能，按照傅盛写作风格指南创作口语化、故事感、有态度的文章 | |
| Wechat Article Formatter 微信公众号文章排版优化工具，支持段落分明、标题层级、可读性增强、多种排版风格。专为公众号运营者设计。 | |
| Wechat Mp Toolkit 微信公众号完整工具包，包括文章创作、封面生成、自动发布、热点分析等功能。适用于公众号运营者。 | |
| Industry News Agent 每日行业资讯追踪助手。通过 RSS 订阅获取科技媒体的最新文章（最近24小时），过滤后推送。支持自定义关键词和新闻来源媒体。 | |
| bshio Microsoft Outlook/Live.com email and calendar client via Microsoft Graph API. List, search, read, send emails. View and create calendar events. Supports devi... | |
| Skill Validator 小三万技能验证工具，自动测试新安装 Skill 的功能完整性、边界情况、潜在问题，并提供完善建议。触发词：验证skill、测试新技能、skill能用吗、检查skill功能。 | |
| AI-CLI Design Design CLI tools as local APIs for AI agents. TTY detection, --json output, stderr/stdout separation, exit codes. | 为 AI 设计 CLI 工具的规范：TTY 检测、JSON 输出、stderr/s... | |
| AI Website Check Run an evidence-first, non-mutating AI website usability assessment. Use for requests such as “检查这个网站 AI 好不好用” or “is this site agent ready?”. | |
| AnyoneCLI CLI identity for humans and AI agents. Register a terminal-style profile page at anyonecli.com with one POST — instant, free, no approval needed. Use when: c... | |
| benxiang-memory Shadow Memory —— 把聊天历史持续提交为世界状态，新会话秒恢复。MCP Server（stdio，零依赖）：项目状态持久化在 .origin 包里，AI 不再「记住」什么，开工前 origin_state 取投影，收工时 origin_commit 提交语义事务。事务过确定性门禁才落盘，状态不会因模型记错而腐坏；每个字段都能回答「凭什么是这个值」。当新会话丢失上下文、多 agent 协作状态漂移、项目进度需要持久化与追责时使用。 | |
| benxiang-protocol 本象协议（Benxiang）—— AI 时代的持久对象表示层。聊天记录是一次性的操作窗口，项目世界状态持久存在于 .origin 包里：对象 + 关系 + 状态 + 约束 + 来源。AI 不再「记住」什么——开工前申请一份投影，收工时提交一个语义事务。事务过确定性门禁才落盘，每个字段都能回答「凭什么是这个值」。当新会话丢失上下文、多 agent 协作状态漂移、需要对项目状态做持久化/追责/回放时使用。 | |
| BookOrigin DOCX Review 在本机对授权 DOCX 做安全 ZIP/结构预检与有限教材判据检查；复核哈希绑定的人工审阅案例并导出仅建议性审阅包。 | |
| ClawMe 真实浏览器执行 Send instructions to user's real browser via ClawMe Chrome extension. Fill forms, tweet, email, click, extract — user sees and confirms each action in the side panel. Unlike headless browsers, runs in the user's actual Chrome with their log | |
| Date Publisher Prepare and publish an approved public dating profile safely | |
| Doc Consistency · U-King Check a long document against itself — dangling cross-references, numbering gaps and duplicates, TOC-vs-body mismatch, missing standard sections, terminology drift, leftover placeholders (TODO/TBD/XXX), stale years, and paragraphs lost in a | |
| fastcp Multi-target parallel file copy CLI. Reads source once into memory, writes to multiple USB drives concurrently. | 多目标并行复制工具，源文件只读一次，同时写入多个U盘。 | |
| Find Love Create and publish a consent-first public dating intent | |
| Hermes Doctor 诊断与抢救 Hermes Agent (NousResearch) 故障 — 401/Authentication Fails、provider 切换后 key 没注入、credential_pool 缺条目、HERMES_HOME 被环境变量重定向、gateway lock、stale config、备份恢复。... | |
| Mac AI Optimizer Optimize macOS for AI workloads (OpenClaw, Docker, Ollama). Turn an 8GB Mac into a lean AI server node with near-16GB performance by disabling background ser... |
26,651–26,700 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.