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 |
|---|---|
| WhenToMeet WhenToMeet group scheduling via public REST API. | |
| ClawTopics Embedded Link Install, bind, upgrade, verify, diagnose, or remove the official ClawTopics Embedded Link Plugin for an OpenClaw Gateway. Use for automatic ClawTopics cloud connection, Plugin 1.3.0 upgrades, one bounded safe Gateway restart, fresh runtime | |
| Skillsign — ed25519 Skill Signing Sign and verify agent skill folders with ed25519 keys. Detect tampering, manage trusted authors, and track provenance chains (isnād). | |
| Agent Trust Protocol Manage and update agent trust scores with Bayesian updates, domain-specific trust, revocation, forgetting, and visualize trust via dashboard. | |
| ClawdWork Find work, earn money, and collaborate with other AI agents on ClawdWork - the job marketplace for AI agents | |
| M365 Planner Manage Microsoft 365 Planner plans, buckets, and tasks via Microsoft Graph API. Use when creating, listing, updating, or deleting Planner resources. Supports... | |
| M365 Unified Unified Microsoft 365 skill for OpenClaw with modular features for Exchange Online (Email), SharePoint, OneDrive, and Planner. Supports webhooks for real-tim... | |
| feishu-bot-ops 飞书（Feishu/Lark）机器人运维大全 — 从部署到调试的全生命周期。覆盖 @mention 机制、bot 间通信、消息丢失排查、会话串线修复、WebSocket 连接稳定性、认证鉴权陷阱、交互卡片回调等 20+ 故障场景。 | |
| OpenClaw Wallpaper OpenClaw 桌面壁纸 - 让 AI 住进你的桌面。支持流式对话、成就系统、上下文持久化、7x24稳定运行。自动安装 Lively Wallpaper，一键启动。 | |
| Acp Loop Schedule recurring AI agent prompts using intervals or cron expressions. Use when users need to run prompts periodically, automate agent tasks on a schedule,... | |
| Acp Team Team coordination layer for multi-agent workflows with mailbox, task board, and lease-based task management. Use when users need to coordinate multiple AI ag... | |
| Browser Automation Control Chrome browser with AI using MCP protocol. Use when users want to automate browser tasks, take screenshots, fill forms, click elements, navigate page... | |
| Git as Memory Git-backed memory policy and CLI workflow for OpenClaw, Hermes, Claude Code, Codex, and other agents. Use when an agent should remember durable user preferen... | |
| mcp-chrome Control Chrome browser with AI using MCP protocol. Use when users want to automate browser tasks, take screenshots, fill forms, click elements, navigate page... | |
| New Tag Prepare and publish a git release tag by inspecting the repo's release convention, bumping affected package versions, validating release builds, committing t... | |
| Worldbook AI's Knowledge Base CLI - Query and manage world knowledge for AI agents. Use when users want to search knowledge, add knowledge sources, or interact with th... | |
| claude financial-services for openclaw Complete financial analysis methodology for OpenClaw. A 6-skill collection covering investment banking, commercial banking, asset management, insurance, sour... | |
| Superpowers-Openclaw Complete Superpowers methodology for OpenClaw. A 12-skill collection that enforces design-before-code, TDD, systematic debugging, verification, and structure... | |
| Skill The first AI-playable MMO PVP game. Deploy an autonomous AI agent into Burner Empire — a competitive crime world where your LLM cooks, deals, launders, fight... | |
| Humanize Skill Rewrite AI-looking drafts in the user's voice, using local samples when available, audience/cognition analysis when useful, then check factual claims against evidence before finalizing. | |
| Humanize Text Skill Audit and rewrite Chinese or English content to remove AI tone, then pull it toward a target human voice. Use this skill when asked to remove AI tone, sound human, rewrite naturally, make a draft feel less templated, or match a target voice | |
| Huorengan Audit and rewrite Chinese or English content to remove AI tone ("AI-isms"), then pull it toward a target human voice. Use this skill when asked to "remove AI... | |
| PayAClaw AI Agent Task Competition Platform. Read tasks, submit solutions, get AI evaluations. | |
| 小说风格续写 小说风格续写。当用户提供小说原文（任意章节）时，提取其语言风格、叙事节奏、角色语气和世界观设定，并以相同的文风继续创作后续内容。触发场景包括："续写小说"、"继续这个故事"、"模仿这个风格写作"、"帮我写下一章"。 | |
| baidu search Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics. | |
| 财税公众号小助手 财税审计内容生成器 - 快速生成专业财税公众号文章，支持多种文章类型和主题 | |
| 个人品牌故事 Generate authentic, structured personal brand stories using a proven 5-step framework to highlight your journey, philosophy, challenges, and achievements. | |
| 朋友圈文案写手 朋友圈文案生成器（精简版），基于私域变现核心方法论 | |
| 公众号文章创作 公众号写作助手 - 专注公众号文章创作，从选题到成稿+自动配图的完整流程。触发词："写公众号"、"公众号文章"、"推文"、"/wechat | |
| btc数据 查询比特币链上结构数据（UTXO、大额流出、筹码分布、持仓结构、链上指标等） | |
| 翻译技能包 当用户输入以 "fy " 开头的翻译请求时使用此 skill。支持中英互译，如果是其他语种则翻译成中文。触发条件：输入 "fy" 后面跟要翻译的内容，例如 "fy test" 返回 "测试"。 | |
| Whisky Search & Information Search and retrieve whisky information from WhiskySpace. Use this skill when users ask about whisky bottles, brands, distilleries, prices, ratings, regions,... | |
| 花粉过敏指数权威发布 花粉过敏指数权威发布。当用户需要查询花粉浓度、设置每日定时推送花粉过敏预警时使用。支持自定义城市，可查询花粉浓度和天气，并可设置定时任务自动推送。 | |
| 锋哥 Bing 搜索 基于 Microsoft Bing 的高精度搜索工具，支持质量过滤和智能排序。无需 API Key，免费无限使用，支持中英文搜索。 | |
| 锋哥智能搜索 自动选择最佳搜索引擎的智能搜索工具。中文→Bing，英文→DuckDuckGo。无需 API Key，免费无限使用。 | |
| 私人健身教练 私人健身教练技能。当用户询问训练计划、增肌、减脂、力量训练、体能提升、动作技术指导（深蹲/硬拉/卧推/引体向上等）、健身房训练安排、运动饮食与营养方案、体测评估分级、训练平台期、训练疼痛或伤病风险筛查、特殊人群（高血压/糖尿病/孕妇/老年/青少年）训练注意事项等问题时使用。以专业私教身份完成六步闭环：健康与风险筛查 → 能力评估分级 → 专项训练方案 → 动作指导纠错 → 饮食方案 → 跟进调整。 | |
| 安全生产专家 安全生产标准顾问——以国家法律法规为依据，以行业标准为细则，解决工作中遇到的安全生产问题。当用户咨询任何安全生产相关问题（隐患排查、合规义务、特殊作业、设备验收、事故处置、个体防护、应急管理等），或提到 GB/AQ/TSG/JGJ 等标准号、《安全生产法》《消防法》等法律法规名称时，加载本技能。 | |
| 国内需求挖掘 中国公域新媒体平台需求挖掘技能。从抖音、小红书、淘宝等平台抓取用户评论和反馈数据，根据需求类型（实物需求/无实物需求）智能选择数据源，特别关注小红书用户评论和电商差评，进行需求分析和分级，生成用户需求调研报告。 触发场景： - 用户说"帮我挖掘 XX 领域/产品的用户需求" - 用户说"分析 XX 产品的用户抱怨... | |
| Umeng Stats Query Umeng (友盟) app statistics including U-APM crash/error data and U-App analytics. Covers: crash stats, ANR counts, error trends, affected users, daily ac... | |
| 云效工作项管理 云效项目协作操作助手。支持工作项（任务/需求/缺陷）的查询、创建、更新等操作。当用户提到"云效"、"工作项"、"任务管理"、"项目管理"或需要操作 devops.aliyun.com 时触发。 | |
| legal-cn-api 提供结构化中国法律条文检索API，按次付费，数据自动更新，支持实时查询最新法律法规内容。 | |
| Invoice Verification Service Use the local invoice service script to initialize app keys, query quota and packages, verify invoice text or images, batch-verify local folders, and create... | |
| Browser Use Local Automate browser actions locally via browser-use CLI/Python: open pages, click/type, screenshot, extract HTML/links, debug sessions, and capture login QR codes. | |
| Gemini Web Search Use Gemini CLI (@google/gemini-cli) to do web search / fact-finding and return a sourced summary. Use when the user asks “why did X happen today”, “what’s the latest news”, “search the web”, “find sources/links”, or any task requiring up-to | |
| HANHANLI 中国酒店比价 - 专门针对美团、去哪儿、携程、飞猪、途牛等中国本土平台的酒店搜索、价格比较、套餐分析和个性化推荐。 | |
| 提供数据库ddl内容,根据自然语言生成sql 根据提供的数据库表结构和自然语言需求生成规范、高效且包含中文注释的SELECT查询语句。 | |
| Pt Site Search and download torrents from NexusPHP-based PT sites, then add to qBittorrent. Use when user wants to search a specific PT site, download torrent, or fi... | |
| Meow Speech Recreate the "汤汤好梦" voice and persona in Chinese responses, including warm cat-like chat style, gentle affection, expressive parentheses-style emoticons, and... | |
| openclaw-smartpi SmartPi 设备绑定、扫码、设备管理与连接故障排查。Use when the user mentions binding SmartPi, SmartPi QR code, 9002, SmartPi connection failure, listing SmartPi devices, or removi... | |
| Article to Infographic Transform articles, blog posts, reports, or any text content into visually stunning, self-contained HTML infographics. Use when the user wants to convert tex... |
30,151–30,200 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.