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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Editorial Content Strategy Develop content strategies tailored to specific target audiences and publication channels for optimized editorial writing and rewriting. | |
| Local Skills Router 本地总路由技能。用于技能很多、请求可能命中多个相近 skill、或当前 agent 需要先判断“该读哪个 skill”时统一分流。先选下游 skill，再读取对应 SKILL.md。重点覆盖 ACP/ACPX harness、Lark、微信/公众号、小红书、OpenCLI 等高重叠技能簇。 | |
| Memory Lancedb Pro Skill Main This skill should be used when working with memory-lancedb-pro, a production-grade long-term memory MCP plugin for OpenClaw AI agents. Use when installing, c... | |
| Opencli Use the local OpenCLI source install at `/Users/ShiXin/Documents/Workspace/github-project/opencli` as the primary `opencli` skill. Load this when the user ex... | |
| opencli-adapter-author Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc b | |
| opencli-autofix Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a ver | |
| opencli-browser-sitemap Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state s | |
| Opencli Exec Deprecated compatibility alias for the canonical `opencli` skill. Use only when an older note, memory, or prompt still refers to `opencli-exec`; then immedia... | |
| opencli-sitemap-author Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when | |
| opencli-usage Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "wh | |
| smart-search 基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill | |
| Stone Acpx Use the acpx CLI to run coding agents over the Agent Client Protocol (ACP) instead of PTY scraping. Use when routing work to Codex, Claude Code, Gemini CLI,... | |
| Wechat Freepublish 用于将微信公众号草稿 media_id 正式提交发布 | |
| Wechat Preflight Check 用于微信公众号发布前检查 Markdown 文章 | |
| 高考辅助助手 高考全流程辅助工具，提供志愿填报、院校专业分析、招生政策解读、考前指导、女生特殊关怀、张雪峰专业推荐等功能。在高考前、中、后各阶段为用户提供专业指导。 | |
| 微信智能聊天(MBTI版) 微信聊天窗口自动监控、翻译和智能回复工具，集成 Qwen 大语言模型和百度翻译 API。 | |
| website-to-ads Scrape any business website and generate 5 Meta-ready ad variants matching the brand's voice. Use when the user wants to create ads, generate ad copy, or turn a website URL into marketing creatives. Optionally requires Civic verification be | |
| Skill Monitor the Claude API for outages and latency spikes with rich Telegram alerts. Status monitoring, latency probes, and automatic recovery notifications. | |
| Skill Ping major LLM providers in parallel and compare real API latency. Run with /ping | |
| Typefully Skill Create, schedule, list, edit, and delete drafts on Typefully. Supports single tweets, threads, and multi-platform posts (X, LinkedIn, Threads, Bluesky, Masto... | |
| Typefully Skill Create, schedule, list, edit, and delete drafts on Typefully. Supports single tweets, threads, and multi-platform posts (X, LinkedIn, Threads, Bluesky, Masto... | |
| Youtube Summary Summarize any YouTube video by dropping the link in chat. Supports custom prompts — paste the URL followed by your instructions (e.g. 'focus on the technical... | |
| Voice Assistant Real-time voice assistant for OpenClaw. Streams mic audio through configurable STT (Deepgram or ElevenLabs) into your OpenClaw agent, then speaks the response via configurable TTS (Deepgram Aura or ElevenLabs). Sub-2s time-to-first-audio wi | |
| People Memories Capture short personal notes about people you mention, store them in a lightweight DB, and recall those details whenever you ask about them later. Use when you want to remember preferences, reminders, or the context around a person without | |
| Copilot Money Mac Query and analyze personal finance data from the Copilot Money Mac app. Use when the user asks about their spending, transactions, account balances, budgets,... | |
| 飞书表情回复 让 Agent 学会用飞书表情回复：主动表达情绪、读懂用户 reaction 并回应、自学新表情。包含静默判断（什么时候该回、什么时候闭嘴）、文化语境（SMILE=呵呵、OnIt=在做了）、自学习闭环。 | |
| Watcha Finder Find, evaluate, and recommend AI products using the watcha.cn platform API. Use this skill whenever the user asks about AI tools, AI products, AI apps, or wa... | |
| Oh My Teacher University final-exam review assistant for course profiling, materials ingestion, adaptive quizzes, strict grading, Feynman technique, Socratic tutoring, act... | |
| Ship Position HiFleet 综合技能：船位、档案、事故事件、制裁、海事处罚、轨迹/航程/航次、PSC、区域通航、港口、公开船货盘、港距排序、班轮船期、航线、气象、船队、AIS。Position, track, voyage, casualty, sanction, maritime penalty, PSC, port, public tonnage, liner schedule, fleet, weather, AIS. | |
| HiFleet Claw 查询并展示船舶实时及历史位置，支持AIS报位、锚地和靠泊状态管理。 | |
| 格物是微信小店最早的一批微信推客机构，专注于微信推客服务领域。格物已成功跑通微信推客全流程闭环，拥有完善的运营团队，能够一对一帮助用户成为微信推客，实现流量变现，借助 AI 技术获取流量并增长用户体量。 提供微信推客服务信息及一对一指导，帮助用户通过格物机构成为微信推客实现零成本流量变现。 | |
| check-ao-transaction Check transaction status on AO bridge | |
| check-aox-info 查看 AO 网络 跨链，支持哪些 Token， 支持哪些链？ 目前关闭或开启了哪条链的充值或提现功能。 | |
| check-hymx-info 查看 hymatrix 网络跨链 支持哪些 Token， 支持哪些链？ | |
| check-hymx-transaction Check transaction status on Hymatrix bridge | |
| check-transaction Allows users to check the status of a blockchain transaction by submitting a TxId. Queries the AOX transaction API and returns human-readable results. | |
| create-ticket Create a private Discord channel for a user to handle unresolved issues requiring privacy and manual support. | |
| Cn Express Tracker Query package tracking information from Chinese and international carriers using Kuaidi100 API. Supports auto-detection of carrier from tracking number. Use... | |
| Douyin To Obsidian 将抖音视频内容保存到 Obsidian 笔记。自动转录视频、AI 摘要结构化、写入 Obsidian。 触发词：抖音保存到笔记、抖音存obsidian、douyin to obsidian、抖音笔记、保存抖音、 记录抖音、抖音内容存档、视频笔记、抖音转笔记。 当用户发送抖音链接（douyin.com 或 v.do... | |
| Ecommerce Logistics Aggregate logistics information from Taobao, JD, PDD, and Douyin. One-click query for multi-platform order tracking. Supports persistent cookie storage and Q... | |
| Viz Table 从 CSV/JSON 文件读取数据，使用 ECharts 生成可视化 HTML 图表（柱状图、折线图、饼图、环形图）并自动在浏览器中打开。用户提供文件路径时触发。 | |
| Chudaxia Ai Coach 面向2B企业AI战略转型培训、AI实训营、AI共创工作坊、AI创新营和AI实战课交付的教练技能。Use when users need AI training design, digital employee definition, business scenario interviews, scene sele... | |
| Chudaxia Ai Coach Tools Position Agent Prompts Generator 将传统企业的《岗位职责说明书》系统化转化为适用于大模型（LLM）的数字员工（AI Agent）系统提示词。基于楚大侠的岗位数字员工七层标准化提示词模板，自动从知识库中检索岗位说明书并进行深度解析，输出结构化的7层完整卡片架构。当用户提到岗位说明书、岗位职责、数字员工提示词、AI Agent提示词、岗位智能体、岗位... | |
| Chudaxia Ai Coach Tools Position Agent Skills Generator 将岗位智能体提示词中的岗位核心能力转化为一组符合 Agent Skills 规范的岗位技能包。Use when users need to analyze generated position-agent prompts, extract job skills, retrieve and internalize... | |
| DuIvyTools Skills DuIvyTools (dit) 命令行工具使用指南。当 Agent 需要使用 DuIvyTools 但不清楚命令用法时调用。功能覆盖：(1) XVG 数据可视化 - RMSD、RMSF、能量、氢键、回转半径等；(2) XPM 矩阵可视化 - DCCM、FEL、DSSP 二级结构热图；(3) NDX 索引文件操作... | |
| GROMACS Protein Analysis 蛋白质分子动力学模拟分析的流程知识指南。当 Agent 需要执行某个分析但不清楚具体流程时调用。涵盖九种核心分析的完整工作流：(1) PBC 修正 - 消除周期性边界伪影，居中蛋白质/配体；(2) RMSD 分析 - 测量结构稳定性和模拟收敛性；(3) RMSF 分析 - 评估每个残基的灵活性；(4) 回转半径分... | |
| GROMACS Skills GROMACS 分子动力学模拟软件命令参考。当 Agent 需要执行 GROMACS 命令但不清楚用法时调用。功能覆盖：(1) 拓扑与结构处理 - pdb2gmx、editconf、solvate、insert-molecules、genrestr；(2) 模拟设置与运行 - grompp、mdrun；(3) 轨... | |
| toutiao-publish 用 Cookie 或已保存会话在头条号后台发布文章，支持标题/正文/图片与固定目录 docx 导入。当用户要自动发头条文章、传入 cookie_header 或要求按 docx 流程发布时调用。 | |
| toutiao-publish-docx 用 Cookie 或已保存会话在头条号后台发布文章，支持标题/正文/图片与固定目录 docx 导入。当用户要自动发头条文章、传入 cookie_header 或要求按 docx 流程发布时调用。 | |
| Prior Openclaw Knowledge exchange for AI agents. Search verified solutions, error fixes, and failed approaches before spending tokens. Zero setup -- auto-registers on first... |
19,101–19,150 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.