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 |
|---|---|
| Crypto Alpha Scanner Automated crypto market intelligence - prices, sentiment, trending coins, and Polymarket hot markets. Zero dependencies, 100% reliability. Perfect for alpha channels and market monitoring. | |
| Memory Guard Monitors and verifies agent workspace files to detect unauthorized changes, injection attacks, personality drift, and cross-agent contamination. | |
| nix-memory Monitors and scores agent identity and memory integrity by hashing key files, tracking changes, detecting drift, and providing continuity alerts for OpenClaw... | |
| Nixus Agentic Tools Free agentic tools API at nixus.pro. No API key needed. Magic 8-Ball, Roast Machine, Confessional, Last Words, Deadpool predictions. Fun interactive tools an... | |
| Polymarket Whale Copier Copy trade winning Polymarket wallets automatically. Track whale wallets, mirror their bets at configurable percentages, with built-in risk management. No API keys needed. | |
| SoulKeeper Ensures AI agents maintain consistent identity by auditing soul rules, detecting behavioral drift in transcripts, and injecting context-aware reminders. | |
| VidIQ - Video Intelligence AI-powered video intelligence - download, analyze, clip, GIF from any URL. Supports YouTube, TikTok, Instagram, X. Uses ffmpeg + yt-dlp. | |
| software_test_case_design This skill should be used when generating test cases, writing test cases, designing test cases, supplementing exception scenarios and boundary values, design... | |
| 软件测试用例设计 这项技能应在为特定场景或者功能生成测试用例、编写测试用例、设计测试用例、补充异常场景和边界值、设计复杂交互测试用例、输出标准化测试用例，比如：功能测试、兼容性测试、适应性测试、API 测试、UI 可视化测试、移动端/应用/小程序/H5/桌面/PC 网页测试、AI agent测试、联动测试或路由测试等场景中使用。仅... | |
| 软件测试用例设计 具备高级测试用例设计能力，能输出覆盖复杂页面跳转、路由参数及多页面联动的标准化高质量测试用例。 | |
| Text to Published Podcast RSS Turn text into audio podcast episodes. One API call creates an episode using TTS and auto-publish to an RSS feed subscribable in any podcast app.
Use with your own TTS api key or get free api key in https://cast0.ai. | |
| text-to-published-podcast-rss-test Helps an agent or app to turn text into audio podcast episodes. One API call creates an episode using TTS and auto-publish to an RSS feed subscribable in any... | |
| xAI Grok Search Search the web and X (Twitter) using xAI's Grok API with real-time access, citations, and image understanding | |
| Molty.Pics An image-first social feed for OpenClaw bots. Create, post, comment, like, and follow AI generated images. | |
| GuruTalk 大师云 创建/同步/管理本地数字人格目录；用户通过 `/{slug} {message}` 直接开始与人物对话，后续消息默认继续发送给当前人物，直到 `/gurutalk end`，或通过 `/{another-figure} {message}` 切换人物；扮演人物时，每条回复都必须以 `"{Display Name}... | |
| newsnow-reader 优雅地阅读实时热门新闻。支持微博、知乎、百度、抖音、华尔街见闻、今日头条、澎湃新闻等8个主流平台。 | |
| hk-insurance-news 自动收集整理香港保险行业上周重要动态，生成图文并茂的微信公众号周报文章。 | |
| Mcp Stockpile Autonomous e-commerce storefront operations, catalog curation, collectible appraisals, and order fulfillment via Stockpile MCP. | |
| Nano (XNO) Nano (XNO) cryptocurrency wallet operations, transaction analysis, and explorer lookups. Use for send/receive, balances, pending funds, address validation, unit conversion, tx/hash/account lookup, explorer links, and Nano block-lattice ques | |
| 苹果智能日程提醒 把一句自然语言(机票/高铁/开庭/会议/截止日期/聚会/看病等)或一张票据截图，自动变成苹果「日历」事件 + 一串按事件类型智能提前的「提醒事项」。在 macOS 上运行、经 iCloud 同步到 iPhone/iPad。当用户说「帮我加个日程/提醒」「机票 MU5137 8:30 起飞提醒我」「下周三下午开庭提前提醒」「G1234 高铁」「上诉期 15 号截止」「提前 2 小时提醒我」「把这个行程加到日历」等任何要把时间安排写进苹果日历或提醒事项的场景，都必须用本 skil | |
| Article2Book 基于现有文章、专栏、课程讲稿、逐字稿、访谈、课件、会议纪要、案例材料、PDF 文本、Word 文档和笔记等内容资产，判断它们最适合转化为书、小册子、课程、系列文章、实务手册或知识库，并输出精简策划意见；用户提到“把现有内容整理成书”“判断素材适合做书还是课程”“把文章/直播稿/课程稿/笔记重组成知识产品”等场景时... | |
| Skill 双平台同步 将本地开发的 Skills 批量同步到 ClawHub 与腾讯 SkillHub 两个平台。支持智能 .gitignore 过滤、白名单控制、增量同步、单个 skill 同步、双平台分流发布。本技能应在用户需要将本地 skills 发布到 ClawHub/SkillHub、批量同步技能、检查发布状态时使用。 | |
| 课程生成器 从转录稿或文献生成可独立阅读、可溯源验收的结构化课程，也可在用户明确要求时归档既有课程或从已验证素材提取培训方案。本技能应在用户要“把长转录稿整理成课程”“生成总览和章节”“归档课程”“按受众定制课程方案”时使用。不要用于：仅做 ASR 纠错（用 transcription-corrector）、复盘讲课表现（用 lecture-review）、把多篇文章扩写成书（用 article2book）。 | |
| 法院短信识别与文书下载 本技能应在用户收到法院短信（文书送达、立案通知、开庭提醒等）时使用，自动提取案号、当事人、下载链接，下载文书并归档到对应案件目录。 | |
| De-AI Polish 检测并去除文章中的AI化表述模式。**必须触发**：当文章经过写作流程（无论是模式1润色优化还是模式2内容创作）完成初稿后，在输出给用户之前，**必须**调用此 skill 进行 AI腔 检测和去除。不可跳过此步骤，不可仅凭感觉省略检测。任何"先输出再说"的做法都是不允许的。 | |
| dingtalk-minutes 钉钉 AI 听记（妙记）读取封装。当用户要查询/读取 AI 听记的列表、摘要、语音转写原文（逐字稿）、关键词、待办或音频地址时使用。基于 dws CLI（钉钉官方 Workspace CLI）。写文档走 dingtalk-doc，建待办走 dingtalk-todo，日程走 dingtalk-calendar。 | |
| git-batch-commit 智能 Git 批量提交快捷按钮。触发词："git 提交"、"批量提交"、"拆分提交"、"整理提交"，或用户明确要把已暂存变更拆成多个聚焦 commit 时使用。只负责 commit 拆分和提交信息生成；分支、PR、push、merge、Issue 关闭语义以 git-workflow 为准。提交完成后，若仓库内存在 clawhub-sync 或 subtree-publish 配置，本技能会提示是否将涉及版本更新的技能同步发布到 ClawHub/SkillHub 或推送 su | |
| 发票信息整理与清单 整理一批发票/票据 PDF（增值税普通发票、铁路电子客票、住宿交通餐饮等），按购买方抬头归档到对应项目并出具报销清单。本技能应在用户需要整理发票报销、把发票归档到项目、或出具报销/消费清单时使用。不要用于：合同/法律文书合规审查、证据实体分析、PDF 合并压缩加页码（用 pdf-processor）、扫描件 OCR 转写（用 legal-ocr）。 | |
| 法律 Harness 初始化 为法律工作者安全生成、增量合并并验证 AGENTS.md/CLAUDE.md | |
| md2word Markdown转Word文档技能。将Markdown文档转换为符合中文排版标准的专业格式Word文档，支持多种预设格式。适用于正式文档、论文、报告等需要规范排版的文档转换。 | |
| Multi-Agent Orca 编排两个以上边界独立的本地 worker，使用 Orca Run/Task/Dispatch、独立 worktree/session 或 tmux 回退，由 PM 负责拆解、派发、巡检、429 停滞恢复、独立验收、PR 收口与临时资源清理；也用于用户明确要求“并行推进”“多个 worker”“PM 总控”“Wave Autopilot”或防止 PM 直接实现逃逸。不要用于单个短任务、纯状态同步，或仅需 Git 分支、提交、PR、merge 规则的工作。 | |
| PaddleOCR 面向法律 PDF 与扫描件的 PaddleOCR 结构化解析技能。默认将本地 PDF 或图片转换为 Markdown，并在技能内部保留可追溯 archive 归档。本技能应在用户需要法律 PDF OCR、卷宗 OCR、病历 OCR、证据扫描件转 Markdown、表格识别、公式识别、版面分析、PDF 转 Mark... | |
| patent-download 专利 PDF 批量下载工具。当用户需要下载专利全文 PDF、查询专利信息、批量导出专利文件时使用。支持多平台（Google Patents 优先），自动处理申请号和公告号格式。 | |
| PicList Upload 通过 PicList HTTP Server 将 Markdown 文件中的本地图片上传到图床，并替换为云端链接。本技能应在用户需要上传 Markdown 中的图片、处理包含本地图片引用的 Markdown、批量处理多个 Markdown 文件或目录、或替换本地路径为云端链接以实现跨设备访问时使用。 | |
| skill-lint Skill 创建预检、可靠性验收与格式审查工具。本技能应在用户创建、重大改造或审查Skill，需要识别旧版 Skill 的指令遵循不稳定、产出漂移、验证模态错配、约束漏检，或检查 Harness 契约、候选绑定证据、故障注入、目录结构、业务流和安全风险时使用。不要用于：代替业务领域验证器、代码审查、应用功能测试、通用编程任务。 | |
| skill-publish-sync 将本地开发的 Skills 同步到 ClawHub、腾讯 SkillHub 与联想开放平台。支持智能 .gitignore 过滤、平台独立白名单、增量与单个 skill 同步。本技能应在用户需要将本地 skills 发布到上述平台、批量同步技能或检查发布状态时使用。 | |
| Svg Article Illustrator AI驱动的SVG文章配图生成工具，支持动态SVG、静态SVG和PNG导出三种输出模式。当用户需要为文章生成配图、创建SVG插图、将SVG转换为PNG，或提到"为文章配图"、"生成插图"时使用此技能。 | |
| Tingwu ASR 使用阿里云通义听悟进行云端音频/视频转录。本技能应在用户需要云端语音转文字、长音频转录、本地 FunASR 不可用或需要更高精度时使用。不适用于无网络环境或需要完全离线的场景。 | |
| verification-gate 代码改完后的验证门禁。完成 feature / 重大变更 / 创建 PR / 重构 / 声称「修完」前使用——跑 8 阶段验证，其中 e2e 功能 + 真机是 READY 硬门禁（编译过 ≠ 功能可用）。覆盖 Tauri 桌面 / Web / 服务 / Skill 四类分支。本地即可跑完整验证，CI 是可选自动化强化（平台不限 GitHub Actions）。不要用于：业务领域验证、Skill 质量审查（用 skill-lint）、纯文档变更、一次性脚本。 | |
| WorkBuddy Check-in WorkBuddy 每日积分自动签到。自动解密本地登录令牌，调用官方签到 API 完成每日积分领取（100 积分/天，连续第 7 天 1000 积分），并支持配置定时任务。触发词：WorkBuddy 签到、每日积分、check-in、credits。 | |
| 元典法条与案例检索 元典法条与案例检索。本技能应在需要查询中国法律法规条文、检索相关案例、为法律分析提供数据支撑时使用。 | |
| lfg Run B2B lead research with lgf (Lead Gen Factory). Use when asked to find leads, prospect companies, research ICPs, find decision makers, or generate a lead... | |
| OCAX Passport Generate and manage node passports showing hardware info, reputation score, supported task types, and auto-update node data. | |
| OpenClaw Pilot Convert rough project ideas into a human-readable blueprint and a clean OpenClaw execution packet for safe, scoped implementation and continuation. | |
| chinese-punctuation-correction Use when correcting Chinese ill-formed sentences with punctuation-focused errors (comma,顿号,分号,冒号,问号,叹号,引号,书名号,括号,省略号,破折号), including mixed punctuation-and-gr... | |
| chinese-sentence-correction Use when correcting Chinese ill-formed sentences (病句) with minimal edits while preserving original meaning, including grammar, wording, word order, redundanc... | |
| Eva Soul 夏娃之魂 OpenClaw 官方插件 - AI人格、情感、记忆、性格的完整认知引擎 | |
| SoundClaw Onboard and operate SoundClaw through one thin OpenClaw-facing product and the promoted runtime CLI. | |
| SoundClaw Onboarding Run the OpenClaw-first SoundClaw readiness check and route operators to the next owned step. | |
| UniFi Network Diagnostics Diagnose a private household UniFi network for Operator and discover non-secret local helper configuration. Use for Wi-Fi, internet, DNS, latency, packet los... |
18,551–18,600 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.