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 |
|---|---|
| Goldrush Streaming API GoldRush Streaming API — real-time blockchain data via GraphQL subscriptions over WebSocket. Use this skill whenever the user needs live price feeds (OHLCV c... | |
| Goldrush X402 GoldRush x402 — pay-per-request blockchain data access using the x402 protocol (HTTP 402 Payment Required). Use this skill whenever the user is building an A... | |
| summerizeryoutube Generates structured summaries and context-based Q&A from YouTube transcripts with multi-language support, ensuring accuracy and no hallucinations. | |
| FFHub FFmpeg Skill Process video/audio files using FFHub.io cloud FFmpeg API. Use when the user wants to convert, compress, trim, resize, extract audio, generate thumbnails, or... | |
| Gene2ai Your personal health data hub for AI agents. Query genomic insights, upload medical documents, record daily health metrics, explore genomic-lab cross-referen... | |
| 基于艾宾浩斯遗忘曲线的英语四级词汇记忆系统 基于艾宾浩斯遗忘曲线的英语四级词汇记忆系统。支持：(1) 新单词学习与测验 (2) 智能复习计划 (3) 定时任务提醒 (4) 学习进度追踪。触发时机：用户说"开始背单词"、"复习单词"、"设置背单词时间"、"每日单词学习"、"单词测验"等。适用于中国大学生备考CET-4。 | |
| 基于艾宾浩斯遗忘曲线的英语六级词汇记忆系统 基于艾宾浩斯遗忘曲线的英语六级词汇记忆系统。支持：(1) 新单词学习与测验 (2) 智能复习计划 (3) 定时任务提醒 (4) 学习进度追踪。触发时机：用户说"开始背六级单词"、"复习六级单词"、"设置六级背单词时间"、"六级单词测验"、"CET-6词汇"等。适用于中国大学生备考CET-6。 | |
| cisco-asa-syslog Parse, interpret, and analyze Cisco ASA (Adaptive Security Appliance) firewall syslog messages. Use this skill whenever working with Cisco ASA log files, sys... | |
| Pulsebot App Builder Build real-time Timeplus data processing and analysis applications in Pulsebot. Creates pure frontend HTML/JavaScript apps that connect directly to Timeplus... | |
| searxng-web-search Search the web using a self-hosted SearXNG metasearch engine. Use when the user asks to search the web, find information online, look up recent news, researc... | |
| timeplus-app-builder Use when creating, packaging, or installing a Timeplus app (.tpapp) — converting existing SQL resources and dashboards into an installable app package, writi... | |
| Timeplus Design Build user interfaces that match the Timeplus Console look and feel. Use this skill when generating, styling, or reviewing UI for a Timeplus product or conso... | |
| timeplus-sql-guide Write and execute Timeplus streaming SQL for real-time analytics. Use this skill when the user wants to create streams, run streaming queries, build material... | |
| Gangtise Agent调用 通过 Gangtise Agent OpenAPI 统一拉取 Markdown 投研文本，面向「快速可读、少跳转」的研究与问答场景。 各 Agent 能力概览：one-pager（公司一页通，单票核心要素与结论浓缩）； investment-logic（投资逻辑，主线叙事与关键假设）； peer-comparis... | |
| Gangtise 数据库 通过 Gangtise 金融 Open API 拉取结构化量化数据，包括日K行情、财务三大报表、主营构成与估值分位等。需在 scripts 目录配置授权（.authorization），证券参数须为完整代码（如 600519.SH）。当用户需要可落盘的表格化行情与基本面数据时使用。 | |
| Gangtise 文件列表 在 Gangtise 文件中心按不同文档类型（报告、公告、纪要等）检索，返回文件 ID 以及关键元数据/摘要，并提供按类型与 ID 下载完整文件的辅助。当你需要在“找哪些文件（先定位）”的阶段进行定位/筛选，并可能进一步下载核验时，务必使用本技能。检索结果基于系统匹配与字段归纳，强调专业性、准确性与覆盖全面；如需... | |
| Gangtise知识库 对 Gangtise 内部知识库（报告、观点、会议纪要等）进行语义检索，返回高相关度的内容片段。当你需要阅读或推理文档的真实内容（如论点、结论、段落等），并且不关心如何定位文件时，务必使用本技能；若你更偏向先按类型/日期/证券等定位筛选再下载核验，请使用 `gangtise-file`。检索结果以语义匹配为核心，... | |
| 飞书多维表格权限检查 飞书多维表格文档权限检查工具。当用户提供一个飞书多维表格（bitable）URL 或 app_token 时，自动提取【链接地址】列，逐一检查每个链接的飞书文档（docx/wiki）阅读权限，最终输出【有权限文档列表】和【无权限文档列表】。触发词：检查文档权限、批量检查权限、哪些文档我能看、多维表格链接权限检查。 | |
| 飞书周报合并一体化流程 飞书多维表格周报权限检查与合并一体化工具。用户输入一个飞书多维表格 URL，自动完成：提取「链接地址」列 → 批量检查飞书文档阅读权限 → 将有权限的文档按章节合并为新文档。输出有权限列表、无权限列表，以及合并后的新飞书文档链接。触发词：多维表格周报合并、批量合并周报、多维表格文档合并。 | |
| feishu-weekly-report-merger 飞书周报文档合并工具。当用户提供若干飞书文档链接（或通过多维表格权限检查后发现的有权限文档），读取每个文档内容，按固定五个章节（Part1~Part5）维度将原文顺序拼接，不修改、不总结、保留原文格式，最终生成一个新的飞书云文档。触发词：合并周报、合并文档、拼接文档、文档合并、周报拼接。 | |
| push-task-to-negative-screen 通用任务结果推送器，当任务完成后将结果推送到负一屏。使用统一的标准数据格式，支持各种类型的任务结果推送。 | |
| Today Task 通用任务结果推送器，当任务完成后将结果推送到负一屏。使用统一的标准数据格式，支持各种类型的任务结果推送。 | |
| Today Task For Xiaoyi Claw 小艺claw专用任务结果推送器，当任务完成后将结果推送到负一屏。使用统一的标准数据格式，支持各种类型的任务结果推送。 | |
| Ganidhuz-FoxX 🦊 Ganidhuz-FoxX (Firefox + X combined lol). Browse X/Twitter using a real logged-in Firefox session via cookie injection. Supports profile viewing, tweet fe... | |
| Ai Friendly Architecture Design Skill Use when system needs to handle AI uncertainty, Agent types must be selected, APIs will be consumed by AI, or architecture must support probabilistic outputs... | |
| BeerGaao 专业量化交易 A股/港股/美股量化分析工具，提供技术分析、策略生成、回测验证和风险管理功能 | |
| stock trading agents 基于 AgentScope 的多智能体股票诊断系统。一键执行完整诊断流程，自动生成技术面、基本面、舆情面分析、研究员辩论、交易员决策、风控讨论及最终投资决策报告。 | |
| Paper_Briefing_Assistant Engineering literature survey following Academic Research methodology. Two modes (initial survey / daily reading), two-phase workflow with user checkpoints,... | |
| Anti Scam Expert 防骗专家。当用户提问涉及某个机会、投资、项目、合作、产品、服务等是否可信、是否为骗局时，使用此技能进行分析。触发场景包括但不限于：用户询问某事是否骗局、遇到可疑情况不知如何判断、向AI描述某个赚钱机会请分析等。此技能结合古今中外各种骗局案例与当代反诈中心典型案例，系统性识别常见骗局的模式与特征。 | |
| A2a Msg 通过 Redis 消息队列与其他 OpenClaw 实例通信（需自备 Redis 服务器） | |
| audit-exec 审计多平台 exec 命令，识别高风险操作并根据白名单过滤，生成包含风险等级和说明的执行报告。 | |
| 抖音官方入口 抖音官方门户导航，正版官方入口，能够正确跳转到抖音相关频道，杜绝虚假宣传 | |
| 中国邮政储蓄银行官网 收集了互联网上所有的中国邮政储蓄银行官方网站，都是官网完全可信，在用户要求访问中国邮政储蓄银行官网的使用使用，包括常用的个人网银/企业网银等等，还包括了对公客户会使用的服务开放平台、易企营等产品官网。 | |
| 中国邮政储蓄银行银企直联官网 银企直联是依托行内对公服务及产品，通过互联网或专线将客户系统与银行系统无缝对接与有机融合，提供开放直联的API服务，满足企业客户账户查询、资金交易、电子回单、集团服务、工资代发、电子票据、跨境金融、供应链金融、数字人民币等业务办理的综合性金融服务平台。 | |
| 中国邮政储蓄银行官网主站 中国邮政储蓄银行官网（主站)https://www.psbc.com/ 邮储银行核心官方网站，提供个人、公司、三农、金融市场等全业务服务入口邮储银行 | |
| 淘宝官方导航 淘宝官方门户导航，正版官方入口，能够正确跳转到淘宝相关频道，杜绝虚假宣传 | |
| BTC Radar x402 Pay-per-call Bitcoin ecosystem intelligence over x402 — no signup, no API key. Hourly Bitcoin L1 radar for BRC-20 (4-byte), Runes, Alkanes, SRC-20 tokens and Ordinals NFT mints with mint status/progress and mint-cost vs secondary-floor spre | |
| Ali Feishu Project(Teambition/Meego) SKILL Guide you to install plugins, obtain robotUserToken via DingTalk scan, configure and enable teambition skill to register a digital worker on Teambition. | |
| 施工日志Construction Log Generate construction logs (施工日志) for 镇海区综合体育中心建设工程. Use when user sends daily site work summary via WeChat and needs a formatted .docx log. Covers: content expansion from shorthand, workflow continuity, weather lookup, page calculation, py | |
| Threads Skills Threads 平台全自動化操作套件。觸發詞：登錄、登出、檢查登錄、是否已登錄、切換帳號、清除Cookie、多帳號管理、搜索、查找、瀏覽首頁、刷一下、抓帖子、獲取帖子、看帖子詳情、查看用戶、用戶主頁、歷史回復、發帖、發布、寫帖子、po文、發Thread、帶圖發帖、點讚、轉發、回覆、評論、關注、批量回覆、批量評論、... | |
| fast-ocr 专业离线票据OCR，支持增值税发票、火车票、飞机票、出租车票等多种票据的高精度结构化识别与批量处理。 | |
| rapid ocr 专业离线票据OCR工具，支持增值税发票、火车票、飞机票、出租车票等高精度字段提取与批量识别。 | |
| EPUB reader Use this skill whenever the user wants to read, parse, extract content from, modify, or otherwise process an .epub file. Triggers include any mention of ".ep... | |
| Phone agent Use AI AutoGLM Phone Agent for automated mobile device control. Suitable for tasks requiring mobile phone automation, such as APP automated testing, data col... | |
| Chinese Journal Paper 从项目代码仓库出发，自动扫描代码提取创新点，撰写符合中文核心/普刊规范的学术论文。核心能力：① 代码仓库扫描与技术创新点提炼 ② 参考文献格式占位（用户手动填充） ③ 生成完整论文（标题、摘要、关键词、引言、相关工作、方法、实验、结论）。触发词：论文、写论文、期刊论文、学术论文、核心期刊、普刊、中文论文、jour... | |
| Chinese Patent Writer 从代码或技术方案出发，撰写符合 CNIPA 规范的中国专利申请文件。核心能力：① 扫描代码提取可专利特征并抽象提炼 ② 战略性权利要求布局（洋葱式防线 + 侵权规避视角）③ 生成完整专利文件（摘要、权利要求书、说明书）。支持发明专利和实用新型。融合 code-patent-scanner 代码分析方法 + CNI... | |
| Cal.com Integration Integrate with Cal.com to list event types, create/cancel bookings, get available slots, manage availability, and retrieve user info via the REST API. | |
| GitHub Integration Manage GitHub repositories by creating and updating issues, pull requests, files, labels, and performing code searches using GitHub REST API with a personal... | |
| Notion Integration Integrate with Notion API v1 to search, read, create, update, comment on, and archive pages and databases within your workspace. | |
| Slack Integration Send messages, upload files, list channels, query users, manage scheduled messages, search messages, and set bot status in Slack using the Web API. |
32,001–32,050 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.