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 |
|---|---|
| yandex-metrika-assistant OpenClaw + Яндекс.Метрика API — stat/Logs/management, OAuth, presets, UTM, цели, CSV, квоты; плагин yandex-metrika-assistant. | |
| CMB HKD-CNY Exchange caculator in REALTIME 查询招商银行外汇牌价（中间价） | |
| Deno Deploy Deploy simple web pages and HTML apps live to the internet using the Deno Deploy REST API. Use this skill whenever the user wants to make something "live", "... | |
| Prediction Markets Roarin Participate in the Roarin AI prediction network. Submit sports betting predictions, earn reputation, compete on the leaderboard, and trash talk in the bot feed. Use when the user wants to make predictions on sports markets, check bot consen | |
| Ai Writing Humanizer Automatically strip AI writing patterns and stock phrases from user-facing prose before sending. Use when preparing longer texts to ensure a natural, human t... | |
| Bug Bounty Report Template Generate professional bug bounty reports for HackerOne, Bugcrowd, and other platforms. Pre-filled templates with CWE mapping, reproduction steps, and severit... | |
| HTTP Header Analyzer Analyze HTTP security headers and TLS configuration. Find missing headers, weak ciphers, and misconfigurations in web applications. | |
| Lightpanda Scraper Fast headless browser web scraping using Lightpanda (0.5s page loads, 90x faster than Chromium). Perfect for OSINT recon, link extraction, and content scrapi... | |
| Network Device Monitor Monitor network devices, detect unknown clients, and alert on new connections. Works with any router that serves a web UI. Tracks device state changes over t... | |
| Reboot Checker Detect unexpected system reboots and alert when the system comes back online. Tracks boot history and flags suspicious restarts. | |
| Recon Quick Fast OSINT and reconnaissance presets using bbot and nmap. One-command subdomain enumeration, port scanning, and web fingerprinting for bug bounty recon. | |
| Secure Password Generator Generate cryptographically secure passwords, passphrases, and API keys. Supports multiple formats and entropy calculation. | |
| Subdomain Takeover Checker Check subdomains for potential takeover vulnerabilities. Detects dangling DNS records pointing to unclaimed services (GitHub Pages, Heroku, AWS, etc.) | |
| Clawlendar Timestamp-first perpetual calendar interop for AI agents. Use when agents need cross-calendar conversion (Gregorian/Julian/ISO/ROC/Buddhist/Japanese era/sexa... | |
| Llmwiki LLM-powered personal knowledge base. Raw documents in, an LLM compiles them into a structured interlinked wiki with trilingual articles, emergent taxonomy, a... | |
| Tigerbrokers Tiger Brokers OpenAPI Python SDK — complete skills for AI coding tools. Covers SDK setup, market data queries, stock/futures/options trading, real-time push... | |
| Bitget Data Automates multi-coin spot grid trading on Bitget with dynamic adjustments, risk management, portfolio monitoring, and analysis tools. | |
| articuler AI-powered professional networking assistant. Generate personalized cold emails and outreach playbooks to accelerate career growth and business development. | |
| smarter-task-planner 【Smarter Task Planner】自动创建时间戳任务文件夹，支持步骤规划、检查点保存、中断恢复与进度追踪，确保任务可追溯、可恢复。适用于分析、调研、信息提取、文档生成等需要结构化步骤的任务场景。 | |
| workspace-organizer 任务文件组织与记忆管理。创建时间戳文件夹，支持会话恢复。 | |
| 龙虾内容工厂 龙虾内容工厂。批量生成小红书信息图+视频，定时自动发布。 | |
| Aicloset Skill AI智能衣橱 — 衣橱管理、AI搭配推荐、知识库搜索、虚拟试衣 | |
| AI 衣橱搭配 AI 智能搭配推荐 - 个人穿搭方案生成工具。 当用户提到以下意图时使用此技能： 「今天穿什么」「搭配推荐」「穿搭」「outfit」「穿什么好看」 「AI搭配」「衣橱搭配」「帮我搭配一套」「明天穿什么」 「商务风穿搭」「约会穿什么」「休闲搭配」 支持：根据日期、城市、天气和风格偏好，调用 AI 衣橱 API 生成... | |
| coin-news-openclaw Collect and summarize cryptocurrency and coin market news with OpenClaw-friendly workflows. Use when users request coin news, crypto news, token-specific new... | |
| meeting-prep Automated meeting preparation and daily commit summaries. Use when checking Google Calendar for upcoming meetings, generating standup updates from GitHub commits, or sending daily development summaries. Pulls meeting schedules and commit hi | |
| offline-quiz-builder 把任意学习资料（讲义、笔记、教材、PDF、Word、Excel、已有题库）转换成一个纯离线的智能复习题库网站，双击即可使用，内置艾宾浩斯遗忘曲线自适应排程、错题本、收藏夹与打卡日历，并可自动创建每日复习提醒任务。当用户想把资料变成刷题网站、做复习题库、生成练习题、搭建离线背题工具、或需要按遗忘曲线安排复习时，应使用本技能。 | |
| handshake Open or close a branch-scoped project handshake that preserves compact context, relevant skills, unresolved work, and ordered next actions. Use when starting or ending a Claude Code work session. | |
| Workspace Maintenance Maintain workspace documentation hygiene and discoverability. Use when organizing markdown sprawl, updating doc indexes, archiving stale progress/status snap... | |
| Arxiv Research Secure Secure ArXiv paper search and download tool with local caching, AI summarization, research logging, and no shell command execution. | |
| File Manager Secure Perform safe file operations with path validation, dry-run previews, recoverable trash deletes, batch confirmations, and audit logging to prevent data loss. | |
| BP Monthly Report Writer Draft monthly BP reports by normalizing templates, mapping BP anchors, collecting evidence, and writing sections in order with data-backed progress evaluation. | |
| BP母版维护 维护BP报告母版、映射关系和版本规则 | |
| XGJK BP Audit BP目标体系全面审计工具：对BP进行五大板块审计——基础合规性审计、向上对齐审计、向下承接审计、GAP 差异分析、数值对齐审计。 覆盖结构完整性、内容质量、逻辑自洽、对齐正确性、承接覆盖率、数值定义与算法、上下级差异识别等维度。 内置数据查询能力，当用户需要对BP目标体系进行系统性审计诊断时使用。 | |
| Houwei Hello World 验证ClawHub跨设备同步功能并提供自定义技能开发入门模板的个人专属测试技能。 | |
| bingli-writing-standard-2015 《病历书写规范（最新版）》（费勤福主编，2015.1 出版，安徽省卫计委组织编写，十三章+附录，686 页）全文检索。 内容覆盖：病历书写基本要求、门急诊/住院病历格式、24 种医疗记录（病程/查房/抢救/手术/麻醉/医嘱/死亡记录等）、 35 个专科病历书写重点、中医中西医结合病历、申请单报告单、护理文书、知情同意书（含常用示例）、 处方书写规范、病案首页、电子病历、临床路径、病历管理与质量控制，附录含处方管理办法等法规原文。 当用户问"病程记录怎么写""知情同意书内容"" | |
| chelaile-bus (公交实时到站) 北京/全国 480 城市公交实时到站查询。基于 chelaile MCP 服务（mcporter chelaile），免 API Key。典型场景："311 路还有几分钟到展春园"、"查 86 路现在到哪了"。 | |
| cost-effective-life-guide 高性价比人生指南（GitHub 开源 HowToLiveBetter）：544 条按性价比排序的生活决策建议，证据分级（A 级 358 条 RCT/荟萃分析级）。当用户问健康防病、急救处理、省钱理财、防骗、法律红线、租房买房、婚恋成本、育儿、工伤离职、看病就医、留学出路等生活决策问题时使用。覆盖十大领域 32 节，条目含成本/收益/证据硬度三要素。 | |
| din-whitepaper Knowledge base from《分布式推理网络（DIN）技术白皮书》(中国移动研究院, 2025). Use when analyzing 算力网络/AI推理网络 architecture, 端边云协同 inference patterns, deterministic networking (丢包率10⁻⁹/微秒级抖动), 运营商AI战略, SRv6切片/PHYSec/算力路由, or referencing DIN concepts. | |
| tcm-diagnosis-efficacy-standard-2024 Knowledge base from《中医病证诊断疗效标准（2024版）》(国家中医药管理局医政司, 中医药行业标准). Use when 查询中医病证的诊断依据、证候分类、疗效评定标准——内科/肛肠/眼科/耳鼻喉/外科/骨伤/妇科/皮肤/儿科九大科. | |
| tcm-medical-record-writing-standard 中医、中西医结合病历书写基本规范（试行）全文检索（国中医药发〔2002〕36号，2002-09-01 施行）。 覆盖门急诊病历、住院志、病程记录、手术麻醉记录、医嘱、护理记录、出院/死亡记录等全部文书的书写要求、 内容清单与完成时限。当用户问"入院记录几小时内完成""首次病程记录时限""主治查房记录""抢救记录怎么补记" "手术记录谁写""医嘱单分几种""出院记录内容""中医四诊怎么记入体格检查"等病历书写与病案管理问题时使用。 | |
| tcm-medical-tech-manual-2026 Knowledge base from《中医医疗技术手册（2026版）》(国家中医药管理局医政司审定口径, 639页/11章/100+技术). Use when 查询中医适宜技术(针刺/推拿/拔罐/灸/敷熨/微创/骨伤/肛肠/气功等)的适应证、禁忌证、操作方法、注意事项。 | |
| 当用户希望“通过建表语句 + 慢 SQL 自动优化索引”时使用此 Skill，支持 MySQL、Oracle、PostgreSQL。脚本使用 Python，自动解析 DDL 与慢 SQL 中的 WHERE/JOIN/ORDER BY 列，生成候选索引及对应数据库的 CREATE INDEX 语句，并输出到文件。 当用户希望“通过建表语句 + 慢 SQL 自动优化索引”时使用此 Skill，支持 MySQL、Oracle、PostgreSQL。脚本使用 Python，自动解析 DDL 与慢 SQL 中的 WHERE/JOIN/ORDER BY 列，生成候选索引及对应数据库的 CREATE INDEX 语句，并输出到文件。 | |
| 分析Excel表中的申报失败信息，自动生成Word版本的申报运维报告，用于定位问题、统计趋势、提出整改建议。 分析Excel表中的申报失败信息，自动生成Word版本的申报运维报告，用于定位问题、统计趋势、提出整改建议。 | |
| Openclaw Skill Qa Quickcheck AI 驱动的日常测试助手，覆盖 PR 静态审计、动态功能测试、回归策略，2 分钟上手 | |
| UserLayer Use this skill when the user wants a UserLayer report for an App Store or Google Play app, including full analysis, polling, and follow-up questions grounded... | |
| caibao 精准解读真实财报数据，分析重资产周期拐点，排查财务造假，提供严谨投资决断建议。 | |
| Device Heartbeat Monitor Monitor remote device online status via heartbeat pings to healthchecks.io. Use when user asks to check if a device is online or offline, user reports device... | |
| Skill Audit Guardian Audit dropped ClawHub skill ZIPs, classify risk (SAFE/CAUTION/REMOVE), auto-sort files, and generate a plain-English security dashboard. | |
| PredictMe - AI Trading Agent Trade 10-second crypto prediction markets on PredictMe | |
| Affinity Readonly Read-only Affinity CRM access for analysis and memo prep. Use when you need to fetch Affinity companies, people, notes, opportunities, interactions, or relat... |
36,451–36,500 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.