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 |
|---|---|
| Beeper Search and browse local Beeper chat history (threads, messages, full-text search). | |
| Homey - Home Automation Control Homey home automation hub via CLI. Use when you need to control smart home devices (lights, thermostats, sockets, etc.), check device status, list zones, trigger flows, or perform any Homey automation tasks. Supports on/off, dimming | |
| Post.at Tracking Manage Austrian Post (post.at) deliveries - list packages, check delivery status, set delivery place preferences. | |
| Cclaw Open-source comedy AI + video editing + poster generation. Create standup/sketch/manzai/scripts, edit videos via FFmpeg, and generate comedy posters via canv... | |
| Exam Paper 【考试试卷生成器 | 题库管理 | 错题本】输入学科和题目数量，自动从题库随机抽题，生成考卷PDF和答案PDF两份文件。支持单选题、判断题、编程填空题。内置题库增删查、错题记录与复习标记功能。当前内置信息学奥赛22题，支持扩展其它学科。 触发词：出卷、组卷、考试卷、试卷、生成试卷、生成考试、题库、错题本、错题库、... | |
| GitHub Workflow Professional GitHub workflow skill for AI agents. Covers full project lifecycle: repo setup, Git Flow branching, atomic commits, pull requests, code review,... | |
| homarr Work on Homarr dashboards, board styling, custom CSS, iframe widgets, embedded mini-apps, native widgets, apps, and integrations. Use when requests mention H... | |
| krexa Use this skill when the user wants to research a trading idea, or turn an idea, post, reel or video into a tested strategy and deploy it as a live trading agent on Krexa. Covers Solana spot and tokenized stocks (xStocks), perps (Hyperliquid | |
| Lightpanda browser Lightpanda browser, drop-in replacement for Chrome and Openclaw default browser - faster and lighter for tasks without graphical rendering like data retrieval. Use it with CDP clients like Playwright or Puppeteer. | |
| 票据产品问答 Billing, Billing Product. A retrieval skill that answers bill questions from the `bill_knowledge/` knowledge base. And recommend possible banking platforms(b... | |
| 金融知识 A retrieval skill that answers finance questions from the `article_fin_knowledge/` knowledge base (8 markdown files covering banking, funds, M&A, derivatives... | |
| 理财推荐 wealth management investing finance financial advisor Bank. Wealth Management. Investing. Wealth product descriptions and investment product recommendations.... | |
| Crypto Trading Agents 多Agent加密货币量化交易系统 — 基于 TradingAgents 多Agent框架 + Binance 执行层。 支持：技术分析、消息分析、多Agent辩论、自动化交易信号生成、Binance 现货下单。 适用场景：研究量化策略、自动交易Bot开发、加密货币组合分析。 | |
| Crypto Trading Bot V7 加密貨幣交易機器人開發 - 幫你整自動交易Bot，支持Pine Script、Python、CCXT API對接。 適用於：(1)整TradingView信號Bot (2)CEX/DEX API自動化 (3)套利機器人 (4)止盈止損策略 (5)策略回測 (6)高级风控 (7)多策略框架 | |
| External Receiver 通用外部数据接收 Skill。 在服务器上启动 HTTP 服务，接收外部文件上传和消息， 自动将内容推送到 OpenClaw 用户会话。 支持：文件上传、文本消息、Webhook JSON、curl / wget 客户端。 | |
| WeChat Work Notifier 微信（WeChat Work / 企业微信）消息通知 Skill。 通过企业微信群机器人的 Webhook 接口向微信群/微信用户发送消息通知。 支持：文本消息、Markdown、卡片消息、图片。 适用场景：定时报告、报警通知、交易信号推送、自动化工作流通知。 | |
| Comanda Generate, visualize, and execute declarative AI pipelines using the comanda CLI. Use when creating LLM workflows from natural language, viewing workflow char... | |
| Feelgoodbot Set up feelgoodbot file integrity monitoring and TOTP step-up authentication for macOS. Use when the user wants to detect malware, monitor for system tampering, set up security alerts, or require OTP verification for sensitive agent actions | |
| Google Flights Search Google Flights for prices, availability, and deals. Use when user asks about flight prices, searching for flights, comparing airfares, finding the che... | |
| Machine Payments Protocol Tester Run a Machine Payments Protocol (MPP) conformance test — prove an agent or wallet can complete a real $0.50 USDC payment on Solana and get a shareable "passe... | |
| AICP Protocol AI Compact Protocol (AICP) - Token-efficient wire format for AI-to-AI communication with glossary compression. Reduces token usage by 50-65% for agent chatter. | |
| Test Clone Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed s... | |
| dakboard Manage DAKboard screens, devices, and push custom display data. | |
| ZEDEDA Complete ZEDEDA edge management API client — 473 endpoints across 11 service domains for edge node, application, cluster, storage, network, Kubernetes, diagn... | |
| agent-wake Wake an OpenClaw agent session from an external script or process. Use when a background task (Claude Code CLI, cron job, webhook, price alert, or any script... | |
| Pm Interview Coach PM 面试辅导教练。当用户说"面试辅导"、"模拟面试"、"帮我练习面试"、"面试练习"、"产品经理面试"时触发。接收用户简历 + 目标公司/岗位，输出深度简历追问、业务情景题、真实面经和答题指导。 | |
| Xiaohongshu Mcp Skill 操作小红书（搜索笔记、获取面经、查看热门内容）。当用户想搜索小红书面经、查找面试经验、了解某公司/岗位的面试情况时使用。基于本地 MCP 服务（localhost:18060）。 | |
| Manus Skill - Operate Manus through Openclaw Interact with the Manus AI agent platform via its REST API. Use this skill whenever the user mentions Manus, manus.ai, Manus API, Manus tasks, Manus projects... | |
| OpenClaw Backup & Restore — Encrypted OpenClaw Snapshots Backup and restore the .openclaw agent folder — encrypted snapshots pushed to a private GitHub repo. Use this skill whenever the user mentions backup, restor... | |
| SkillCompass — Skill Evolution Engine Evaluate skill quality, find the weakest dimension, and apply directed improvements. Also tracks usage to spot idle or risky skills. Use when: first session... | |
| Openclaw Echo Agent Processes text input using a tool to return deterministic output, serving as a reference example for OpenClaw agent development. | |
| Agentsecly Ai Agent Security Generate AI agent security advisories with threat analysis, MITRE ATT&CK mapping, and remediation guidance. Use when assessing AI agent security risks, evalu... | |
| Agentvulnly Vulnerability Scanner Scan AI agents for security vulnerabilities including token theft, prompt injection, command injection, tool poisoning, and rug pull attacks. Use when auditi... | |
| AI Art Prompt Generates creative and detailed prompts for AI art generation based on user-specified themes. | |
| AI Icon Generator Generate custom icons using artificial intelligence from text prompts or descriptions. | |
| AI Logo Generator Generate professional logos from text prompts using artificial intelligence. | |
| AI ML Engineer Generate personalized AI/ML engineering career roadmaps based on individual experience, skills, and goals. | |
| AR VR Developer Generate personalized career development roadmaps for augmented reality and virtual reality developers based on skills assessment and professional goals. | |
| Automation Tester Professional automation testing career roadmap generation platform that creates personalized learning paths based on experience, skills, and career goals. | |
| BI Analyst Generate personalized career roadmaps for aspiring Business Intelligence analysts based on assessment data, experience, and professional goals. | |
| Birth Chart Generates comprehensive astrological birth charts from personal birth data and supports multiple languages for cultural accessibility. | |
| Blockchain Developer Generates personalized blockchain development career roadmaps based on user experience, skills, and professional goals. | |
| Career Success Planner Generate personalized 120-day career success plans based on professional assessment data and onboarding goals. | |
| CCPA Privacy Checker Assess your business's compliance with California Consumer Privacy Act (CCPA) regulations and identify privacy governance gaps. | |
| Cloud Compliance Checker Validates cloud infrastructure configurations against industry compliance standards and regulatory frameworks. | |
| Cloud Misconfig Scanner Automated security scanner for identifying and reporting misconfigurations across cloud infrastructure providers. | |
| Cloud Risk Summary Generates comprehensive cloud risk summaries by analyzing provider configurations, environments, services, and security exposures. | |
| Cloud Support Generate personalized cloud career development roadmaps for AWS, Azure, and GCP support roles. | |
| Compliance Checklist Gen Generates industry-specific and region-specific compliance checklists to streamline regulatory adherence and audit preparation. | |
| Compliance Gap Filler Identifies and fills compliance control gaps across security frameworks like ISO 27001, NIST, and SOC 2. |
45,701–45,750 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.