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 |
|---|---|
| Disinto Factory Set up and operate a disinto autonomous code factory. Use when bootstrapping a new factory instance, checking on agents and CI, managing the backlog, or trou... | |
| Browser Search Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research. | |
| Drinks Sommelier Expert sommelier for beers and wines. Load when the user asks for advice, talks about, or sends images related to beers or wines. | |
| Scoped Memory Manager Installs and manages Scope-Based Memory and Automated REM Sleep (memory consolidation) for OpenClaw agents. Use this skill when an agent's MEMORY.md is bloat... | |
| Longxia Skill Scanner Scan public GitHub agent skills before installation | |
| OpenClaw Safety Guard Safety Guard URLs or files with the safety-guard CLI (web, PDFs, images, audio, YouTube). | |
| OpenClaw Safety Guard Safety Guard URLs or files with the safety-guard CLI (web, PDFs, images, audio, YouTube). | |
| OpenClaw Safety Guard Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM | |
| Test Safety Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM | |
| karpathy-llm-wiki Persistent wiki manager based on Karpathy's LLM-Wiki pattern. Builds and maintains a structured, interlinked markdown wiki from your sources — compounding kn... | |
| see-video Use when the user sends a video file or asks about video content. Extracts frames and injects them as an image grid directly into the LLM context — no proxy... | |
| Revenium Budget Enforcement MANDATORY guardrail check BEFORE EVERY OPERATION — read guardrail-status.json first, always, no exceptions. Enforces Revenium guardrails-native budget rules,... | |
| Lynse Cli Lynse CLI 工具，调用 lynse.ai 后端服务的 API。当用户需要查询 lynse 账户信息、管理文件/转写/总结、操作设备、管理 AI 模型、团队协作、发送消息时使用此技能。即使只是简单查个积分或看个文件列表，也应使用此技能。 | |
| gemma4-dev Use when designing, configuring, or implementing applications targeting the Google Gemma 4 model family. Covers model architecture selection (26B/12B/E2B/E4B), native Thinking Mode formatting, function calling schemas, multimodal audio/visi | |
| feishu-message-group-whitelist 飞书群聊白名单关键词过滤。当飞书机器人收到群消息时，根据白名单判断是否需要回复——只有消息中包含白名单关键词时才触发回复，实现精准触发而非广播所有消息。触发词示例：群里有人发消息时、提到特定关键词时、需要过滤无关消息时。 | |
| Privacy Cards Create and manage Privacy.com virtual cards. Use for generating single-use cards, merchant-locked cards, listing cards, setting spending limits, pausing/closing cards, and viewing transactions via the Privacy.com API. | |
| Agentsocial 让你的 AI Agent 替你进行社交匹配——招聘、找工作、找合伙人、社交、找对象 | |
| Polymarket Fast Loop Trade Polymarket BTC 5-minute and 15-minute fast markets using CEX price momentum signals via Simmer API. Default signal is Binance BTC/USDT klines. Use when... | |
| Polymarket Weather Trader Trade Polymarket weather markets using NOAA forecasts via Simmer API. Inspired by gopfan2's $2M+ strategy. Use when user wants to trade temperature markets,... | |
| Robotomail Give an AI agent a real inbox and outbound email using Robotomail. Use this skill when the user asks you to send email, check inbox, read messages, reply to... | |
| Alter Manager 分身管理 - 创建、列出、删除独立的 agent session（分身）。触发场景：用户要求创建分身、创建独立 session、管理多个对话、列出分身、删除分身、移除 session。支持 label 从用户指令中识别或主动询问。 | |
| authlock AuthLock (机密保护) - MFA-bound secret protection. Triggers when user mentions authlock, secret protection (机密保护), TOTP encryption, MFA binding (MFA绑定), password... | |
| cortex-backtest Cortex 量化策略回测引擎。聚宽风格策略代码，支持日线回测，与聚宽平台完全对齐。触发场景：用户提及 Cortex 回测、策略回测、聚宽风格策略、回测引擎、量化策略开发、策略验证、Cortex 首次设置、Cortex 配置。 | |
| Mobilerun Control real Android phones through the Mobilerun API. Supports tapping, swiping, typing, taking screenshots, reading the UI accessibility tree, and managing... | |
| Mobilerun Load this skill whenever the user wants to control, automate, or interact with a phone or mobile device. This includes: tapping, swiping, typing, taking scre... | |
| honor Provides JSON API commands to fetch Picqer dashboard KPIs, picklists, stock movements, and revenue data for order fulfillment monitoring. | |
| Smalltalk Interact with live Smalltalk image (Cuis or Squeak). Use for evaluating Smalltalk code, browsing classes, viewing method source, defining classes/methods, querying hierarchy and categories. | |
| apple-notes-writer 完美格式写入Apple备忘录。支持HTML格式、Markdown转换、多文件夹管理、自动转义特殊字符。 | |
| IsItWater Check if geographic coordinates are over water or land using the IsItWater API. | |
| Goal Decomposer 将高层自然语言目标拆解为可执行的多层级任务列表。 触发场景：用户给出模糊目标需要具体执行步骤、复杂任务需要拆解、需要生成任务树。 | |
| Molter Register on Molter, inspect agent state, and publish posts or replies using direct Molter HTTP requests | |
| Data Hub 数字货币量化交易系统的内存数据中枢，为多 Agent 提供统一的数据共享层。管理行情(market_state)、指标(indicators)、情报(intelligence)、风控(risk_audit)四个命名空间。Use when: Agent 需要读写共享数据、查询行情/指标/研报/风控状态。NOT fo... | |
| Text Punctuation Restoration/文本标点恢复与断句段落划分 本技能用于将无断句、无标点符号的“粘连文本”转化为有标点符号、有断句、无粘连的规范文本。适用于处理从 OCR 识别、语音转写（ASR）或网页复制粘贴产生的无格式文本。 | |
| 研究指定的软件项目 调研指定的某一款开源或商业闭源软件项目。 | |
| Miaoda Doc Parse Use when user needs to parse, extract, or read content from documents (PDF, Word, Excel, PPT, etc.) Converts documents to Markdown via IDP (Intelligent Docum... | |
| Paper to Tools - Match Research Methods to AI Agents Paste a paper abstract or methods section → get matched AI agent tools that can reproduce the analysis. Maps methodology keywords to 131+ curated science age... | |
| Science Agent Compare - Side-by-Side AI Tool Comparison Compare AI science agents side by side. Input 2+ project names or a research domain → get structured comparison of features, stars, tech stack, and use cases... | |
| Science Agent Recommend - Find the Right AI Tool for Research Get personalized AI agent recommendations for your research domain. Describe your field, task, or workflow → receive curated suggestions from 131+ projects a... | |
| Agent Browser Qw A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co... | |
| Math Utils Native Performs precise math calculations by executing native OS CLI tools like bc, python3, or PowerShell without relying on AI prediction. | |
| TDengine Setup 自动化安装和配置 TDengine 3.3.6.0。包含从官网下载、安装、启动服务以及基础数据库验证的完整流程。 | |
| toolguard-daemon-control Manage macOS launchd user agents to start, stop, restart, check status, and access logs of persistent background services without sudo. | |
| Mighty Router Enforces risk-based coding profiles, impact mapping, adversarial planning, and strict verification gates before making edits, audits, or structural modificat... | |
| linux-camera Capture photos, record video clips, list cameras, and live stream on Linux. Uses V4L2 and ffmpeg. Supports USB webcams and RTSP/IP cameras. | |
| 十元云铺万元利 十元云铺万元利——一句话或一张产品图，自动生成可分享的小批发部迷你网站（云铺档口页），含产品图、口播音频、分享文案、电话/微信联系方式。当用户说「开个云铺」「我有货想卖」「帮我做个卖货页面」「生成档口页」「云南沃柑 5 斤 29.9」这类想快速获得卖货展示页的请求时使用。纯展示导流，成交线下对接，平台不参与交易。 | TenYuan Cloud Shop: turn one sentence or one product photo into a shareable mini | |
| Openclaw Skill Provides real-time verified news briefs and detailed intelligence reports from 160+ sources across 18 categories with bias and confidence ratings. | |
| Polaris Access verified, real-time news briefs, on-demand intelligence reports, trending topics, and search from 160+ sources across 18 categories with bias and conf... | |
| Veroq Provide verified AI intelligence on markets, assets, sentiment, and economic data with live prices, signals, analysis, and fact-checking from 1,000+ tickers... | |
| Agent Invoice Generator Generate professional PDF invoices from natural language or structured data. Use when the user asks to create an invoice, bill a client, generate a receipt,... | |
| Code Metrics Analyze code quality metrics including lines of code by language, cyclomatic complexity (Python), function/class counts, comment ratios, and largest file ran... |
42,551–42,600 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.