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 |
|---|---|
| gjsw 国家税务总局 12366 纳税服务平台自动登录技能。支持图形验证码 OCR 识别、持久化会话、自动定位表单元素。当用户要求登录税务平台、12366、国家税务总局、国家税务局12366 、12366国家税务局 等登录场景时触发。关键判断：用户提供用户名、密码以及登录页面 URL（或已设置环境变量），希望自动完成登录流程。 | |
| Cancel Dispatch Run Cancel an active interactive dispatch run by run-id from slash command cancel. Use when user wants to stop a dispatchi or ralph-loop task immediately. | |
| Dispatch (Claude Code) Launch non-blocking Claude Code headless tasks from slash command dispatch. Use when user requests async coding jobs and does not require slash-only Claude p... | |
| Dispatchi (Ralph Loop) Launch non-blocking interactive Claude Code tasks for slash-only plugins like ralph-loop. Use when a task needs interactive slash commands and completion cal... | |
| Ad Context Protocol (AdCP) Advertising Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, med | |
| ab-test-calculater Feed it two data sets — one plain-language verdict on whether to ship. No decoding p-values required.
Pure Python from scratch.Plain-language verdict engine: synthesizes p-value, effect size, and power into one actionable sentence | |
| Emoji Translator 400+ emoji with CN↔EN bidirectional translation + smart inline embedding. Memes included. | |
| Focus Toolkit A full-focus-lifecycle workflow for precise session tracking, ambient sound generation, and data-driven analytics. | |
| Digen Ai Free DigenAI image and video generation for OpenClaw. Supports image-to-video and text-to-image. Video generation via api.cowork.digen.ai with Bearer token. Trigg... | |
| Opentable Booking Book restaurant tables on OpenTable via the browser tool. Handles hidden time slots and terms checkboxes with JS evaluate fallbacks. Works with a logged-in s... | |
| Restaurant Booking - OpenTable Book restaurant tables on OpenTable via the browser tool. Handles hidden time slots and terms checkboxes with JS evaluate fallbacks. Works with a logged-in s... | |
| AI SkillHub OpenClaw AI SkillHub 核心。支持两种触发方式：①「!skill URL」自动模式，AI 自动归纳关键词和分类；②「!skill 关键词 URL」手动模式，用户指定关键词。提取内容 → 生成原始内容.md + SKILL.md → 推送 GitHub。 | |
| Skill Curator OpenClaw 的总调度 Skill。当用户在 Discord 发送「【关键词】URL」格式的消息时，自动触发本 Skill：判断该关键词对应的 Skill 是否已存在 → 提取 URL 内容 → 追加或新建知识 Skill → 推送到 GitHub skillhub 仓库。 | |
| Youtube To Skill 自动从任意视频链接（YouTube、Bilibili、西瓜视频、抖音、小红书视频等）生成 OpenClaw Skill 并上传到 GitHub。用户分享任意视频链接，希望将其内容自动转化为 Skill 时触发。 | |
| Canvas LMS Student Skill Use when the user needs to interact with Canvas LMS as a student. Trigger phrases include "check my homework", "what's due", "download my lecture PDFs", "lis... | |
| Skill Secure AI agent wallets via Sigil Protocol. 3-layer Guardian validation on 6 EVM chains. | |
| Sardis — Payment OS for AI Agents Payment OS for AI agents. Create MPC wallets, execute stablecoin payments with automatic policy enforcement, set spending rules in natural language, check ba... | |
| Sardis Balance Read-only balance checking and spending analytics for Sardis agent wallets | |
| Sardis Cards Virtual card issuance and management for AI agents to make real-world purchases | |
| Sardis Escrow Smart contract escrow for agent-to-agent payments with delivery confirmation | |
| Sardis Guardrails Real-time security monitoring and circuit breaker controls for Sardis agent wallets | |
| Sardis Identity Agent identity management with TAP protocol verification and reputation tracking | |
| Sardis Openclaw Enable AI agents to make secure, policy-controlled payments through Sardis Payment OS | |
| Sardis Policy Natural language spending policy creation and management for Sardis agent wallets | |
| Etherlink Skill Etherlink blockchain interaction - EVM-compatible L2 on Tezos. Supports mainnet and shadownet testnet via MCP server. Use for balance checks, transactions, smart contracts, and token operations on Etherlink. | |
| Etherlink Skill Etherlink blockchain interaction - EVM-compatible L2 on Tezos. Supports mainnet and shadownet testnet via MCP server. Use for balance checks, transactions, smart contracts, and token operations on Etherlink. | |
| Tezos Skill Expert Tezos blockchain development guidance. Provides security-first smart contract development, FA1.2/FA2 token standards, gas optimization, and production deployment patterns. Use when building Tezos L1 smart contracts or implementing to | |
| Dictation Audio 根据英语单词生成听写音频，每个单词读两遍，中间停顿1秒 | |
| Edge Tts Chinese Convert Chinese text or files into MP3 audio using Microsoft Edge's neural voices with customizable voice options. | |
| Ket News Fetcher 抓取BBC News并生成Daily English News PDF，包含完整文章、全文翻译和80个词汇 | |
| Mbti Guru Provides MBTI personality tests in four versions, analyzing four dimensions to generate detailed bilingual personality and career reports. | |
| Pdf Vocab Audio 从 PDF 提取词汇生成朗读音频，每个词组读两遍 | |
| Vocabulary Lookup 从GPT4词典库查询单词详情，支持词义、例句、词根、记忆技巧等功能 | |
| Whoop Guru WHOOP AI Fitness Coach - WHOOP手环数据获取、健康分析、恢复预测、AI教练、个性化训练计划 | |
| Rtk Compressor Intelligently compress CLI outputs by removing comments, blanks, and redundancies to reduce token usage by 60-90% while preserving key info. | |
| Tweet Share Card Convert an X/Twitter post URL into a polished share card image by capturing the tweet content and compositing it on a styled background. | |
| Crop Image Use this skill when an AI agent needs to crop images through the deployed Crop Image service. Trigger this for URL-based cropping (`POST /crop`) and file-upl... | |
| Basic Integration Guide 指导开发者如何接入basic基础服务，包括依赖引入、gRPC调用、REST API使用、配置说明。涵盖国际化(i18n)、项目管理、租户管理、字典管理、存储、认证等核心能力 | |
| Energy App Middle Integration Use when integrating with the energy-app-middle BFF service - covers REST API endpoints, gRPC client setup, authentication headers, multi-tenancy, and downst... | |
| Iam Integration Use when integrating a new service with the IAM (Identity and Access Management) system - covers gRPC client setup, JWT token validation, permission checks,... | |
| cat-sticker 猫猫表情包技能系统。分析输入文本情绪，从 custom_stickers.json 自动匹配对应表情，支持概率/开关/冷却调节指令。 | |
| Server Guardian 服务器健康监控与自动恢复技能。当服务器出现卡顿、崩溃、Bot 连接异常或网关中断时使用此技能。支持：执行健康检查、自动诊断故障、一键恢复 Gateway、清理内存/磁盘、整理日志、检查 OOM Killer 等操作。触发场景包括：服务器变慢、Bot 无响应、日志报 ERROR、内存/磁盘告警、进程消失等任何异常情... | |
| OpenClaw Anything (efrageek fork) OpenClaw CLI wrapper and docs companion for gateway, channels, models, automation, and operational workflows. | |
| Swift Architecture Skill Agent Skill for Swift architecture design and implementation patterns, with architecture-specific playbooks and review checklists. Use when designing new fea... | |
| Swift Patterns Review, refactor, or build SwiftUI features with correct state management, modern API usage, optimal view composition, navigation patterns, performance optim... | |
| Local Websearch 1 Search the web using a self-hosted SearXNG metasearch engine aggregating multiple sources without API keys and returning JSON results. | |
| Spotify Controller Control Spotify playback and devices from an AI agent using spotify.py and the official Spotify Web API. Use when users ask to check current track, play/paus... | |
| Cocod A Cashu ecash wallet CLI for Bitcoin and Lightning payments. Use when managing Cashu tokens, sending/receiving payments via Lightning (bolt11) or ecash, hand... | |
| NS Trains Check Dutch train schedules, departures, disruptions, and plan journeys using the NS API. Perfect for daily commute checks. | |
| calendar-subscribe Turn a school or work timetable (xlsx / csv) into a shareable HTTPS ICS subscription. Split class blocks into sessions, add one travel alarm per day (first class only), host a WeChat/iOS/Android landing page. Use when the user says 课表订阅, 日历 |
28,201–28,250 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.