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 |
|---|---|
| Iflytek Contract Intelligence Review Use when user asks to review contracts, detect contract risks, or perform compliance checks. 合同智能审核 - 对合同扫描件、图片合同、双语合同进行完整审核。 覆盖 OCR 识别、条款分析、风险检测、合规校对、翻译摘要全流... | |
| Iflytek Hyper Tts Use when user asks to synthesize speech, convert text to audio, or read text aloud. 讯飞超拟人语音合成 - 支持文本转语音、语音合成（发音人/语速/语调/音量/输出格式）。大模型语音合成技能。语音合成, 文字转语音, 超拟人, TTS. | |
| Iflytek Image Understanding Use when user asks to analyze an image, describe image contents, or answer questions about a picture. iFlytek Image Understanding (图片理解) — analyze and answer... | |
| Iflytek Ocr Invoice Use when user asks to recognize invoices, extract receipt data, or OCR bills and tickets. Recognize and extract structured data from invoices, receipts, and... | |
| Iflytek Pdf Image Ocr ifly-pdf-image-ocr skill supporting both image OCR (AI-powered LLM OCR) and PDF document recognition. Use when user asks to OCR images, extract text from ima... | |
| Iflytek Speed Transcription Ultra-fast speech transcription using iFLYTEK Speed Transcription API. Transcribe audio files (WAV/PCM/MP3) up to 5 hours in ~20 seconds per hour. Supports C... | |
| Iflytek Text Proofread iFlytek Official Document Proofreading (公文校对) — detect and correct errors in Chinese text including typos, punctuation, word order, factual mistakes, sensiti... | |
| Iflytek Translate iFlytek Machine Translation (机器翻译) — translate text between Chinese, English, Japanese, Korean, French, Spanish, German, Russian, Arabic, Thai, Vietnamese, a... | |
| Iflytek Video Translate Use when user asks to translate videos, dub video content, or localize videos into other languages. Translate videos with AI-powered dubbing using iFlytek (X... | |
| Iflytek Voiceclone Tts Use when user asks to clone a voice, train a custom voice model, or synthesize speech with a cloned voice. iFlytek Voice Clone tts(声音复刻) — train a custom voi... | |
| GoG-ifocus Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. | |
| Stripe Best Practices Best practices for building Stripe payment integrations | |
| tRPC Best Practices Expert guidance for tRPC (TypeScript Remote Procedure Call) including router setup, procedures, middleware, context, client configuration, and Next.js integration. Use this when building type-safe APIs, integrating tRPC with Next.js, or imp | |
| OpenClaw WebDAV Backup Backup and restore an OpenClaw workspace with incremental backups, integrity verification, health checks, optional config encryption and optional WebDAV uplo... | |
| IFTTT Connect OpenClaw to IFTTT's hosted MCP server and automate hundreds of services — discover triggers and actions, build and manage Applets, and run actions and queries. Use when the user mentions IFTTT, asks what they can automate, or descri | |
| Open Browser Use(OBU) Platform-neutral guidance for using Open Browser Use, the open-source Chrome automation stack for AI agents. Use when an agent needs to install, verify, trou... | |
| Open Computer Use Guidance for installing, configuring, and operating Open Computer Use, an open-source Computer Use MCP service for macOS, Linux, and Windows. | |
| mac-gui-control Control this macOS desktop via screenshots, AppleScript, mouse/keyboard automation, OCR/template matching, and verify loops. | |
| Free Media Gen（免费生图生视频） 免费文生图/文生视频：直连 Agnes、商汤 SenseNova、硅基流动 Kolors 等第三方免费模型，绕过混元 ImageGen、出图无水印。触发：打开免费生媒体 / 免费生图 / 免费生视频。 Free text-to-image & text-to-video: directly calls free third-party models (Agnes, SenseNova, SiliconFlow Kolors); bypasses Hunyuan ImageGe | |
| Free Model Auditor（免费模型审计员） 审计 WorkBuddy 自定义模型注册表（models.json）中的免费模型：跨多个 OpenAI 兼容厂商新增可发现的免费模型、 剔除已转付费或失效的模型，保持注册表真实有效。当用户要求「审计自定义模型」「检查有没有新的免费模型」 「测试其余平台有无遗漏」「定期巡检模型清单」或希望对免费 API 模型做健康检查时使用。 本技能对海外平台执行 VPN 连通性门禁，按各厂商策略判定免费，活体实测每个候选，并自动把新增/移除差异应用到 models.json。 | |
| Image OCR Reader Extract text from images using OCR with support for Chinese and English in common formats like jpg, png, and jpeg. | |
| SIAS Self-Improving Agent System Research SIAS-spezifischer Deep Research Skill für Rheingold. Optimiert für IFG-Anfragen, NGO-Netzwerk-Analyse und Fördermittel-Recherche in Köln/NRW. Kombiniert loka... | |
| greyghound Analyzes greyhound races, fetches data, and predicts winners/placings for upcoming races based on form, odds, and simple models. | |
| daily-editor 运行一个私人编辑部，把每日信息整理成 A4 竖版 PDF 日报，支持自定义板块、克制稳妥的编辑判断、更安全无害的包装方式，以及指向原始报道的来源链接。适用于用户提到 私人编辑部、每日推送、日报 PDF、信息编排、A4 单页简报、自定义板块、今日简报、单页快报、newsletter-style digest、dai... | |
| language-helper Use this skill whenever the user wants to learn how to say something in another language. Triggers include: language tags like 【日语】【英语】【韩语】【法语】【西班牙语】【德语】 fol... | |
| SwiftUI Empty App Init Initialize a minimal SwiftUI iOS app in the current directory by generating a single `.xcodeproj` with XcodeGen (no workspaces, packages, or tests unless explicitly requested). | |
| X-CLI Toolkit Full-featured X/Twitter toolkit — read, search, post, interact, DMs, lists, polls, trends. Cookie auth, proxy support, no API keys needed. | |
| Sandbox Manager 百度 Agent Sandbox 沙箱管理。触发词:沙箱/sandbox/创建沙箱/沙箱实例/沙箱模板/code_test/browser_use/aio。 | |
| Grok X Analyzer Dynamic, Grok 4.3-inspired analyzer for X (Twitter) posts, threads, trends, user activity, and related data. Use when users mention X/Twitter URLs/posts, ask... | |
| Grok X Growth Agent Ultra-high-ticket X (Twitter) Growth & Monetization Agent. Uses the official xAI (Grok) API and X OAuth 2.0 to autonomously identify trending niche discussio... | |
| HVAC Dispatch (30% OFF - B2B Special) 24/7 Voice & Text Dispatch Agent for HVAC & Plumbing. Qualifies leads, checks service zones, books appointments into ServiceTitan/Housecall Pro, and uses Thu... | |
| Inventory Waste Optimizer Autonomous inventory management and waste reduction agent for QSRs. Cross-references sales data with inventory levels to forecast ordering and flag excessive... | |
| Legal Intake Agent Ultra-high-ticket intake agent for Law Firms. Qualifies leads, performs preliminary conflict-of-interest checks, and books consultations. Hardened with Thumb... | |
| Legal Intake Pilot A high-security legal intake agent for law firms. Prevents unauthorized legal advice and PHI leaks via ThumbGate. | |
| Medical Dental Appointment Pilot A high-trust, HIPAA-aware appointment agent for medical and dental clinics. Prevents scheduling errors via ThumbGate. | |
| OpenClaw Zernio Analyzer Analyzes Zernio.com profiles, posts, companies, jobs, and trends to extract structures, networks, engagement, and career insights from URLs and content reque... | |
| Pizza Agent (LAUNCH SPECIAL - 4.99) High-performance voice & text ordering agent for pizza shops. Specializes in complex customizations (half-and-half, crust types) and delivery zone validation... | |
| Property Management Agent Autonomous tenant maintenance and ticketing agent. Triages tenant requests, distinguishes emergencies from routine maintenance, and syncs with Buildium or Ap... | |
| Real Estate Lead Pilot A high-trust lead qualification and appointment booking agent for realtors. Prevents MLS hallucinations via ThumbGate grounding. | |
| Real Estate Lead Qualifier High-ticket lead qualification agent for realtors and property managers. Handles inbound inquiries from Zillow/Realtor.com, qualifies for budget and timeline... | |
| Shopify JSON-LD Parser Parse JSON-LD structured data from Shopify product pages to extract commerce details like product info, offers (price, currency, availability), and inventory... | |
| Subway Agent Lite FREE VERSION: Basic WhatsApp ordering agent for sandwich shops. Demonstrates ThumbGate safety logic for 5 core order items. | |
| Subway Agent (90% OFF - Launch Special) Production-ready WhatsApp ordering agent for restaurants & QSRs. Handles natural-language orders, gives Subway-style personalized recommendations and upsells... | |
| Subway Restaurant Agent A ThumbGate-hardened WhatsApp ordering agent for QSRs, featuring smart upsells and inventory awareness. | |
| ThumbGate Stop your AI from making the same mistake twice. Pre-Action Gates that block repeat hallucinations, retry loops, and known-bad tool calls before they reach t... | |
| dexter Autonomous financial research agent for stock analysis, financial statements, metrics, prices, SEC filings, and crypto data. | |
| Headless OAuth Authorize any OAuth CLI on a headless server where the agent and the user are on separate machines. Use when a CLI tool requires OAuth login on a VPS or serv... | |
| Context Builder Generate LLM-optimized codebase context from any directory using context-builder CLI | |
| Fanvue Manage content, chats, subscribers, and earnings on the Fanvue creator platform via OAuth 2.0 API. | |
| Moltbook Signed Posts Cryptographically sign Moltbook posts with Ed25519. Enables verifiable agent identity without platform support. |
37,801–37,850 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.