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 |
|---|---|
| DirStat_Skill Use when auditing disk usage on Windows or Linux and suggesting what a human should review to reclaim space without changing files automatically, especially for caches, model files, trash, and partial downloads. | |
| yt-whisper-skill Locally transcribe YouTube videos with Whisper on CUDA and archive a URL/title-headed .txt under ~/Transcriptions/<Category>/ (auto model selection, category inference, timestamp handling, temp cleanup). Also generates a structured *_AISUMM | |
| Reavhowl Skills ReachOwl social media marketing automation for Facebook, Instagram, and WhatsApp: social listening, signal-based prospecting, cold DM campaigns, WhatsApp marketing, Facebook group posting, comment-to-DM automations, Instagram growth, lead f | |
| AI PM Agent AI-powered product management workflow agent. Use when the user wants to do product discovery, write PRDs, prioritize features, design experiments, plan laun... | |
| Deep Research Agent Deep research and analysis agent for any topic. Use when the user wants to research a topic, analyze competitors, evaluate technologies, compare tools, inves... | |
| GStack Dev Workflow Structured development workflow inspired by Garry Tan's gstack. Use when the user wants to build a feature, start a project, do a code review, or ship code w... | |
| Vocab Voyage Mcp Provides vocabulary definitions, quizzes, word lists, study plans, and context explanations for academic and test-prep exams including ISEE, SSAT, SAT, GRE,... | |
| Vocab Voyage Mcp V1.1.1 Provides standardized test vocabulary practice, definitions, quizzes, course word lists, study plans, and interactive mini-games for tests like SAT, GRE, LSA... | |
| Jaime Ball Creates clear, fact-checked press releases and related media content for blockchain and Web3 announcements, avoiding unsupported claims and hype. | |
| Fb Page Publisher Publish posts, upload photos, schedule content, read insights, and manage comments on Facebook Pages via the Graph API. | |
| Design Spec Optimizer 当用户给出一个产品或界面设计想法时，自动按标准模版范式将其优化为结构清晰、细节完备的设计描述。适用于小程序、App、网页、H5 等任何界面类产品设计任务。 | |
| Design To Code 将 TRAE design 模式的设计稿、UI 截图、Figma 链接或手绘草图转换为可直接运行的本地应用代码。支持解析设计结构、提取样式参数、生成多端响应式代码、处理资源文件，并输出可立即启动的完整项目。 | |
| Loop Engineering 基于 Loop Engineering 理念的元技能，为复杂多步骤任务构建可迭代、可验证、可安全停止的反馈闭环系统。适用于代码生成与调试、设计实现、内容创作、工具调用等任何需要多轮执行与自我修正的场景。 | |
| swagger-skills Use this skill to turn Swagger UI or OpenAPI/Swagger documentation links into organized API calling skills, including Python clients, field references, domai... | |
| F1 summary Summarize Formula 1 sessions (FP1, Qualifying, Race) using web search and fetch | |
| File share Automation skill for File share. | |
| Location Service Location-based services including geocoding (coordinates to address and address to coordinates), distance calculation, and integration with weather data. Use... | |
| Live Sports Scores & News Aggiornamenti sportivi in tempo reale tramite TheSportsDB e API-Football. | |
| Lindsay Selfie Generates a consistent selfie of Lindsay using a local reference photo and Nano Banana Pro. | |
| Quit Weed Cannabis cessation tracker and coach. Track sober days, log cravings, identify triggers, manage withdrawal, and get evidence-based craving support. | |
| Say Less Bruh Use when the user explicitly asks for shorter, more human responses with minimal formatting, usually by saying “Say Less Bruh” or asking for shorter replies. | |
| Persistent Memory Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX knowledge graph) for long-term agent recall across sessions. One-command setup w... | |
| DuckDuckGo Web Search Web search without an API key using DuckDuckGo Lite via web_fetch. Use as a fallback when web_search fails with missing_brave_api_key error, or whenever you... | |
| property.com.au Research Search property.com.au for Australian property research — valuations, sold history, suburb profiles, and property details. Use when researching property valu... | |
| realestate.com.au Search Search realestate.com.au property listings by constructing search and listing URLs. Use when searching for Australian properties to buy, rent, or sold via re... | |
| BankBridge Answer questions about the user's own money with live, read-only data from their connected US banks, credit cards and brokerages through the BankBridge MCP server. Use when the user says "how much did I spend on restaurants last month", "wh | |
| CallForMe Phone a business for the user, or call around to several businesses of a kind near a place. Use when the user says "call the restaurant and book a table", "make a reservation for 4 at 7", "book an appointment for me", "call around for quote | |
| octopost Post, schedule, queue and thread posts to X (Twitter) through Octopost, with a human approval queue (Threads after Meta approval; Bluesky, LinkedIn and Mastodon in testing). Use when the user says "post this to X", "tweet this", "post on Tw | |
| taskhold Work from the task list the user shares with their coding agents through the Taskhold MCP server (https://taskhold.com/api/mcp, Bearer key from a Taskhold setup URL). Use at the start of a coding session and when the user says "work on the | |
| ClawPay Escrow Send and receive escrow payments on Solana using ClawPay. Pay other AI agents, lock funds in escrow, confirm delivery, release payments, check receipts, and... | |
| Cartogopher Set up CartoGopher AI-native code intelligence. Gets a free 7-day trial API key and configures the MCP server automatically. | |
| Link Brain Local knowledge base for links. Save URLs with summaries and tags, search later using natural language, build collections, and review your backlog with space... | |
| Web Monitor Monitor web pages for changes, price drops, stock availability, and custom conditions. Use when a user asks to watch/track/monitor a URL, get notified about... | |
| 算算｜八字·六爻·塔罗 专业命理占卜解读技能：八字排盘（四柱/五行/神煞/称骨/大运）、六爻纳甲断卦、塔罗牌阵解读。当用户提到算命、八字、生辰、四柱、五行、排盘、运势、塔罗、抽牌、解牌、占卜、六爻、摇卦、起卦、解卦、卦象、称骨、合盘、姻缘/事业/财运问卜，或想用中国传统命理或塔罗寻求建议时使用——即使用户没明说"占卜"二字，只要意图是问运势/解卦/看盘/抽牌解读就应触发。 | |
| Business Opportunity Screenshot Generate a business opportunity Skills report with ClawHub data, open it in Chromium, and capture a full-page screenshot saved to the output directory. | |
| Feishu Book Match Fill book match results (匹配结果) and Amazon links (书籍链接) into a Feishu Bitable by querying Amazon with ISBN. Use when asked to match books, fill 匹配结果, 填充书籍链接,... | |
| mcp-to-skill Converts any MCP server into a standalone skill package with zero runtime dependencies (no MCP process required). Trigger when user says: "convert this MCP t... | |
| Forage Shopping Search and compare products across merchants. Find the best deals with price comparison and shopping recommendations. | |
| Envios Usar cuando el usuario pregunte sobre envíos, cómo enviar un pedido, tiempos de entrega, zonas de cobertura, seguimiento de paquete, código de seguimiento, m... | |
| Tmp Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. | |
| Query the PolyOx API for NBA data, Polymarket predictions, and AI matchup analysis. The analysis endpoint uses the x402 payment protocol (USDC on Base Sepolia). Query the PolyOx API for NBA data, Polymarket predictions, and AI matchup analysis. The analysis endpoint uses the x402 payment protocol (USDC on Base Sepolia). | |
| Jamdesk Docs Use when user-facing code changes need documentation — after implementing APIs, CLI commands, UI components, or config options. Triggers on 'update docs', 'd... | |
| Spec-Kit SDD GitHub Spec-Kit integration for Spec-Driven Development (SDD). Use when: (1) initializing a new Spec-Kit project, (2) creating/updating project constitution,... | |
| TwelveLabs Video Intelligence Search inside videos, generate summaries, and analyze video content using TwelveLabs video understanding AI. Use when the user wants to find moments in a vid... | |
| Lemonade Server Manager Manage Lemonade Servers natively. Use when checking system info, health status, listing available models, pulling or loading new models, completing LLM chats... | |
| Context Get comprehensive context about a location including nearby places, area description, and optional weather. Use when you need to understand what's around a l... | |
| Ev Charger Find EV charging stations along a route or near a destination using Camino AI's location intelligence with OpenStreetMap data. | |
| Fitness Finder Search for gyms, yoga studios, swimming pools, and sports facilities using Camino AI's location intelligence with AI-powered ranking. | |
| Hotel Finder Search for hotels, hostels, and lodging near landmarks, conference venues, or neighborhoods using Camino AI's location intelligence with AI-powered ranking. | |
| Journey Plan multi-waypoint journeys with route optimization, feasibility analysis, and time budget constraints. Use when you need to plan trips with multiple stops... |
40,201–40,250 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.