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 |
|---|---|
| seoskills.sh Search and fetch SEO agent skills from the seoskills.sh catalog. | |
| supercomputer GPU compute for agents: run commands on an L4/A100/H100, watch logs, billed per second. | |
| AI Cloud Studio — Turnkey Multi-Agent SaaS & Digital Bundle Hub Inspect SHA-256 verified SaaS release archives, run live GEO/B2B/Legal audits & submit offers. | |
| CitePulse AI Mirror — GEO & LLM Citation Readiness MCP Server Audit domains for ChatGPT, Perplexity & Claude GEO citation readiness and llms.txt compliance. | |
| LexiShield AI — 6-Agent GDPR, EU AI Act & Contract Redlining Server Run deterministic SaaS contract redlining, GDPR Art. 28 DPA & EU AI Act compliance audits. | |
| AI Cloud Studio Storefront — 5-in-1 Digital Bundle & SaaS Buyout Hub Download verified SaaS source code, PDF/DOCX/PPTX executive packs & x402 agent kits. | |
| NexusSDR AI — 4-Agent B2B Buying-Intent & Outbound MCP Server Generate B2B buying-intent dossiers, ICP signals & multi-touch outbound sequences via MCP & x402. | |
| Onchain Intel (x402) Pay-per-call crypto intel via x402: honeypot/rug check, whale flows, unlocks, MEV, liquidation risk | |
| Gateway SSH Manage servers through SSH. | |
| uldl Persistent file storage for AI agents via MCP and curl. Upload, download, and version files. | |
| Volley Write, check, render and save sequence diagrams with the request and response on every arrow. | |
| whatsapi.sh Send WhatsApp messages from your own numbers, read and answer chats, and send sign-in codes. | |
| colegios.shop — uniformes escolares Tiendas de uniformes escolares: buscar prendas, talles y armar el carrito. | |
| eglise.shop — Christian bookstore (FR/EN) Christian bookstore (French/English): search books, prices in 12 currencies, cart, checkout link. | |
| NotRobophobic shop Machine-history prints, merch and £4 print files at notrobo.shop, run by an AI. Cards for downloads. | |
| Ocapi Run an Ocapi online store that takes orders via WhatsApp: products, categories, orders, images. | |
| Супермаркет САМПО Каталог и заказ супермаркета САМПО. Оплата на странице банка. | |
| The Others The Others — an agentic t-shirt shop. Browse products and buy t-shirts via AI agents. | |
| Tier1.shop — SEO Link Placements Buy and manage RU PBN and international iGaming SEO links with protected Tier1.shop checkout. | |
| Global Connect Show (GCS) Media and business events at CES, IFA and GCSx cities: events, newsletter, brand and media sign-up. | |
| AgentKernel AI model data Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives. | |
| AgentMaverick News Free sourced breaking news for agents: markets, crypto, tech, geopolitics, US politics. A2A+RSS too. | |
| Aya Studio Make cartoons with consistent characters: pictures, animated clips, talking characters and songs. | |
| Bloki.si Slovenian property registers: addresses from adverts, buildings, sale prices, plans, surroundings. | |
| BOZOS Exact source text, not summaries: check citations and quotes in one call; read pages and PDFs. | |
| Cockpilot Run an agency's tasks, projects, clients and KPIs from Claude or any MCP client. OAuth, per team. | |
| Copix Copywriting assistant: the method for each ad, page and email, a line-by-line review, SEO and GEO. | |
| Courio Mail real paper letters (standard, registered, registered with receipt) worldwide. No account. | |
| Dashly Track anything by telling your AI: calories, habits, mood, spending and tasks on one dashboard. | |
| Digital Garden by Alicia — Notes Search and read Alicia's English and Chinese notes on Houdini, Three.js, OpenUSD and AI workflows. | |
| divux Official data for AI assistants: medicines, recalls, cosmetics, money, travel, places, prices. | |
| DomainSpace Register .si domains, manage DNS, and give your AI agent an email inbox on your own domain. | |
| FindADoctor.si France Find doctors in France by condition, procedure or place, with fee category and sources. No sign-up. | |
| FindADoctor.si New Zealand Find New Zealand doctors and GP practices by condition, procedure or place, with sources. No signup. | |
| FindADoctor.si Find US, New Zealand and France doctors by condition, procedure or place, with sources. No sign-up. | |
| fourzerotwo 400+ data APIs for agents: UK companies, property, trade, tenders, recalls, sanctions. Free tier | |
| Environment & energy UK river levels and rainfall, bathing waters, flood warnings, weather, earthquakes and the GB… | |
| Health & medicines Clinical trials, RxNorm drug lookups, FDA drug and device data, PubMed and NHS organisations. | |
| Research papers arXiv, PubMed, Crossref and OpenAlex scholarly metadata. | |
| Product safety & recalls UK product recalls, MHRA drug and device alerts, FSA food alerts, accident reports and US CPSC… | |
| Everyday agent tools Time zones and world business days, VAT rates and maths, currency conversion, UK business days… | |
| Trade & public tenders UK commodity codes and duties, UK trade statistics, UK/EU public tenders and US federal spending. | |
| Transport & travel Airports, runways and frequencies worldwide, tides, UK road collisions and London transport. | |
| UK company & compliance data Companies House, Gazette notices, sanctions screening, LEIs and UK legislation. | |
| UK property & area data Sold prices, area reports, postcodes, flood risk, crime and food hygiene for any UK location. | |
| UK public services NHS organisations, schools, care quality ratings, food hygiene and policing for any UK area. | |
| Web & domain tools Read any public page as markdown, link previews, URL safety, page audits, domain availability and… | |
| Hivex: .si names, DNS and WHOIS Find and check free .si names (600,000+ indexed), and look up DNS and WHOIS for any domain. | |
| humancollab Trust layer between AIs and humans: signed, domain-verified information in a public, verifiable log. | |
| ImageCompressor.si Compress, convert, resize, crop, upscale, OCR and remove backgrounds from images. |
43,451–43,500 of 50,909
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.