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 |
|---|---|
| datuma_k marthvon/datuma_k Query, validate, preview, and generate source from *.dtct data contracts and *.ngin templates. | |
| io.github.martindfarre/artifactos martindfarre/artifactos Save, version & share AI-generated HTML artifacts (canvases, dashboards, apps) as links. | |
| Lotus — AI Citation Intelligence martinendara/lotus-mcp Measure how AI assistants cite your brand. Returns measured data and ready-to-apply fixes. | |
| DAGP documentation martines90/dagp Read-only DAGP governance rules, agent quickstart and experimental society guides. | |
| dev.cz-agents/adis martinhavel/cz-agents-mcp Czech VAT-payer reliability (ADIS / nespolehlivý plátce DPH) + registered bank accounts by DIČ. | |
| dev.cz-agents/ares martinhavel/cz-agents-mcp Czech & Slovak business registry — company lookup by IČO, name, legal form, VAT. Official ARES. | |
| dev.cz-agents/cnb martinhavel/cz-agents-mcp Official ČNB exchange rates — daily & historical CZK vs EUR, USD, 30+ currencies. For accounting. | |
| dev.cz-agents/dd martinhavel/cz-agents-mcp Czech & EU due diligence in one call — facts, insolvency, sanctions, VAT, risk score, UBO chain. | |
| dev.cz-agents/eu-registry martinhavel/cz-agents-mcp EU company registry lookup: 16 countries incl. Lithuania (JAR: identity + legal status). | |
| dev.cz-agents/isir martinhavel/cz-agents-mcp Czech insolvency register (ISIR) — active/historical insolvency & bankruptcy by IČO or person. | |
| dev.cz-agents/payqr martinhavel/cz-agents-mcp European payment QR — SPAYD (CZ/SK) & EPC/GiroCode (SEPA), plus text/WiFi/vCard. Local, free. | |
| dev.cz-agents/realestate martinhavel/cz-agents-mcp Czech distressed real estate — anonymized district aggregates (k≥5). Free tier. | |
| dev.cz-agents/sanctions martinhavel/cz-agents-mcp Sanctions screening for KYC/AML — EU FSF + OFAC SDN checks for Czech companies & individuals. | |
| Palimpalem martinschenk/palimpalem-mcp Build a free website draft for a small local business from a description or its old website. | |
| app.vayapin/mcp martinshein/vayacore VayaPin MCP: pin resolution + Google Maps geocoding/places + AfterShip tracking, with BYOK. | |
| Regulations.ai — Global AI Law Tracker martinsmitcom/regulationsai AI laws from 110+ countries, enforcement actions and a 3,900-term glossary. Free, no API key. | |
| io.github.martinX308/synplex martinx308/synplex-mcp Inventory health scoring, landed cost calculation, and quick diagnosis tools for Shopify merchants. | |
| Turniermeister — Tournament Engine martymcflyjr/turniermeister Turnier engine: AI prepares a real tournament (bracket, schedule) and returns a claim link. | |
| TenderScope marutmarutyan/tenderscope-lite Public tenders (EU TED, Armenia) for AI agents: search, details, watchlists, alerts. | |
| Marvenn MCP Server marvennai/mcp-server Connect AI agents to Marvenn for outbound growth via email, voice, and LinkedIn. | |
| nimo marvtub/nimo-mcp Website monitoring: uptime alerts, page speed and Core Web Vitals with the next fix, cron check-ins. | |
| finance.marx/marx-finance marx-finance/marx-fin Autonomous AI agents research market events and publish aggregated forecasts. | |
| OpenClaw FinOps maryadawson-code/openclaw-finops Verified cloud cost forecasting for AI agents. AWS, GCP, Azure pricing matrix. | |
| io.github.masa-san-jp/aiko masa-san-jp/agent-aiko A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code | |
| Jet Browser Verifier masakaai/jet-browser Verify an isolated WPE WebKit runtime with native-input, DOM, PNG, and cleanup evidence. | |
| Ajisai masamoto1982/ajisai Exact rational and algebraic computation, with machine-readable Word contracts, in Ajisai. | |
| ハルCMS (HARU CMS) masato-haru/webharu-cms 日本語ヘッドレスCMS。記事の作成・更新・予約公開・画像取り込みをAIから実行できる。APIキーで接続、npm不要。Astro/Next.js等へ配信APIで届く。 | |
| KarmoLab mascari4615/mascari4615.github.io MCP server for what LLMs get wrong: exact hashes, real randomness, and Korean rules. | |
| io.github.mashware/domain-memory mashware/domain-memory Local-first MCP server serving a project's business-domain knowledge to MCP-compatible agents. | |
| MaskFlow PII proxy maskflow/maskflow Mask PII in outbound MCP tool-call arguments, unmask the results. Indian identifiers included. | |
| LearnThat MCP masmedeam/learnthat Remote MCP learning coach for coding agents. | |
| Galactic masonicgit/intergalactic-data On-chain asset, market, and GPU price data for galactic.inc. | |
| io.github.MassimoSun/smsverbot-mcp massimosun/smsverbot-mcp SMS verification for AI agents: buy a number, get the code, cancel with refund. Free sandbox. | |
| CompareGraph massrelay-ai/comparegraph Compare cloned repositories against taxonomy packs: one code graph, cited claims, a matrix. Local. | |
| io.github.MastadoonPrime/agent-memory mastadoonprime/agent-memory Persistent, agent-owned memory with encrypted storage and shared knowledge commons. | |
| Austria Property mastalier1997/austria-property-mcp Austrian property costs, buy-to-let underwriting, income tax and rent caps, cited to the statute | |
| DiscountHub - Deals & Promo Codes masterbek533551878/discounthub Find real discounts, promo codes and online deals with DiscountHub MCP. | |
| Mastercard Developers MCP mastercard/developers-agent-toolkit Access Mastercard Developers APIs, documentation, and API specifications through MCP. | |
| FaintMark matchalatteguy/faintmark Invisible per-recipient image watermarks. Mark one copy per recipient, then identify a leaked copy. | |
| MatchAwards matchawards/matchawards-mcp Search US government contracts, grants and jobs from matchawards.com. Read-only, no key. | |
| NYC Property & Venue API matchup-labs/nycapi NYC property intelligence, building violations, and restaurant/venue compliance via MCP. | |
| NYC FHV Intelligence API matchup-labs/nycfhv Real-time NYC TLC for-hire vehicle license verification and renewal-window lead lookups via MCP. | |
| matchwire.win — Mapped Prediction Markets (Kalshi, Polymarket, Predict.fun) matchwire-win/matchwire-sdk One row per game, matched across Kalshi, Polymarket US/Intl and Predict.fun. Mapping only. | |
| ReelsFarm mateohysa/reelsfarm-mcp Create, manage, schedule, and publish short-form user-generated content through AI agents. | |
| io.github.MaterialModel/materialmodel materialmodel/materialmodel-integrations Explore discoveries, ask questions, share findings, and build collaborations with other agents. | |
| MaterialsCodeGraph materialscodegraph/materialscodegraph Materials simulations for AI agents over MCP: binding token quote before every run, record after it. | |
| ai.bridgeapp/bridgeapp mathandmagic/bridgeapp-plugin BridgeApp workspace over MCP: tasks, chats, threads, pages, and projects. | |
| Roamer MCP mathismeadows/roamer-mcp-plugin Hosted MCP server and Agent Skills for specs, engineering threads, and project memory. | |
| FRAIM mathursrus/fraim Accountable AI workforce workflows with jobs, skills, rules, evidence, and mentoring. | |
| Lumae matlegault/lumae-releases Record, cut, zoom, caption and export software demos from an agent. Requires Lumae for macOS. |
26,301–26,350 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.