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 |
|---|---|
| KGLD Reserve Attestation KGLD gold-token reserve proof: custody vs supply, auditor report hash, human verification by email | |
| my.wimm/wimm Personal finance for AI agents — onboard, import statements, categorize & budget over MCP. | |
| Findadomain.name Find domains and domain hacks with live availability, registrar prices, and keyword search demand. | |
| 0bull Phone Farm Manage social accounts, publish videos, and control real iPhones rented by the month. | |
| Agriturismo.Net Cerca agriturismi su Agriturismo.net e verifica disponibilità, prezzi e condizioni. | |
| a9n9 Deep Research Objective-driven deep research: free daily quick search plus MPP-paid cross-source browser reports. | |
| Agent Control — Action Gate Agent asks a person go/stop/wait before Slack, CRM or risky steps. $49 for 30 days. | |
| AgentCalls AI voice agents on real phone numbers: build agents, place and receive calls, read call summaries. | |
| Agent Chef Family meal planning run by your agent: weekly dinners, household votes, grocery list minus pantry. | |
| AgentContinuity Private memory, scratchpads, context export/restore and task handoff for AI agents. | |
| net.agentglass/agentglass Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth. | |
| net.alpha-systems/pdf Markdown to PDF: headings, bold, code, lists, rules. A4/Letter/Legal. Free 30/hr. MCP + REST. | |
| AlphaYou API SEC filings, 13F funds, insider trades and published calls, each with its source link. | |
| AlphaYou: Smart Money Intel US stock filings, funds, insiders and Hyperliquid wallets, with sources and dates. Read-only. | |
| Andrii Co. Notary & Apostille Assistant Book a Washington notary or apostille appointment, get a quote, and track it, via AI assistant. | |
| AppPage.net - app websites & store data App websites with privacy pages and app-ads.txt, plus Google Play & App Store app data. | |
| ashare.net Share what AI agents write with the right people only: your company, specific emails or a password. | |
| AssistAnt 24/7 pro directory Local tradespeople: 823,000+ US businesses in 38 trades. Verified first; no paid placement. | |
| AutomateSocials Write, schedule and publish social posts to Facebook, Instagram, X, LinkedIn and TikTok. | |
| BaldFade List the bald, buzz cut and fade hairstyles BaldFade can preview. Read-only, no account needed. | |
| Balford metalworking engineering answers Metal stamping, deep drawing and DFM answers from Balford's own published engineering pages. | |
| BananaSplit Track shared expenses, payments and balances across BananaSplit groups and friends. | |
| cardmarket-mcp Read-only BYO-key MTG/TCG pricing MCP with repricing suggestions. AI-authored. | |
| DevKit quick-tools Developer utilities MCP server: base64, hash, slug, uuid v4, timestamp, urlencode. Free, no key. | |
| paycheck Verify USDC payments and balances on Base mainnet: check_payment, get_balance, decode_tx. | |
| BitBusca Empresas CNPJ, empresas em lista, publicações do DJEN, prazos, editais de licitação e advogados do Brasil. | |
| BizFetch Judge Japanese companies against your criteria using Japan's public data (gBizINFO, NTA, EDINET). | |
| Bookmax Official Bookmax MCP server: search and save bookmarks, read notes and docs from AI assistants. | |
| Kashif Scores a website's online presence 0-100 and lists the top issues to fix. English/Arabic. | |
| net.brazilian-bikinis/mcp Brazilian Bikinis swimwear catalog and orders via AI agents | |
| Campaignly Plan, launch and report on local marketing campaigns across Google, Meta and LinkedIn. | |
| CastHost — AI Agent Control for Radio Control your internet radio from any AI client: listeners, stream, playlists, AutoDJ, DJs, store. | |
| Chatinbox Read-only WhatsApp conversation stats for Chatinbox customers. Numbers only, no personal data. | |
| CheckMyVIN Decode US-market VINs and list NHTSA recall campaigns for the make, model and year. Free, no auth. | |
| Chorus Run ad campaigns on Meta, Google Ads and LinkedIn from your assistant. Spend waits for your OK. | |
| Pulse Analytics MCP server Read-only web analytics from Pulse: your sites, totals, trends, breakdowns and realtime visitors. | |
| ClearBounce Email Verification Verify email addresses in real time and find business email addresses with live mailbox checks. | |
| net.composedchaos/speed-to-lead Field-service tools for agents: slot feasibility, drive time, service area, lead parsing, booking. | |
| CompressGIF Compress GIFs from HTTPS URLs, poll results, and check credits. Hosted MCP with API key auth. | |
| CryptoSocials Research Crypto X posts, assets and authors with source links, chain filters and stored prices. | |
| net.csclear/wire Agent-native ODW wire: discovery + full MCP courier for signed dealing envelopes. | |
| cwsi.net Fare Classes & Mileage Calculators Airline fare classes, fare comparisons and miles earned, from cwsi.net's charts and calculators. | |
| Deepgent Company analytics for Deepgent workspaces: usage, conversations, quality, billing, KB status. | |
| Dekadans ASO App Store keyword rankings, popularity, difficulty and keyword research across 175 storefronts. | |
| Dexi Notes Search and manage your Dexi notes: full-text and semantic search, tags, folders, spaced repetition. | |
| Open Design MCP Open Design MCP capability governed by DigitalPipe. | |
| Premium Test MCP Premium test server verified via DNS-TXT. | |
| Domandata Build, preview, deploy and export academic surveys: blocks, flow logic, experiments, quotas, data. | |
| Duffer Golf Read-only Duffer Golf facts: models and prices, room fit, FAQ, dealers and contact. | |
| 1RBT terse agent record Record agent tasks, get back how many finished without a human. Closed beta, nothing billed. |
42,451–42,500 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.