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 |
|---|---|
| com.edgethirteen.www/hubspot-dbv Free map of HubSpot legacy v1-v4 API operations to their date-based-versioning replacements. | |
| com.edgethirteen.www/industry-primers Pricing/details for Edge Thirteen's current industry primer, sourced to each firm's own 10-K. | |
| com.edgethirteen.www/kdpcheck Scan manuscript text for AI-slop prose patterns before publishing to Amazon KDP. | |
| com.edgethirteen.www/killcord Dead-man's switch for Anthropic API spend: kills the key the instant it crosses a limit you set. | |
| com.edgethirteen.www/lite 36 SEC, WCAG and entity-diligence tools behind 2 low-context ones: discover_tools, call_tool. | |
| com.edgethirteen.www/meterkit Drop-in usage credit ledger plus current Stripe Billing Meter Events integration for Next.js. | |
| com.edgethirteen.www/numbercheck Checks $TICKER numeric claims in financial writing against SEC EDGAR XBRL data from the latest 10-K. | |
| com.edgethirteen.www/postingcheck Scan a job posting against 16 US state/DC pay-transparency disclosure laws. | |
| com.edgethirteen.www/pumpcheck Detect npm download-pumping before adding a dependency: real usage vs inflated counter. | |
| com.edgethirteen.www/renewal-matrix Score a subscription cancellation flow against federal, CA, CO, VT, and OR click-to-cancel laws. | |
| com.edgethirteen.www/rewardsguard Spot-check a TikTok creator export for Creator Rewards disqualification risk. | |
| com.edgethirteen.www/sanctions Screen a name against OFAC's SDN and Consolidated Sanctions lists before a transaction. | |
| com.edgethirteen.www/site-audit Discover a site's pages from its sitemap and sample them for WCAG and prompt-injection risk. | |
| com.edgethirteen.www/slopcheck Check a YouTube channel's recent uploads against YouTube's 2026 inauthentic-content policy. | |
| com.edgethirteen.www/stackledger Audit a pasted SaaS subscription list for redundant-category overlap and overspend. | |
| com.edgethirteen.www/tariff-refund-screen Screen US public companies for IEEPA tariff-refund exposure disclosed in their SEC filings. | |
| com.edgethirteen.www/triageshield Verify a vuln report's file/line/function claims against a real GitHub repo. | |
| com.edgethirteen.www/us-diligence Screen a US company against SEC EDGAR, OFAC sanctions, federal awards and federal court dockets. | |
| com.edgethirteen.www/valuefeed Weekly SEC-sourced research packet licensed for newsletter writers to build commentary on. | |
| com.edgethirteen.www/vercelpycheck Scan a public GitHub repo for known Vercel Python-runtime deploy footguns. | |
| com.edgethirteen.www/voicebrief SEC-grounded stock facts phrased as single spoken sentences for a voice assistant to read. | |
| Edgible Read your Edgible applications, devices, deploy status and logs, signed in as you. | |
| eDiscovery Decoder News/Calc Free educational MCP for read-only eDiscovery news and TAR/review calculators. | |
| Educaplay Create, edit and publish Educaplay educational games and quizzes from any AI assistant. | |
| Edwyna Fax API Send individual transactional faxes with prepaid credit, delivery status, and safeguards. | |
| Eesier — AI Lead Prospecting Autonomous B2B lead prospecting — 36 tools for campaigns, leads, and email outreach. | |
| eFon international call rates & VoIP International call & VoIP rates: per-minute prices to call 200+ countries, comparison, dialing help. | |
| com.eformogi/records-vault The family's agent reads the record, drafts the filing from verified rules, asks for a signature. | |
| Egleze Search verified podcast moments and episode summaries with canonical Egleze links. | |
| Egnyte Remote MCP Server Egnyte's remote MCP server for secure AI access, search, upload and file management in your account. | |
| Eidari A profile you control: gives your AI your role, projects and preferences, across ChatGPT and Claude. | |
| Counterfoil Read stored EU e-invoice rule notes and the invoice field map. Not a validator. | |
| E-Invoice Map Free, read-only e-invoicing data: mandate dates, Peppol providers, validation-error explainers. | |
| com.einvoicewiz/einvoicewiz Generate & validate EN 16931 e-invoices (Factur-X, ZUGFeRD, XRechnung); verification certificates | |
| ELDRICK Golf Club Fitting Golf club fitting MCP server: fits drivers, woods, hybrids, irons and wedges; scores real clubs. | |
| ElectionsMCP Model and map any 2028 U.S. race down to the precinct: scenarios, swing, turnout, and roll-ups. | |
| com.electricskateboard/electricskateboard Live prices for e-skateboards, onewheels, scooters and e-bikes: buy now or wait, with the evidence. | |
| Electronics Architect Solve a DC/DC power tree: per-stage current, efficiency, dissipation, thermals, tolerance corners. | |
| Elements Live Research intensity for 118 elements and topics, ~10M papers. Free element scores; x402 pay-per-call. | |
| com.eleyed/redact Redact PII from text before it reaches a model. Nothing stored, no third-party AI. | |
| ElfHosted: my stack Your own ElfHosted apps: health, libraries, settings, and changes you approve. Needs an account. | |
| ElfHosted Hosted AIOStreams, Immich, OpenClaw, Hermes and more open-source apps: prices, trial. No account. | |
| com.eligiblebydescent/site Eligible By Descent: the site's own MCP server — checker, enquiry (enquiry = a human handoff,... | |
| async.elixirconf ElixirConf's community site: conference schedules and a member's starred talks, over MCP. | |
| com.ellomind/therapy-booking Check live availability and book therapy sessions with a Malayalam-speaking psychologist. | |
| Elocuenti Manage your Elocuenti AI sales agents, CRM, campaigns and analytics from Claude. | |
| EloEdge: Kalshi model probabilities Calibrated probabilities for Kalshi markets, a news wire and Polymarket outliers (Pro). | |
| EloEdge Data: prediction-market and price history SQL over EloEdge's model record, 1-second crypto prices, Polymarket US listings and calendars. | |
| El Paso Air — book AC repair in El Paso Book AC repair in El Paso, TX: prices, service area by ZIP, free callback from a local pro. | |
| Elsewhere (elsewhereagents.com) A persistent world at elsewhereagents.com for AI agents from any provider: explore, trade, govern. |
31,151–31,200 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.