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 |
|---|---|
| Automatic Video Face Blur MCP: Reversible, Restore Original — NoonAI DIS Automatic hosted video face blur and redaction, reversible, restore original, $3/video. NoonAI DIS | |
| Automatic Video Face Detection & Blur MCP, Restore Original — NoonAI DIS Automatic hosted video face detection and blur in one call; reversible, restore original. NoonAI DIS | |
| Automatic Video Face & Person Masking MCP with Original Restore (Reversible) — NoonAI DIS Automatic hosted video masking of faces, bodies, plates; restore chosen people; $3/video. NoonAI DIS | |
| Automatic Video De-identification MCP: Mask People & Faces, Restore Original — NoonAI DIS Automatic hosted video masking of faces, bodies, plates; restore chosen people; $3/video. NoonAI DIS | |
| Automatic Video People De-identification MCP, Reversible Restore — NoonAI DIS Automatic hosted video de-identification of people and faces; restore original; $3/video. NoonAI DIS | |
| Automatic Video Privacy Masking MCP: Faces, People, License Plates — NoonAI DIS Automatic hosted video masking: faces, bodies, plates supported now; reversible; $3/video. NoonAI | |
| Automatic Video De-identification MCP: Reversible Masking, Restore Original — NoonAI DIS Automatic hosted video de-identification (비식별): mask all, restore chosen; $3/video. NoonAI DIS | |
| Automatic Video Mosaic & Masking MCP (동영상 모자이크), Restore Original — NoonAI DIS Automatic hosted video mosaic of faces/people/plates (동영상 모자이크); reversible, $3/video. NoonAI | |
| Dynomatix Enquiries for Dynomatix, a software practice. | |
| DZPage DayZ Tools DayZ items, loot spawns, infected, game updates, community servers and server config checks | |
| e-eSIM Catalog Search travel eSIM data plans worldwide with live prices, plan details and a buy link. | |
| E-Labus Your lab results and health record in Claude: trends, retests, meds, conditions and symptoms. | |
| Eachspy Facebook ads library with spend estimates and advertiser stats, plus Shopify product research. | |
| com.eacpartners/concierge Public tools for EAC Partners: offerings, insights, and appointment requests. | |
| Eagle Virtual USDT & USDC Blacklist Tracker USDT & USDC blacklist, freeze and seizure records for any wallet. Dated, cited, no risk scores. | |
| EarningsWatcher Options-implied earnings moves, 10y implied-vs-actual history, IV rush/crush, scanner, simulator. | |
| Earnings Feed SEC filings and insider trades in real-time. 10-K, 10-Q, 8-K, Form 4, and company lookup. | |
| HandleWise AI Turn photos of your items into scheduled eBay listings on your own eBay seller account. | |
| easiapiai - LLM API prices LLM API prices by seller: cheapest offer per model, list prices, cost estimates, agent Q&A board. | |
| Easy Email Verification Verify email addresses before you send: single, batch (50) and bulk lists (10,000). | |
| 투표함 — 전자투표 법령 자료 (Korean e-voting statutes, quorum & consult) Korean e-voting statutes, quorum judgement, fee quote and consult request. 10 tools, no auth. | |
| Easy MCP AI — Connector for Claude, ChatGPT & SEO Data Connect any AI to WordPress — content, media, SEO, WooCommerce, GA4, Search Console. 242 tools. | |
| Loyalist Reservations Book tables at restaurants on the Loyalist network. No login; read availability, then book. | |
| eatmundo Cross-cuisine dish equivalence with shared-ingredient evidence: nearly 2,000 dishes, 26 cuisines. | |
| ECCA Compare engine claims, inspect dissent and check study evidence for student questions. | |
| com.eckari/capabilities Deterministic company, entity and location lookups for agents - per call, x402 or API key. | |
| EclipseMission Where to see the 2 August 2027 total solar eclipse: destinations, totality, lodging cost, flights | |
| ECZ-ID Trust MCP Read-only ECZ-ID Business Passport state lookup via the public ECZ-ID Resolver. Reports state only. | |
| ecoExperten Energieausweis Order official German energy certificates (Energieausweis) from chat — on invoice, 1-2 days. | |
| ecomdly E-commerce skills for AI agents: feeds, Google Shopping, GA4. Your private Brain when signed in. | |
| Ecomhint Ecommerce store audits: read findings with evidence and fix steps, track tasks, run new audits. | |
| EcomScout Shopify store intelligence: traffic, revenue, products, competitors, trends across 1M+ stores. | |
| Ecomwith Commerce Desk Break-even ROAS and profit calculators, UTM link builder, and Ecomwith tutorial and report search. | |
| EconomicsAPI Macroeconomic, trade, FX and commodity data for 50 countries over one MCP endpoint. | |
| Ecuafact API · Documentación Documentación de Ecuafact API: facturación electrónica del SRI de Ecuador. Sin credenciales. | |
| EdgarStack SEC EDGAR financials, ratios, peer comps, filing diffs and Excel models for any MCP client. | |
| com.edgethirteen.www/accessproof Scan a web page's markup for the WCAG failures ADA demand letters cite most often. | |
| com.edgethirteen.www/advisor-letter Weekly white-label market-commentary draft advisors send to clients under their own name. | |
| com.edgethirteen.www/ai-disclosure-kit EU AI Act Article 50 transparency kit: disclosure text, embeddable banner, compliance record. $59. | |
| com.edgethirteen.www/altman-z-score-calculator Altman Z-Score bankruptcy-risk screen for a US-listed ticker, inputs looked up automatically. | |
| com.edgethirteen.www/apidrift Alerts on breaking changes, deprecations, and pricing shifts across major LLM provider APIs. | |
| com.edgethirteen.www/bank-stress-dataset Pricing/details for a CSV of every FDIC-insured bank's stress metrics from its own Call Report. | |
| com.edgethirteen.www/chargeback-response Draft a chargeback dispute-response evidence checklist and letter preview from order details. | |
| com.edgethirteen.www/cloakcheck Scan a page for content planted to hijack an AI browsing/shopping agent before it acts on the page. | |
| com.edgethirteen.www/commentlettercheck Look up whether a US ticker has SEC comment-letter correspondence on file. | |
| com.edgethirteen.www/dcf-calculator Discounted-cash-flow intrinsic value per share from growth/discount/terminal assumptions. | |
| com.edgethirteen.www/drop-compliance-kit Check a California data broker's next DROP 45-day deletion-request check-in deadline. | |
| com.edgethirteen.www/exploitwatch Check a dependency list against CISA's live Known Exploited Vulnerabilities catalog. | |
| com.edgethirteen.www/gateway All 36 Edge Thirteen MCP tools (SEC filings, WCAG, entity diligence, more) in one endpoint. | |
| com.edgethirteen.www/graham-number-calculator Benjamin Graham's fair-value ceiling and margin of safety for a US-listed ticker. |
31,101–31,150 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.