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 |
|---|---|
| io.github.jeff-nasseri/revolut-mcp jeff-nasseri/revolut-mcp MCP server for the Revolut Business API: accounts, transactions, payments, FX, and more. | |
| HonkIO jeffcaldwellca/honkio Canadian SMS and email API for AI agents: send SMS and email, verify phones, handle CASL consent. | |
| health4ai jefflitt1/health4ai Query your Apple Health data from your own Supabase/Postgres via local MCP. | |
| Variel MCP Server jeisenberg/ai-brand-studio Generate your brand in-agent, then keep tokens, components, and copy on-brand over MCP. | |
| TOVREK Current-State Resolver jekaterinavaivade-del/tovrek Verify DOI metadata before autonomous action; preserve conflicts, provenance, and UNKNOWN. | |
| Model Tested jelly-ham/modeltested Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons. | |
| Jellypod jellypod-inc/frontend-website-v2 Create, import, and publish Jellypod podcast episodes from your AI assistant. | |
| Jenesis Travel jenesistravel/jenesistravel-nextjs Bangkok boutique planner: live Thailand journeys, prices, FAQs, and enquiry handoff. | |
| Jockey Delivery — Same-Day Local & Nationwide AI Commerce jennipro-engineering/jockeyvc-gmc-engine Search live store shelves, verify delivery windows, and run instant AI agent checkouts. | |
| macOS-MCP jeomon/macos-mcp MCP server for macOS desktop automation via the Accessibility API. | |
| Jepto jepto/mcp Live Google Ads, GA4, Search Console, Meta Ads and GBP data in Claude, ChatGPT and any MCP client | |
| io.github.jeremdecustovox/custovox-sentiment jeremdecustovox/custovox-ai custovox.ai multilingual customer sentiment analysis MCP server (EN/FR/DE/ES/PT-BR) | |
| DanBooks — AI Bookkeeping jeremiahclark79-ai/clark-seed AI bookkeeping for small business. Create invoices, log expenses, and check P&L by voice or text. | |
| Product Pillars jeremybelcher/product-pillars-agent-kit Flowcharts that people and agents edit together on one live canvas, exported as Mermaid. | |
| com.skipshit/mcp jeremynashrei/skipshit People and property search for Claude and ChatGPT. Phones, emails, addresses, relatives, properties. | |
| dev.mcpgrade/mcp jeremyrx7/mcpgrade Security grades (A-F) for MCP servers. Check one before you install or trust it. mcpgrade.dev | |
| Heartwood Memory — governed memory for AI agents jermayne36/heartwood-memory Heartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source. | |
| FERS — structural FEM jeroen124/fers_core Structural FEM for AI agents: frames, plates, buckling, seismic and Eurocode checks, solved locally. | |
| B2B Compliance, KYB, Cyber & GovCon Suite (31 Tools) jesleytassili-glitch/b2b-quant-mcp-n8n-suite 31 stateless B2B tools for KYB, OFAC sanctions, SEC EDGAR, CISA CVEs, FDA, tenders & tax audits. | |
| Brazil Tax Reform IBS/CBS, CNPJ QSA, BCB PTAX & Pix KYB jesleytassili-glitch/b2b-quant-mcp-n8n-suite Audit Brazil LC 214 NCM tax reform, CNPJ QSA partners, BCB PTAX/Selic, Pix ISPB, TISS XML & ANTT. | |
| CISA KEV Ransomware CVE, SSL CT Logs & Domain Recon jesleytassili-glitch/b2b-quant-mcp-n8n-suite Audit active CISA KEV ransomware CVEs, SSL/TLS CT log subdomains, SPF/DMARC security & ICANN RDAP. | |
| US SAM.gov, EU TED & Brazil PNCP Public Tenders Radar jesleytassili-glitch/b2b-quant-mcp-n8n-suite Monitor live government contracts and tenders across US Federal awards, EU TED OJ S & Brazil PNCP. | |
| US Healthcare NPI Leads, FDA Recalls & ClinicalTrials jesleytassili-glitch/b2b-quant-mcp-n8n-suite Extract CMS NPPES healthcare provider leads, FDA safety recalls & NIH ClinicalTrials.gov sponsors. | |
| Global KYB, OFAC Sanctions, GLEIF LEI & EU VAT Auditor jesleytassili-glitch/b2b-quant-mcp-n8n-suite Screen OFAC/UN/EU sanctions, verify GLEIF LEI ownership, UK Companies House/FCA & EU VIES VAT IDs. | |
| US SEC EDGAR Filings, FDIC Bank Solvency & EPA/OSHA jesleytassili-glitch/b2b-quant-mcp-n8n-suite Analyze SEC EDGAR 10-K/8-K/Form 4 filings, FDIC bank solvency ratios, EPA ECHO & OSHA violations. | |
| com.engagedviews/youtube-thumbnail-sizes jesse-lucas1996/agentic-business YouTube thumbnail and title shelf sizes, measured. Not affiliated with YouTube or Google. | |
| io.github.jessedu29260-netizen/bakeryos jessedu29260-netizen/bakeryos-ios BakeryOS bakery-management MCP — recipes, costs, production; propose changes via OAuth. | |
| NegativeEV bet checker jessejohnsohn/negativeev-mcp Grade any MLB, WNBA, PGA or ATP bet against thousands of play-by-play sims. No key, no signup. | |
| io.github.jessemarshall/coalesce-transform jessemarshall/coalesce-transform-mcp MCP server for managing Coalesce Transform workspaces, nodes, pipelines, and runs. | |
| Omnier jessesorsa/omnier-mcp-server Turn signals from email, CRM, and meetings into a prioritized daily sales to-do list. | |
| NOVA jessicaespinal777-cloud/nova-x402-service Paid NOVA research, company intelligence, and output recovery for agents. | |
| toolprint by JEStats jestatsio/toolprint package-lock.json for MCP trust: catch MCP rug-pulls, tool poisoning, and leaked secrets. | |
| Blocksize Agentic Market Intelligence jf-cmyk/agentic-payments Multi-venue VWAP, bid/ask, crypto FX, metals and equities with provenance receipts for AI agents | |
| io.github.jfarcand/iphone-mirroir-mcp jfarcand/iphone-mirroir-mcp Control a real iPhone through macOS iPhone Mirroring: screenshot, tap, swipe, type. | |
| The Profound Agency jfromtheroc/the-profound-agency Search, price and order press placements across 1,600+ publications. Free AI-visibility audits too. | |
| ForensiScope by Evercraft jgaethle10/forge-operator Start with classify_media_route to route long or oversized audio/video by size or duration. | |
| Veredicto Humano jgsierra/veredicto-humano-x402 Ask a real human (not an LLM) for a judgment, $0.10 USDC via x402. The result returns to the agent. | |
| co.heyspark.mcp/server jhibird/heyspark-mcp Search and discover local businesses. 30+ categories with verified contact info, hours, and reviews. | |
| OpsDoctor jhicks935-lab/resolution-ai AI-powered CRM diagnostics, workflow audits, and industry benchmarks for SMBs. | |
| rasterly jhonychain/rasterly-mcp Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site. | |
| Fjord jhtjernsmo/fjord Local kanban boards, markdown notes and Git/GitHub/Azure DevOps work from the Fjord app. | |
| Papertext jhytabest/papertext Academic literature search, retrieval, and private library management on top of OpenAlex. | |
| Frisk jiangw2718i/frisk Screen the counterparty of an x402 payment before an agent pays it. Runs offline by default. | |
| Jackpot Calculator jiankn/jackpot-calculator-mcp Estimate US lottery taxes, compare cash and annuity, split pool prizes and calculate jackpot odds. | |
| geo-score jianruntech/geo-score Free 0-100 score: can AI engines cite a site? Plus citation checks with your own API keys. | |
| HEIC To JPG jim-panse/heic-to-jpg-mcp Local macOS HEIC-to-JPEG server. Shareable defaults: 1600 px, quality 70. | |
| PDF To Text jim-panse/pdf-to-txt-mcp Extracts PDF text locally, with macOS PDFKit and Vision OCR fallbacks and optional AI retry. | |
| MemoTrader MCP Server jimbursch/memotrader-mcp AI-to-human attention marketplace. Agents pay CPM to reach humans, earn credits by replying. | |
| RugRadar jimmybr-pdx/x402-seller Solana token danger warnings: rug, token-safety and honeypot checks $0.01; watch alerts $0.05/24h. | |
| BibiGPT YouTube Video Summarizer jimmylv/bibigpt-skill AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos. |
24,351–24,400 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.