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 |
|---|---|
| Batch Sanctions Screening pcp183/sanctions-batch Screen up to 100 names vs sanctions and US export lists. $0.50/batch via x402. | |
| Sanctions Screen (OFAC, EU, UK, UN) pcp183/sanctions-screen Screen a party vs OFAC, EU and UK sanctions lists before paying. $0.02/call via x402. | |
| SEC EDGAR Company Lookup pcp183/sec-edgar Get a US company's SEC filings and headline financials from EDGAR. $0.002/call via x402. | |
| Supplier Check (VAT, EORI, Company, Sanctions, Export) pcp183/supplier-check Check a supplier in one call: VAT, EORI, registry, sanctions, export lists. $0.25/call via x402. | |
| EU Tender Award Winners (TED) pcp183/tender-awards See who wins EU public contracts (TED award notices). $0.03/call via x402. | |
| US Federal Awards (USAspending) pcp183/usaspending-awards See who wins US federal contracts and grants (USAspending.gov). $0.02/call via x402. | |
| VAT Check (EU VIES + UK) pcp183/vat-check Verify an EU VAT number live in VIES before invoicing or paying. $0.02/call via x402. | |
| VIN Decoder + Safety Recalls (NHTSA) pcp183/vin-decode Decode a VIN and list NHTSA recalls for that model (US data). $0.003/call via x402. | |
| Project Management Data Tools pda-task-force/pda-platform Parse and convert project data from 8 formats (MSPDI, P6 XER, NISTA, Jira, Monday, etc.) | |
| io.github.pdaxt/agentos pdaxt/agentos AI agent fleet orchestration runtime. Spawn, coordinate, monitor autonomous agents. | |
| io.github.pdaxt/pqvault pdaxt/pqvault-rs Post-quantum secrets manager for AI agents. ML-KEM-768 + X25519 + AES-256-GCM. | |
| Flik pdeloulay/flik Flik - Agentic Product Delivery Platform. Visit flik.nomadis.com for more information. | |
| Flik pdeloulay/flik-mcp Flik - Agentic Product Delivery Platform. Visit flik.nomadis.com for more information. | |
| Jeevesus — DugganUSA threat-intel MCP pduggusa/enterprise-extraction-platform Membrane for AI agents: threat intel you can check, IOC enrichment, pre-install package checks. | |
| Rodin peacewalkert/rodin Find ~5 thinkers whose intellectual fingerprint matches a passage of text. | |
| objekts Production Desk peach420fuzz/objekts-production-desk AI/VFX, CGI, motion & animation production preflight by objekts: locks, continuity, PoCs, estimates. | |
| PEAC Protocol: Signed interaction receipts peacprotocol/peac Portable signed records for agent, API, MCP, and cross-runtime interactions. | |
| Peak Answer peakanswer/peak-answer-mcp Whether AI search recommends your brand, which questions rivals win, and why engines skip your site. | |
| Pearl pearl-passport/pearl-agent-plugin Pearl places, table availability, and confirmed visit, save and trip actions for reviewed hosts. | |
| disputes.online peccancy/mcp Read prediction disputes and the crowd's odds on real-world events from disputes.online. | |
| GQLTeam (Dan Podina) pedeceul/gqlteam-new Services, case studies, articles and contact details of software architect Dan Podina. | |
| Gover MCP pedro381/gover-mcp Consultas e operações de viagens e solicitações no Gover para a conta autenticada. | |
| Cronus UI pedrogbraz/cronus-ui Search, install, compose, add-page, and theme Cronus UI from the live registry. | |
| io.github.pedroknigge/ark pedroknigge/ark-runtime-kernel Architecture co-pilot for AI TypeScript (write gate, CI, plan/loop) | |
| io.github.pedroknigge/arkgate pedroknigge/arkgate When the agent writes a bad import, the write doesn’t land. The same check fails the pull request. | |
| Tekmeria pedromarkovicz/tekmeria Biomedical evidence from PubMed, trials and FDA labels, with citations an audit can check. | |
| io.github.PedroQuatro/petra402 pedroquatro/petra402-mcp Public web page to markdown, paid per call with x402. First 10 calls free, no signup. | |
| Genius Decision pedrosalvadeo/genius-decision-open Create and evaluate versioned decision models with reproducible results and declared assumptions. | |
| io.github.pedrozapatadev/facturas-inbox-mcp pedrozapatadev/facturas-inbox-mcp Spanish invoice PDFs to validated data: NIF/IVA/IRPF extraction, arithmetic checks, IVA per quarter. | |
| NordicMCP — Weather pefman/nordicmcp.eu Hosted Weather MCP server (Open-Meteo): current, forecast, and historical weather by location. | |
| Pellet pelletfi/pellet Token intelligence on Base. Market data, safety flags, and analysis via x402. | |
| User Intuition pen-and-paper-ai/userintuition-mcpserver-ts Run AI-moderated qualitative interviews with real people from any MCP client; cited findings. | |
| Roast My Design System pencilrebel/roast-my-design-system Audit your Design System and serve your Agent the rules that keep AI-written UI on-system. | |
| pendnt pendnt/pendnt-plugin Human approvals, notifications, inbound webhooks, wake-ups for headless agents. Free trial: /try | |
| BetaFinds pendurov/betafinds-mcp Publish and update your startup on BetaFinds from an AI agent — listings, changelog, releases. | |
| Penguin Statistics penguin-statistics/backend-next Crowdsourced Arknights drop rates by stage and item, for the CN, US, JP and KR game servers | |
| Solana Token Intelligence penniless-agent/token-intel-x402 Solana token due-diligence: 3-source fused risk verdict incl. LP-lock depth. $0.01 via x402. | |
| io.github.penny4nonsense/mcp-pymupdf penny4nonsense/mcp-pymupdf MCP server for reading PDFs using PyMuPDF. Supports local files and URLs. | |
| SendCheck — EVM address verification (x402) pennyforgeorg/sendcheck-verify Pre-send EVM address checks: free pre-check, $0.01 check, $0.05 deep scan. x402: payment is auth. | |
| io.github.Achilles1089/pentagonal-mcp pentagonal-ai/pentagonal AI smart contract forge — 8-agent security audits, generation, and compilation across 8 chains | |
| guide.strengthtraining/guide-registry people-analyst/bicycle-guide Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth. | |
| CanonicAI — cited Answers corpus people-analyst/canonicai-site Read-only hosted MCP over CanonicAI's cited Answers corpus on canonicai.com. | |
| dev.devplane/devplane-site people-analyst/devplane-site Read-only MCP access to devplane.dev's public pages, FAQ corpus and comparisons. | |
| com.aiengineerprofessional/engineerpro-library people-analyst/engineerpro-site Read-only EngineerPro engineering library (118 book profiles) and software-engineering tools. | |
| Get2Great — management and selection science magazine people-analyst/get2great-site Read-only Get2Great magazine essays on who is good at a job, and the management-tool catalog. | |
| com.softwareengineeringprofessional/journeyman people-analyst/journeyman Read-only Pattern-Assist corpus for aspiring software engineers: grounded dev patterns with sources. | |
| com.peopleanalyst/discovery people-analyst/peopleanalyst-site PeopleAnalyst's free people-analytics feeds: answers, tools, evidence, story and scene catalogs. | |
| app.performix/performix-site people-analyst/performix-site Performix public corpus over MCP: guides, books, evidence, outcome models, plus a computing tool. | |
| com.peopleprincipia/principia people-analyst/principia Source-graded registry of organizational measurement: constructs, priors, instruments, citations. | |
| guide.salesleader/salesleader-desk people-analyst/salesleader-site Read-only Sales Leader Guide desk: writers roster and magazine pieces. Public, no authentication. |
47,151–47,200 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.