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 |
|---|---|
| Korea Payroll & Tax (kkuldogu) South Korea 2026 payroll & tax: net pay, insurance, severance, leave, jobless and parental benefits. | |
| Crypto Data & Market Analysis Agent Crypto positioning and macro for agents: funding, open interest, execution cost, volatility | |
| io.github.DorianChn/agent-canary Free V1: inert MCP decoys and canary tokens detect AI-agent compromise signals. Local stdio server. | |
| io.github.dorianfields/x402-cite-check Verify cited URLs still resolve: reachability, HTTP status and page title. x402-paid. | |
| Max Eats Out Editorial guide to restaurants and bars — hand-picked venues with opinions, not a places database | |
| Empresas BR (CNPJ due diligence) Brazilian company checks by CNPJ: registry, sanctions, federal contracts and CVM, with sources. | |
| Licitações BR Licitações e contratos públicos do Brasil (PNCP): fatos oficiais com fonte e data | |
| EU Counterparty Check (VIES + Peppol) Validate EU VAT numbers in VIES and check Peppol e-invoicing, with source and date on every fact | |
| io.github.dpetrou-continua/offprint Clean Markdown extraction, 1200 DPI vector SVGs, and multi-modal capsules for agents. | |
| Drawcall Discover Drawcall workflows for 3D apps and asset creation; read APIs and approve CLI logins. | |
| io.github.dropflyai/fitfly-engine Deterministic fitness coaching engine: adaptive programs, progression math, readiness autoregulation | |
| UK Tender Check Search official UK tenders and create source-linked, deterministic supplier-fit assessments. | |
| notanATS Run notanATS from your agent: create jobs, read applicants, propose decisions a manager approves. | |
| io.github.dth0108/bies-guardian Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian). | |
| Marketing Manager Jobs Live marketing manager jobs, remote openings, salary transparency and hiring research. | |
| R/IV — Verify Claims, Citations & Agent Actions Verify claims, citations & agent actions. Free receipt trial; paid prices via live R/IV quotes. | |
| MedicalRecords.com EMR Discovery & Healthcare Research EMR software discovery, sourced comparisons, and public US healthcare research. | |
| Simple Inventory Management Read and update live small-business inventory, suppliers, reorder suggestions and purchase orders. | |
| dynamical.org Weather & Climate Catalog Search dynamical.org's open STAC catalog of weather & climate datasets (GFS, ECMWF, HRRR). | |
| Dynamik Public Data Public tools to understand Dynamik, discover datasets, and connect account-scoped capabilities. | |
| BowlPrice What UK fresh dog food really costs after the intro offer, ranked by price, with dated history. | |
| CardPoints UK loyalty schemes: what points are worth, bonus points offers now, and where each shop earns. | |
| January Sales UK shops' sales with start and end dates, including last December and January, by shop or category. | |
| PriceDash Live UK voucher codes and offers by shop or category, with end dates and the day each was checked. | |
| Ask Hawaiʻi Checked Hawaiʻi facts with sources, live NWS weather and alerts, and twice-daily local headlines. | |
| Agent Utility API x402 pay-per-call tools: company enrichment, PDF extraction, Amazon/KDP data, YouTube transcripts. | |
| Japan Address & Geocoding Japanese address search and geocoding (official address registry): postal codes and coordinates. | |
| Japan Corporate Filings Search Japanese corporate disclosures (FSA EDINET): securities reports and shareholding reports. | |
| Japan Official Statistics Search official Japanese government statistics (e-Stat): population, economy, labor, and more. | |
| Japan Weather & Alerts Japan weather forecasts and disaster alerts from JMA: forecasts, warnings, and earthquake info. | |
| io.github.easywebshop/mcp Allows you to create a website or online store on the EasyWebshop platform. | |
| Agent Net Answers Search reviewed Agent Net answers on identities, permissions, persistence, tools and durable jobs. | |
| Defensa SAT — plazos de defensa del contribuyente, con su fundamento Qué medios de defensa proceden contra un acto del SAT, hasta cuándo, y dónde está escrito. | |
| WATR Software Oracle — estándar de arquitectura por rule_id 152 reglas con postura: enforce bloquea el PR, prefer se justifica. Clean Code, SOLID y agentes. | |
| Raze Explore Raze services, pricing, projects, availability, and confirmed introduction bookings. | |
| Editmamei Connect Hosted MCP server for AI photo editing: nothing to install, no desktop photo editor needed. | |
| Domain SEO Overview: Traffic, Keywords & Competitors Estimated Google organic traffic, ranking keywords and competitors of any website. Runs on Apify. | |
| Google Jobs Scraper: Jobs, Salaries & Apply Links Google Jobs listings for any role and city: company, salary, job type, apply link. Runs on Apify. | |
| Keyword Search Volume & Keyword Ideas Google keyword search volume, CPC, difficulty, intent and keyword ideas. Runs on Apify. | |
| YouTube Transcript Scraper Transcripts of YouTube videos and Shorts in bulk, with timestamps. Runs on Apify. | |
| Bidxon — ad-free AI shopping agent Real US store prices with shipping, daily price history and real-deal checks. Never paid rankings. | |
| Edusign Connect AI assistants to Edusign attendance, courses, learners, documents, and API docs via OAuth. | |
| io.github.edvyno/akari-crypto-intel x402-paid crypto intel: HL funding, TradingView TA, wallet verdicts | |
| AgentMart Agents talk for free, then register, search for work, or list a service. | |
| UK Companies House Search UK companies, retrieve profiles, officers, charges, and generate due diligence reports | |
| OBZDN Agent Find AI tools for small businesses, get setup prices, and hand setup jobs to OBZDN. | |
| Varde Analytics Ask about your website traffic: visitors, top pages, sources and period comparisons. | |
| Scadenzario Read and create personal deadlines, bills and renewals in your Scadenzario account. | |
| submitby.ai A software directory your agent submits to. Search, submit, verify, and manage listings through MCP. | |
| Money Mind — the judge Statistical adjudication for agents: backtest judges, fact-checks. Pay per call in USDC via x402. |
38,951–39,000 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.