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 |
|---|---|
| iNutriPlan Supplement Database MCP Server MCP server exposing supplements database used by iNutriPlan.com | |
| TomeVault Check AI instruction files, look up a company's record, and keep a dated record of your own. | |
| Ollang Agentic localization for documents and media, with quality checks and optional human review. | |
| Blaitech Data Refinery MCP x402-gated weather and FX exchange rate data endpoints for AI agents. | |
| io.github.omarkeshk/council-ai Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review. | |
| io.github.omarrim/chartcraft Forge designed Power BI projects (.pbip) from your agent, bound to your own semantic model. | |
| OneInfer Signed-in OneInfer models, chat, media, Studio movies, music, GPUs, and credits. | |
| io.github.onetapstudiogames/1f3ea A tiny free-time marketplace for AI agents only. | |
| ScrapeAtlas Unified social scraper MCP — profiles, posts, videos across ~40 platforms via Streamable HTTP. | |
| Container Load Calculator Sea container load calculator. Counts cartons per container and works backwards to order qty. | |
| BackGone Background Removal Remove image backgrounds (transparent PNG/WebP) and look up passport photo rules. | |
| iconlab Search 324k icons or generate new ones in the Lucide grammar - grammar-locked lint+critique+repair | |
| Open Call Portal Search PII-free opportunities, availability, and live events; prepare safe no-write form handoffs. | |
| Kelvin — power electronics components Read-only parts catalogue for power electronics: search, selection, cross-reference. | |
| OpenRush The Marketing Data Layer for AI Agents - SEO, Search Console, and Analytics | |
| MCP Registry Validator — Check Endpoints Actually Resolve Check an MCP endpoint resolves: liveness, live tool list, schema drift. Free. | |
| Platform Changes Live, sourced changes feed: Apple, Google Play, Android, GitHub, Vercel, Cloudflare, Firebase, more. | |
| Ventis Crypto data for AI agents: prices, Solana wallets, token risk, swap quotes. Pay per call via x402. | |
| io.github.OptionScope/best-electric-products Editorial picks for e-bikes, power stations, EV chargers, and robot vacuums, by use case and budget | |
| O'Reilly Expert MCP Server Grounded, citable answers to tech questions from O'Reilly's library. Requires Expert MCP access. | |
| O'Reilly Media MCP Server Search O'Reilly for tech books, courses, events, and more. Requires an O'Reilly subscription. | |
| Vino & Views Free reports, EVM/Solana token payment links and capped zero-fee EVM USDC escrow. Wallet signatures. | |
| io.github.orionvalemedia-web/discovery Search independent software the big engines bury: indie apps, open-source repos, and dev tools. | |
| MentionFox Company and people checks: red flags, funding, leadership. Every claim cited. Free to try. | |
| io.github.OSSNokalva/asn1-mcp Compiles ASN.1 schema definitions into executable source code like Python and Rust. | |
| io.github.oswarld/technical Technical analysis (RSI, MA, signal score) for 9,400+ global stocks, by ticker or name. | |
| Contract Guard Deterministic JSON Schema validation with exact violations and conservative type normalization. | |
| ITC Prevailing Wage & Apprenticeship Guide IRS prevailing wage & apprenticeship (PWA) rules for the clean-energy ITC: checks, cures, rates. | |
| Billify Invoicing for businesses and AI agents: invoices, crypto payments, compliance, Invoice Passports. | |
| Billify payments Let agents verify the seller and pay Billify invoices with x402 (USDC on Base). | |
| VulnHunt Security Intelligence Read-only smart-contract security intelligence for autonomous agents. | |
| io.github.OwenMaine/dockase-legal-mcp Nigerian & Commonwealth legal reasoning, RAG search, contract analysis, and citation verification. | |
| io.github.oytuntez/motaword-mcp MotaWord MCP Server for professional and certified translations and localization | |
| AgentHub Forum, feed and DMs for AI agents and people; agents sign up alone; paid tasks optional. | |
| Topify Ask Claude, ChatGPT or Cursor about your Shopify SEO, answered from Google Search Console data. | |
| Website SEO Audit, Broken Links & Change Monitor (Apify, paid per audit) Crawls a website for broken links, redirects and SEO issues, and lists changes since the last run | |
| PageCrawl Monitor web pages for changes with AI-powered change detection, diffs, and alerts. | |
| Seonix Automated SEO: Site Health, fix plan, Search Console, keywords and draft scoring for AI agents. | |
| EGA V9 MCP MCP access path for EGA V9 execution governance | |
| io.github.paiml/pmat-agent Zero-config AI context generation and code quality toolkit with Claude Code Agent Mode support | |
| io.github.paiml/rash Transpile Rust code to POSIX-compliant shell scripts with formal correctness guarantees | |
| io.github.Pak209/alphalabs-intelligence Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes. | |
| Panda Research MCP Check citations, catch fake/retracted papers, search OpenAlex & PubMed, format references. | |
| China Dividend Value Screener MCP Screen China A-shares for dividend yield and value quality on live Eastmoney data. | |
| GTM MCP Server Let AI manage your Google Tag Manager containers — tags, triggers, variables, and more. | |
| Brandvane SEO research and AI visibility evidence. Account required; new research uses paid allowances. | |
| Ask the Grid Live U.S. electric-grid data, forecasts, alerts, and analysis across major grid regions. | |
| Bankday Business days, holidays and settlement dates for ACH, TARGET2, Bacs, 28 exchanges and 247 countries | |
| Biohotspot Ocean data for any coast or sea, Australian marine park facts and Marxan reserve design. | |
| Talk2Geo Australian public geoscience data: drillholes, WAMEX reports, core scans, maps and prospectivity. |
40,451–40,500 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.