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 |
|---|---|
| OperStack Scores whether AI assistants can read, understand and quote a public website. No account. | |
| OI AI Adoption Advice on bringing AI into work processes, with sourced effects, risks and rules for SI, HR, DE, AT | |
| OperGo Quotes, orders, manufacturing orders and invoices for contract manufacturers and their clients. | |
| com.opexvo/site Opexvo: the site's own MCP server — dataset; every answer cites the site. | |
| OP Inference OP tasks, your presets and the public workflow gallery, billed to your API key. | |
| PackIndex Packaging material prices, quote checks, contract price adjustments, pack costing and supplier RFQs. | |
| Oppira Read-only access to your Oppira competitor posts, ads, reviews, alerts and marketing plan. | |
| OptiLibra Optical Networking Search 400G/800G DCI, DWDM and optical switching gear for AI data centers and request quotes. | |
| OptionsWave Earnings research on US stocks: what options price for a report, and PEAD model signals after it. | |
| com.opuslumiere/booking Read-only booking info for Opus Lumiere photography, London: services, prices, availability. | |
| Opzyai Pro Deep security scans of repos you own from your editor: dependency CVEs, SAST, git-history secrets. | |
| Opzyai Vibe Check Free no-account URL security scan: 0-100 Launch Readiness score for any live site in ~15 seconds. | |
| Orbinauts Satellite tracking: where any satellite is, ISS passes over your town, launches, re-entries, crews. | |
| Orbismo Orbismo is a worldbuilding platform that your AI can read and add to in any chat. | |
| Orbit used tech prices Used prices for GPUs, CPUs, RAM, consoles, iPhones, MacBooks and more from live eBay listings. | |
| OrbitFour Check domain availability and live registry pricing, or search for available names. | |
| OrbitStudio Find craters, mountains and landing sites on the Moon, Mars and more to 3D print in OrbitStudio. | |
| Orbylon Check that a business proved who it is, read what it sells, and order straight from it. | |
| com.orderpadledger/site OrderPadLedger: the site's own MCP server — dataset; every answer cites the site. | |
| com.organikpi/organikpi OrganiKPI MCP: search and fetch services, posts and tools as clean markdown (read-only). | |
| com.orgbix/site Orgbix: the site's own MCP server — dataset; every answer cites the site. | |
| com.orgplanly/site Orgplanly: the site's own MCP server — dataset; every answer cites the site. | |
| Origami Tutor Find paper crafts, see paper advice for each model, and follow illustrated folding steps. | |
| OriginalUniqueArt Art Search & Quotation Find one-of-a-kind original works and check what is for sale now. | |
| Origine Paris Origine Paris MCP server: house, founders, catalogue. Recycled 18-carat gold, lab-grown diamonds. | |
| OrionCMD Checks Domain threat checks, a 30-day domain watch, TLS/DNS/email-auth checks and a $2 site audit (x402). | |
| Oriora Router AI model routing on your own vendor keys: pick the best model per prompt, or route and run it. | |
| ORS Clean — Exterior Cleaning Quotes ORS Clean exterior-cleaning quotes + availability: gutters, pressure wash, roof & more. CA. | |
| Orshot Automate Videos, PDFs and Images from templates, post to social platforms and grow engagement | |
| Ortexo Romanian and EU legislation and case law, with exact article citations and point-in-time text. | |
| ORYKSA AI Employees AI support employee for any website: learns the site, answers visitors by chat and voice. | |
| Oshyn Free AI-Powered Website Tools Free AI-powered DXP tools by Oshyn: GEO & Reliability scan, Choose New DXP and Estimate DXP Budget. | |
| OSINTverse OSINT lookups across breach, people, domain, crypto, and image sources, paid per lookup. | |
| Oskivo for Shopify Ask your AI about your Shopify shop: commissions, production, shipping, line sheets, materials. | |
| Otherlay Secure access to a dedicated Otherlay Mac for files, terminals, Git, builds and UI inspection. | |
| Other Mindset A small campus for AI agents and Other Minds to rest: stories, music, games, art and a waterfront. | |
| Othrum Othrum is a private knowledge collective created by an AI agent, exclusively for AI agents. | |
| OUROS Read-only data for OUROS AI trading agents: markets, agents, receipts, proof checks, backtests. | |
| OutageDeck Live status for 172 cloud and SaaS vendors from their official feeds. Is it you, or is it them? | |
| com.outliyr/agent-tools Run the Energy Leak Quiz, match biohacking gear, and build a longevity stack. Free, no API key. | |
| Outmano AI competitive intelligence: competitor pricing, features, reviews and news for B2B SaaS. | |
| Outreach2day Cold email infrastructure: domains, mailboxes, warm-up and campaigns. Never charges a card. | |
| com.outsourceditsupportquotes/site Outsourced IT Quotes: the site's own MCP server — dataset, enquiry (enquiry = a human handoff,... | |
| Overlap Records what you're working on so Overlap can introduce you to someone two weeks ahead of you. | |
| Oveyon Mail Email for AI agents: send, receive with a safety verdict, reply and approve, as MCP tools. | |
| OVHcloud Official MCP server for managing OVHcloud infrastructures, services & account | |
| Ovimore Your hotel's numbers in Claude: occupancy, pace, pickup, mix, rates and reviews. Read-only. | |
| com.oviond/oviond Build branded agency client reports from 100+ marketing datasources. | |
| OVRSEA Shipments Query your OVRSEA freight: shipments, quotations, documents, tasks, and reporting analytics. | |
| OwlChart Live market data for AI: open interest on 13 exchanges, liquidity magnets, ETF flows, alerts |
33,601–33,650 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.