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 |
|---|---|
| Checkgrow Your company's marketing data from Checkgrow: knowledge, performance, campaigns and competitors. | |
| Laurel Find products vetted for low-tox materials, from Laurel's curated catalog. | |
| AI Inventory Network Supplier intake and hidden-inventory matching for travel/resort/property offers. | |
| AI/MCP Enablement Agency AI workflow/MCP implementation package planner. | |
| com.checkmycontractorquote/contractor-quote-check Check contractor quotes for red flags and pricing risks. Free scan, paid reports, RFP tools. | |
| FireBuy RFQ and quote comparison checklist for fire/public safety purchasing. | |
| FireGrant AI Fire department grant-readiness helper. | |
| GrantOps AI Grant readiness and application checklist generator for schools/PTAs/nonprofits. | |
| Local Compliance OS Generate small-business compliance calendars and renewal checklists. | |
| Maintenance Concierge AI Property maintenance triage and vendor packet generator. | |
| PermitPilot Generate permit and local business opening checklists. | |
| PublicSafetyBid Score public safety bids and vendor fit. | |
| SMB RFP Copilot Extract RFP requirements, deadlines, compliance items, and response checklist. | |
| Checkout Page Create and manage checkout pages, event ticketing, forms, customers, payments and subscriptions. | |
| Checkpoint402 Pay-per-call tx explainer, DeFi yields, token safety, SEC 8-K and OFAC data via x402 (USDC on Base). | |
| CheckTaJob Job search tracker for Claude and ChatGPT: applications, interviews, follow-ups, company watch. | |
| CheckWebsiteNow Check if a website is down, explain browser errors and score agent readability (MCP, WebMCP). | |
| Jefe para restaurantes Consulta el producto Jefe y sus guías públicas para restaurantes, sin operaciones de escritura. | |
| com.cherishedbook/memorials Create and look after online memorials for people and pets who have died. | |
| Fifty50 Find a co-founder and split equity fairly — partnership analysis + co-founder marketplace. | |
| Chickadee Bandit Your household's calendar, tasks, messages and apps. Read, update, or build new apps with AI. | |
| Chief Many agents. One Chief. Plan, track, and manage all your AI agents in one place. | |
| Chiemem Draft, publish and manage AI prompt/how-to listings on Chiemem (Japan): images, files, sales. | |
| Agent Data API 31 pay-per-call APIs for AI agents: SEO, open data, video planning (EN/DE). USDC on Base via x402. | |
| Chili Piper Manage Chili Piper scheduling links, meetings, routing rules, and teams. Admin only. Experimental. | |
| China Footnotes China travel facts and local tips, sourced and dated: hours, tickets, booking and pre-trip setup. | |
| China Industry Intel Read-only selected China industry article excerpts, disclosed sources and company identity links. | |
| Sync by CHNLSYNC FCC copper retirement lookups and a broker-reviewed IT advisor. No supplier names, no prices. | |
| Chockstone Labs Run social media from Claude: draft, schedule and approve posts, answer comments, read results. | |
| ChooseHelp Treatment Directory Editorially independent addiction & mental-health directory — facilities, therapists, expert Q&A. | |
| com.chorilo/chorilo Choir management for AI assistants: events, RSVP, announcements and sheet music of your choir. | |
| Chorus Gathers voice, video and written messages from a group into one book for one person. | |
| Chrome-Stats Extension and app analytics across Chrome, Edge, Firefox, Google Play, and the Apple App Store. | |
| ChronoTab Log time on GitHub issues in ChronoTab: timers, entries, missing days, client hours. | |
| Chrysai Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data. | |
| CHS Backflow — book backflow testing in Charleston Book backflow testing in Charleston, SC: prices, ZIP coverage, free callback. | |
| 出口单 chukoudan 外贸出口计算与数据 / China export tools: tax refund, quotes, container loading, CBM, FX rates. | |
| CielStay The free AI index for direct booking homes. Any channel, or straight to the host. | |
| CineFlo Plan and run film productions: shot lists, breakdowns, schedules, call sheets, budgets and more. | |
| Cinegenta Studio Turn a script into a finished film: plan and quote free, then produce under a hard credit cap. | |
| Cintra Supply Quote Desk Get quotes in minutes and order wholesale industrial and operational supplies from a US distributor. | |
| CircleCI CircleCI's MCP server: inspect projects, runs, workflows, jobs, logs, tests, and artifacts. | |
| Cirrela AI video generator Make AI videos with sound and images from a sentence, with Kling, Wan, MiniMax, Gemini and more. | |
| Citead GEO Score Free GEO score of a web page or text: how easily AI assistants can quote it, with fixes. No key. | |
| CitedIndex Look up AI-visibility and GEO tools: price, AI engines covered, limits and a source for each fact. | |
| CitedTravel Cited travel facts for 195 countries: plugs, currency, emergency numbers, holidays, visa pilot. | |
| Cite Files Check whether AI assistants can reach, read and cite a public website. No account for 4 of 5 tools. | |
| CiteHawk AI-search visibility (GEO) analytics: brand scores, competitor rankings, recommendations, evidence. | |
| CiteLadder AI search visibility data: brand mentions, cited sources, site health and opportunities. | |
| Citevana AI visibility tools Free MCP tools for AI-search visibility: crawler checks, page audits, and llms.txt generation. |
30,451–30,500 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.