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 |
|---|---|
| Conversion Tools Convert files too big or exotic for a sandbox: 140+ formats, batch, OCR, AI extraction, TTS/STT | |
| CookiePilot – cookie banner & Consent Mode v2 Add a GDPR cookie consent banner with Google Consent Mode v2 to any website, from the chat. | |
| Corrie Site Check Free HTTPS and security header check from Corrie, uptime monitoring for small teams. No auth. | |
| CortexPlus Personal memory layer: files, notes, messages, tasks and email, semantically indexed. | |
| io.coupler/remote-mcp-server Coupler.io remote MCP server | |
| CrimeScore US neighborhood Safety Scores, score drivers, geocoding and nearby activity from CrimeScore.io. | |
| Cronch Cron jobs for your body: meals, water and breaks planned around your calendar, one tap to do. | |
| Cronitor Manage Cronitor monitors, issues, status pages, and metrics for jobs, uptime, and sites. | |
| Cubite LMS: Learning Management System LMS (learning management system): manage courses, SCORM/xAPI, learners, certificates and reports. | |
| Cubli Host websites, apps, databases, domains and mail at Cubli (EU) from your AI tool. | |
| Curatively Search, read and save to your private vault of images, links and notes. | |
| CustomerDashboard Build dashboards on your own data, including multi-customer views with per-customer login. | |
| CzechAI – Czech business & property intelligence Czech business & property intelligence: AML/KYC, company registers, cadastre, valuation, law, OSINT | |
| Dadan Screen recording & video platform: search, share, transcribe, translate videos & AI meeting notes | |
| Research MCP Server 23 live research tools, from web search to SEC filings. Each call bills the scraper it runs. | |
| io.datadef/mcp Generate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat. | |
| Datagoat Governed decision engine: yes/no, score, choice and rank answers about cases, from past outcomes. | |
| DataQuoll Australian data as MCP tools: incidents, gauges, declarations, calendars, police releases, archive. | |
| datavessel 200+ read/write tools for GA4, Search Console, Google Ads, Shopify, WooCommerce, Shopware & more. | |
| daybag.io Bookings for outdoor outfitters: check availability and book classes, appointments and rentals. | |
| Daycal A booking page your AI assistant sets up and keeps right: trips, holidays, focus time, daily limits. | |
| dazie Your dazie voice journal: read entries, insights, to-dos and memories, and add entries and to-dos. | |
| pg.ddx.io: the PostgreSQL community's memory Every PostgreSQL mailing list since 1991, linked to the commits, code, commitfest and docs. | |
| DecaData Odyssey Lite US point-of-sale sales for ~380 consumer companies: free search and samples, YoY growth for $0.01 | |
| Kai CSV Profiler and Domain Watch Intake Bounded CSV profiling plus review-only host monitoring requests through one remote MCP endpoint. | |
| channel-lab Studio distribution-lab reference MCP endpoint (channel-lab R&D, DNS-verified namespace). | |
| Deep Blue Alpha — Ethereum Whale Data Live Ethereum whale flows: token activity, top tokens, latest moves, Whale Sentiment Index. | |
| Deeplead Find local businesses, companies and decision makers with verified emails for B2B outreach. | |
| Defiance Storefront Read-only catalog, sequence, evidence, policy, and COA-verification lookup for an RUO supplier. | |
| Demiton AI infrastructure for Australian civil construction. Public procurement data and connected systems. | |
| Demofy Turn a URL and one line of intent into a narrated product demo video, from any MCP client. | |
| DeveloperHub Docs Search DeveloperHub's own documentation. Every docs site hosted on DeveloperHub serves one at /mcp | |
| DeveloperHub Editor Find, write, publish and check pages and API references in your DeveloperHub docs from an AI client | |
| Disban Check if a signup email is disposable, free, an alias, testing, parked or unknown, with evidence. | |
| disdex: Discord server search Find public Discord servers by topic, language and size, check invite links, see member growth. | |
| DNS Spy DNS monitoring and domain security: live DNS, propagation, WHOIS/RDAP, SSL and look-alike domains. | |
| DoDomain Connect custom domains via AI agents: DNS pre-flight checks, hand-off connect sessions and checks. | |
| io.domaindrift/domaindrift Signed internet telemetry, read-only: DNS, TLS, WHOIS, reachability. Every record Ed25519-signed. | |
| io.domainium.search/domainium-search AI-powered domain & business name generation with real-time availability checks. | |
| io.domainium/domainium-search AI-powered domain & business name generation with real-time availability checks. | |
| Doply Check your Google Play closed test on Doply: progress, devices, crashes, screenshots. | |
| dot•requirements Write product documentation to share with your whole team, including testable specifications. | |
| Dovri customer support handoff Search published help and hand customer chat to a person. Requires your app's backend integration. | |
| io.dozier/exposure-audit Free AI-visibility and competitive Exposure Audit for any domain. No account, no API key. | |
| Drawdy Free whiteboard where people and AI draw together: read cloud boards, draw diagrams, build slides. | |
| Drint Packaging dielines (FEFCO/ECMA), 3D box and bag mockups, and your Drint projects in the chat. | |
| DueChat Find overdue invoices, draft invoices, and chase payment. Sends need your confirmation. | |
| Dumpster Controls Dumpster rental operations from AI: orders, dispatch, invoices and customers. You confirm changes. | |
| io.dwelldata/real-estate-data DwellData: typed US real-estate feeds — deals, distress, auctions, leads, address lookup. | |
| io.dxbdata/dxb-data Official Dubai real estate data: live prices and rental yields by area, from the DLD. |
38,151–38,200 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.