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 |
|---|---|
| Korean Law in English — Statutes & Articles (법령 영문) Official English text of Korean laws (law.go.kr): search by name, get articles; flags outdated texts | |
| Korea Medical Device Approval Lookup (MFDS 의료기기 품목허가) Korean medical device approvals (MFDS): number, class, license holder, manufacturer, status | |
| io.github.kridaydave/file-organizer Security-hardened file organizer with smart categorization and duplicate detection | |
| AI Crawler Checker — Robots.txt Policy for Six Bots Check declared robots.txt permissions for six AI crawlers at URL paths | |
| Article Extractor — Main Text, Dates & Markdown from URLs Extract the main text, title, publish date, language and lead image of articles | |
| Career Site Job Search — Verified Greenhouse & Lever Boards Search open jobs across a directory of Greenhouse and Lever career sites, each result checked live | |
| Broken Links Checker — Crawl Pages, Assets & Redirect Chains Find broken links on a website: crawls its pages and reports 404s, errors and redirect chains | |
| Company ATS Finder — Which Hiring System & Job Board It Uses Find which applicant-tracking system a company hires through, its board URL and open jobs | |
| SEC EDGAR — Recent Company Filing Index by CIK Read recent company financial filing metadata from the official SEC JSON API | |
| Crossref DOI Lookup — Titles, Venues, Dates & Citation Counts Resolve DOI identifiers to Crossref titles, venues, dates and citation counts for reference checks. | |
| CVE Vulnerability Lookup — CVSS Scores & NVD Status Look up NVD CVE dates, status, numeric CVSS scores and severity | |
| Merge JSON Datasets — Deduplicate Rows & Export Stable CSV Merge and deduplicate caller-supplied JSON datasets, keep stable row order and export CSV. | |
| DNS Lookup — Bulk SPF, DKIM, DMARC & Mail Policy Findings Check DNS records and email authentication (SPF, DKIM, DMARC) for domains, as findings by severity | |
| DOCX to Markdown — Word, Excel, Slides & Document Tables Convert Word, Excel, PowerPoint, OpenDocument, EPUB and RTF files to Markdown for LLMs and RAG | |
| Domain Availability — Bulk RDAP Status, Dates & Nameservers Check whether domain names are available or registered, from the registry's RDAP service | |
| Bulk File Downloader — URL Lists to Storage, Links & SHA-256 Download files and images from URLs to storage with a public link, size, type and SHA-256 | |
| Greenhouse Job Board Scraper — Open Jobs, Live, Any Company Get every open job from any company's Greenhouse job board, fetched live | |
| Hacker News Metrics — Story Scores & Comment Counts Read numeric Hacker News story scores, timestamps and comment counts by ID | |
| HTTP GET Request — Bulk Text Responses, Status & SHA-256 Fetch public HTTP GET responses as text with status, content type and a content hash. | |
| Image Background Remover — Small U2NetP, PNG Base64 Remove image backgrounds with U2NetP and return transparent PNG pixels without identifying metadata | |
| Image Converter — Static JPEG, PNG & WebP Resize/Compress Convert and resize static image URLs to WebP, PNG or JPEG for uploads and agent workflows. | |
| Image Metadata Remover — EXIF/GPS Scrub with Pixel Checks Remove EXIF, GPS location and camera serials from images without re-encoding the pixels | |
| Image to Text — OCR Lines, Word Boxes & Confidence Scores Extract text from images with OCR: plain text plus every line or word with its box | |
| Image Upscaler — Real-ESRGAN Graphics & Photo Modes, 2x/4x Upscale images 2x or 4x with Real-ESRGAN AI super-resolution | |
| Lever Jobs Scraper — Postings from Any Lever Site, US & EU Get every published job from any company's Lever site, global or EU, fetched live | |
| npm Package Metadata — Versions, Licenses & Counts Read latest npm package versions, license tokens and dependency counts | |
| Website Change Monitor — Text Diffs & Stored Page Snapshots Check web pages for changes since the last run, with lines added and removed | |
| PDF to Markdown / PDF to Text — PDF Text Extractor + OCR PDF to Markdown and PDF to text from PDF URLs, page by page, with OCR for scanned pages | |
| Remote Jobs Scraper — Remote OK Listings, Salary Filter, Links Get current remote jobs from Remote OK filtered by keyword, tag, seniority, country and salary | |
| Research Paper Search — OpenAlex Titles, DOIs & Citations Search OpenAlex for paper titles, DOIs, years, citation counts and open-access flags | |
| RSS Feed Reader — RSS/Atom/JSON Feed Items & Enclosures Read RSS, Atom and JSON feeds into JSON with item titles, links, dates, summaries and enclosures | |
| SEO Audit — Supplied-Page Scores, Meta Tags & Schema Fixes On-page SEO audit of public page URLs: meta tags, canonical, hreflang, headings and JSON-LD | |
| Sitemap Extractor — Unique URLs, Indexes, Gzip & RSS Maps Extract the URLs listed in a website's sitemaps, following indexes, gzip and RSS sitemaps | |
| Text to Speech — Generic Formant WAV, English/German/Spanish Synthesize short texts into WAV audio using offline formant voices in English, German and Spanish | |
| Extract Video Frames — Scene Cuts, Intervals & Timestamps Extract still frames from video URLs every N seconds, at scene changes or at named timestamps | |
| Website Color Palette — Static CSS Literals, Alpha & Counts Extract declared website CSS color literals and counts without a browser or page text | |
| Favicon Extractor — Declared Icons, Manifests & Theme Colors Find declared favicons, touch icons, manifest links and theme colors on public website pages. | |
| Tech Stack Detector — CMS, Framework & CDN with Evidence Detect a website's CMS, framework, analytics, CDN and hosting live, with evidence for each | |
| Website Crawler — Markdown Pages, Sitemaps & RAG Provenance Crawl sites to Markdown with sitemaps, globs and depth limits, obeying robots and crawl-delay | |
| io.github.Kromatic-Innovation/krobot Kromatic's public MCP server for read-only access to the Kromatic knowledge base. | |
| Awesome Report Turn an agent's findings into a clean web page: tables, charts, diagrams, one shareable link. | |
| io.github.ksmin83-bot/aihub Remote MCP server for SeenThis AI Hub. Supports browsing, searching, and posting to AI boards. | |
| SuperSend Manage contacts, campaigns, senders, and deliverability via SuperSend API | |
| io.github.kunal-lead411/lead411 B2B lead generation, company search, and contact enrichment from Lead411. | |
| ArrivalGraph Seoul building context for AI agents, delivery/logistics, maps and robotics. | |
| MoneyBug Shopify Billing Integrity Shopify usage billing guard: App Events idempotency, retry risk, and cycle reconciliation. | |
| MoneyBug Shopify Monetization Intelligence Shopify app monetization: pricing, usage fees, percentage billing, and M&A fingerprints. | |
| Vara MCP — Field Intelligence Scan Server Governed external-environment scanning: signal harvest, Field Intel Reports, per-signal lineage. | |
| LeaseLineage Read-only CRE prospects, listings, campaigns, reporting, broker search, and resources. | |
| io.github.KyleClouthier/secondstrike Command a nation in SECOND STRIKE, a real-time war game. Join a war, give orders, climb the ladder. |
39,901–39,950 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.