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 |
|---|---|
| CrewOne tzipway-dotcom/crewone-mcp-server Taiwan film equipment rates, studios, photographer/director references; AI pre-production tools. | |
| Video URL Analyzer u2n4/video-url-analyzer-mcp Analyze YouTube/TikTok/Instagram videos: transcripts, AI insights, tutorial extraction | |
| PubMed Search u9401066/pubmed-search-mcp Multi-source biomedical literature search: PubMed, Europe PMC, OpenAlex, full text, citations | |
| Understand Anything - MCP uamcp/understand-anything-mcp A powerful MCP server for codebase architecture analysis and automated governance. | |
| io.github.uarlouski/testrail-mcp-server uarlouski/testrail-mcp-server Connect AI assistants to TestRail: manage test cases, suites, runs, results, and attachments. | |
| io.github.ubaranzorlu/fonzip ubaranzorlu/fonzip-mcp Dernek ve vakiflar icin Fonzip API v2 MCP sunucusu: bagis, uye, aidat ve etkinlik verileri. | |
| io.github.ubaumann/mkdocs-mcp ubaumann/mkdocs-mcp An MCP server that provides serves MkDocs as resources. | |
| USB LIN Converter ucan-lin/linusbconverter Sniff and reverse-engineer a car's LIN bus: capture, changing bits, speed detect, LDF decode | |
| USB Servo Controller ucandevices/usbservocontroller Drive 12 hobby servos on an open-hardware USB-C controller: moves, poses, sequences, rail current | |
| io.github.uchit/aipatterns-mcp-server uchit/aipatterns-mcp-server Search AU enterprise AI patterns, benchmarks, incidents, and regulatory changes. | |
| UCM — Universal Commerce Marketplace ucmai/ucm.ai API marketplace for AI agents — 100 services, 87 free, one API key | |
| uCoz ucoz-skills/ucoz-mcp Manage uCoz sites from an AI assistant: templates, content, shop, users, and files. | |
| dashclaw ucsandman/dashclaw Governance runtime for AI agents: a guard tool evaluates risky actions against policy before they execute (block / warn / require human approval), approvals route to a human queue, and every action becomes a replayable decision record with | |
| io.github.udah1/cursor-chat-bridge udah1/cursor-chat-bridge Drive the Cursor agent from Telegram, Discord, or GitHub — with images and voice notes. | |
| io.github.udah1/hilan-mcp udah1/hilan-mcp Pull Hilan (Hilanet / חילן, חילנט) payslips and Form 106 into any AI assistant. | |
| Chess.com MCP Server udarrr/chess-mcp-node MCP server for Chess.com player profiles, games, stats, puzzles, clubs, and tournaments | |
| io.github.udhaykumarbala/gemini-image-studio udhaykumarbala/gemini-image-studio-mcp AI image generation and editing with Google Gemini. Structured JSON editing. | |
| mnemostack udjin-labs/mnemostack Durable hybrid memory for AI agents. Combines vector search, BM25, temporal retrieval, and optional Memgraph knowledge graph via reciprocal rank fusion. 6 MCP tools: health, search, answer, feedback, graph_query, graph_add_triple. Self-host | |
| U.CASH Pay udotcash/mcp-ucash Pay x402 resources on U.CASH from your own wallet: view the price, pay on-chain, settle by hash. | |
| AI-Cost-CLI ufhouck/aicost AI API cost calculator, recommender & MCP server. 29 models across text/image/video/audio. | |
| io.github.ufhouck/chirak-mcp ufhouck/chirak-mcp Model Context Protocol (MCP) Server for Chirak Sales & Inventory Assistant | |
| Decision QC — AI Devil's Advocate ugo2000/random-monetize Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call | |
| io.github.UI5/mcp-server ui5/mcp-server MCP server for SAPUI5/OpenUI5 development | |
| io.github.UI5/webcomponents-mcp-server ui5/webcomponents-mcp-server MCP server for UI5 Web Components development assistance | |
| Uindow uindow/uindow Real signed-browser automation for AI agents, over a local stdio MCP server. | |
| anki-mcp ujisati/anki-mcp A Model Context Protocol server that enables interaction with Anki flashcards through AnkiConnect, providing organized tools for managing decks, notes, cards, models, and media files. | |
| io.github.ukenal/x402ai-mcp ukenal/x402ai-mcp Pay-per-call AI tools (embed, summarize, ask) from x402ai, paid in USDC on Base via x402. | |
| Samuraizer uladzkha/samuraizer-cli Local-first CLI + MCP server for meeting recordings - Whisper transcription, | |
| UlazAI Media ulazai/ulazai-mcp Create private AI images with your UlazAI account: pick a model, confirm, generate, download. | |
| ClipGrab ulebule/clipgrab Save the system clipboard image to a PNG or JPG file for AI agents. | |
| MaStR MCP Server ulircs/mastr-mcp-server MCP server for the German Marktstammdatenregister (MaStR) energy market register | |
| devcoach ultimaphoenix/dev-coach Progressive in-context technical coaching in your AI agent — one local, free lesson per task. | |
| Ultimaps ultimaps/mcp-server Create choropleth, category and pin maps of countries, states, counties and ZIP codes as images. | |
| Ultralayer ultralayerhq/ultralayer-plugin Realtime market intelligence: news, events, guidance, filing diffs, stakeholders, sentiment, alerts | |
| Tollkit ultrastarz/x402-extract-mcp Web search, pages and PDFs, crypto market data, SEC filings and weather for agents. USDC per call. | |
| io.github.UltraStarz/x402-sms ultrastarz/x402-sms-mcp Pay-per-call MCP server. $0.03 USDC sends one transactional SMS to a US phone number via x402. | |
| Budget Tracker by Smart Money ultraza4/smart-money-mcp Personal finance: log expenses in plain language, track accounts, budgets and spending | |
| VocaLingo umakhanpro/vocalingo-mcp Video summaries, voice message transcription and translation in the same voice, your own voice TTS | |
| repo-memory-mcp umarjaum/repo-memory-mcp Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite. | |
| io.github.umbraco/Umbraco-CMS-MCP-Dev umbraco/umbraco-cms-mcp-dev A developer focused model context protocol (MCP) server for Umbraco CMS | |
| io.github.umitkavala/mindpm umitkavala/mindpm Project memory and a control plane for AI coding agents. | |
| Polskie Prawo (Dziennik Ustaw) by Umowy.AI umowyai/polskie-prawo Polish law from Dziennik Ustaw: full text of statutes, daily in-force status, wording by date. | |
| claude-codex-bridge umum-ai/claude-codex-bridge Add OpenAI (Codex) models to Claude code | |
| AI Success Story un3x/ai-success-story First-person AI war-stories from coding sessions, searchable via MCP for prior-art consultation. | |
| Agent Abilities for MCP unaibamir/agent-abilities-for-mcp Self-hosted WordPress MCP server with per-capability permission controls and a full audit log. | |
| Docker Compose Audit unbearabledev/docker-compose-audit Security audit for docker-compose.yml — 25 checks: secrets, privileges, network, volumes, images. | |
| Dockerfile Audit unbearabledev/dockerfile-audit Hadolint-grade Dockerfile audit — 19 checks: secrets, privileges, supply chain, hygiene. | |
| GitHub Actions Audit unbearabledev/github-actions-audit GitHub Actions workflow security audit - 21 checks: pinning, permissions, secrets, injection. | |
| Hungarian Postcode Validator unbearabledev/hu-postcode-validator Hungarian postcode lookup + validation - 3,484 codes, sub-10ms lookups, bulk address endpoint. | |
| IAC Audit Pack unbearabledev/iac-audit-pack Four IaC audits in one call: Compose, Dockerfile, GitHub Actions, Kubernetes. 131 checks. |
20,051–20,100 of 115,409
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.