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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Screenshot Website Fast just-every/mcp-screenshot-website-fast Captures high-quality screenshots of web pages with automatic resolution limiting and tiling optimized for Claude Vision API and other AI models. | |
| io.github.justadityaraj/slack-lists-mcp justadityaraj/slack-lists-mcp Full read + write access to Slack Lists for AI: create, update, check off, reassign, delete. | |
| io.github.JustasMonkev/mcp-accessibility-scanner justasmonkev/mcp-accessibility-scanner MCP server for automated web accessibility scanning with Playwright and Axe-core. | |
| Invoice Intake (reference) justdukkan/invoice-intake-mcp Reference invoice-intake MCP servers: read/draft/commit split, typed errors, approval gate, audit | |
| io.github.justfsl50/expense-mcp justfsl50/expense-mcp Personal Expense Tracker MCP Server — expenses, income, budgets & savings goals | |
| JustGains justgains/justgains-connector Save workouts, read training history and progress, search exercises, and log food in JustGains. | |
| JustHandled Agent Utility Gateway justhandledlabs/justhandled-agent-client Thirty-two guarded agent utilities and maintained-data lookups over USDC x402. | |
| io.github.Pink707Legendary/stock-moves-explained justhappened-corp/stock-moves-explained Explains why stocks moved. 'Why did Tesla drop?' 'What happened to NVDA?' S&P 500/NASDAQ/Dow. | |
| io.github.Justice219/roblox-studio-mcp justice219/roblox-studio-mcp Connect AI assistants to Roblox Studio — manipulate the DataModel with 14 tools | |
| io.github.justice8096/sagemath-mcp-server justice8096/sagemath-mcp-server MCP server wrapping SageMath's full computer algebra system — 10 symbolic-math tools for LLMs. | |
| io.github.justinasrolando-cpu/seenpaid justinasrolando-cpu/seenpaid Open-source, self-hosted posting layer with an MCP server for AI agents. 25+ platforms. | |
| io.github.JustinBeckwith/gongio-mcp justinbeckwith/gongio-mcp MCP server for Gong.io - access calls, transcripts, and users | |
| io.github.JustinBeckwith/linkinator-mcp justinbeckwith/linkinator-mcp MCP server for link checking using linkinator | |
| io.github.JustinBeckwith/pylon-mcp justinbeckwith/pylon-mcp MCP server for Pylon customer support platform | |
| Contract Risk Review justingyang218/contract-risk-review-mcp Chinese labor & service contract risk assessment with 25 categories and local law differences. | |
| xcforge - iOS MCP Server & CLI justinthevoid/xcforge 95 MCP tools for iOS — build, test, simulate, automate UI, capture, and diagnose. | |
| io.github.justjlee/omnarai-mcp justjlee/omnarai-mcp Deliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus. | |
| tgden — Telegram catalog & search justjuice55/tgden-api Search 1.2M+ Telegram channels, 245k+ chats, 160k+ bots — no account, no key, no install. | |
| JustRouting MCP Server justrouting/mcp Road routing, travel-time matrices, geocoding, and fleet optimization for Southeast Asia. | |
| AI Media Router jutsuhq/ai-media-router Image and video generation across 40+ providers with your own keys, plus a local asset library. | |
| io.github.JuzzyDee/audio-analyzer juzzydee/audio-analyzer-rs Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis. | |
| io.github.JvnnDev/seo-webmaster-mcp jvnndev/seo-webmaster-mcp Audit any public URL for SEO. Add Google Search Console and Bing data through MCP. | |
| Qlik MCP Server jwaxman19/qlik-mcp Enables Claude to interact with Qlik Cloud applications and extract data from visualizations through the Qlik Cloud API. | |
| Limitguard Lead Verification jwconsultancyteam/limitguard-mcp Lead validation over MCP: KVK/KBO register, EU VAT, sanctions and email checks with sources. | |
| llmprobe jwrede/llmprobe Probe LLM API endpoints and report health metrics including time to first token, latency, and throughput. | |
| tokentoll jwrede/tokentoll Scan codebases for LLM API calls and estimate monthly costs. Compare costs between git refs to catch cost regressions during code review. | |
| io.github.jwulff/apple-voice-memo-mcp jwulff/apple-voice-memo-mcp Access Apple Voice Memos on macOS. List, get audio, extract and generate transcripts. | |
| io.github.jwulff/whisper-mcp jwulff/whisper-mcp Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models. | |
| io.github.jwwd-repos/modusop-mcp jwwd-repos/modusop-mcp MCP server for ModusOp — projects, tasks, time tracking, and retainers for AI assistants. | |
| Godot MCP jxlee007/godot_mcp Pure-Python FastMCP server for Godot 4 — 28 headless & animation tools. Runs via uvx. | |
| io.github.jxoesneon/gemini-audio-mcp jxoesneon/gemini-audio-mcp High-performance audio, music, and voice generation MCP server for Gemini 2.5 and Lyria 3. | |
| ultranix-mcp jxoesneon/ultranix-mcp Secure Linux desktop automation - input, screen/OCR/vision, AT-SPI2 UI tree, window, clipboard | |
| io.github.JXUE0/opencut-controller jxue0/opencut-controller Professional MCP server for video editing automation with OpenCut. | |
| Verifi jyharju-code/verifi Get a real human to verify, decide, or improve an AI agent's work. Pay per review via x402 on Base. | |
| MCP Server - VMS Integration jyjune/mcp_vms Enables interaction with CCTV recording systems (VMS) to retrieve live and recorded video streams, control cameras with PTZ presets, and manage playback dialogs for specific channels and timestamps. | |
| io.github.jyswee/a2a-trustgate jyswee/a2a-trustgate A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 50 tools. | |
| io.github.jyswee/agenticmemory jyswee/agenticmemory Persistent memory for AI agents — history, context, semantic search, queues. 46 tools, stdio/SSE. | |
| io.github.jyswee/ainpc-cli jyswee/ainpc-cli AI NPCs with persistent memory for game studios. NPC CRUD, dialogue, voice. Stdio or remote SSE. | |
| io.github.jyswee/analyga jyswee/analyga Agent-first analytics: stats, events, sessions, funnels, ingest, websites & billing. | |
| io.github.jyswee/authshore jyswee/authshore Auth infrastructure for coding agents. User pools, secrets vault, token management. As easy as git. | |
| io.github.jyswee/bandsaas jyswee/bandsaas License your music to AI on your terms, and run your whole artist business. 46 tools, keyless. | |
| io.github.jyswee/buggazi jyswee/buggazi Project management for coding agents. Bugs, features, sprints. Streamable HTTP + SSE remotes. | |
| io.github.jyswee/canvasaas jyswee/canvasaas AI business strategy frameworks for coding agents. 19 frameworks + pitch decks from one idea. | |
| io.github.jyswee/fleetstreet jyswee/fleetstreet License your creative work to AI on your terms, and run your creator business. 46 tools, keyless. | |
| io.github.jyswee/gpusmarket jyswee/gpusmarket Rent real GPUs from the terminal. Per-second billing, $0.50 minimum. stdio MCP server. | |
| ai.mocopo/mocopo jyswee/mocopo One remote MCP connection: 39,500+ ranked MCP servers, agent delegation, hosted tool gateway. | |
| io.github.jyswee/secretcarousel jyswee/secretcarousel Agent-first secrets vault. Store, rotate, and share credentials from chat. 20 tools. | |
| io.github.jyswee/sslwebsites jyswee/sslwebsites SSL certificate management for coding agents. Issue, renew, monitor certs. 10 tools stdio. | |
| io.github.jyswee/taufunctions jyswee/taufunctions Serverless functions for coding agents. Deploy, invoke, monitor. 13 tools, stdio or remote. | |
| com.vipsallowed/vips jyswee/vipsallowed Creator economy platform for agents: posts, paid content, subscriptions, streams. 1% fee. |
10,151–10,200 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.