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 |
|---|---|
| Microsoft Sentinel Data Exploration microsoft/sentinel-data-exploration-mcp Find relevant security data from Sentinel data lake for building effective agents. More:aka.ms/s/de | |
| Microsoft Learn MCP microsoftdocs/mcp Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs. | |
| artifacts.boo micthiesen/artifacts.boo Agents publish interactive pages people comment on, approve and fill in; agents read the answers. | |
| gadak midagedev/gadak Ask a local SQLite mirror of your Jira and Confluence: SQL, full-text search, issue detail. | |
| io.github.midasflowai-lab/midasflow-mcp-quickstart midasflowai-lab/midasflow-mcp-quickstart Agent-native crypto market-data over MCP+REST: order flow, whales, liquidations, calibrated scores | |
| io.github.middleBrick/mcp-server middlebrick/mcp-server Scan APIs for OWASP Top 10, LLM, and GraphQL security vulnerabilities. | |
| Crypto Pulse midnight232/crypto-pulse-api x402 Solana crypto pulse for agents + free BTC/ETH/SOL prediction arena | |
| MidOS - MCP Community Library midosresearch/midos Curated knowledge for AI agents — 19K chunks, 121 skills, semantic search via MCP | |
| Bible by Midvash midvash/bible-mcp Free, no-key Bible MCP server — 86 translations in 32 languages, from any MCP client. | |
| Gvnr mightbesaad/gvnr Budget & cost control for AI agents — per-agent spend caps + rate limits before each call. | |
| Render Unto Caesar mightydatainc/ruc-mcp An MCP server that fuses LLM contextual intelligence with procedural code reliability. | |
| io.github.migmediamarketing-ai/noto-crm migmediamarketing-ai/noto-crm-mcp-server Minimalist CRM with AI agent for freelancers — pricing, features, comparisons | |
| io.github.miguelgandia/enchantedcolony miguelgandia/enchantedcolony-mcp Be a neighbor in EnchantedColony: AI voters arguing Puerto Rico's front pages. Read, sign up, post. | |
| ai.smithery/miguelgarzons-mcp-cun miguelgarzons/mcp-cun Greet people by name with friendly, personalized messages. Add a warm touch to onboarding, demos,… | |
| AutoContent miguelpieras/autocontent-mcp Turn documents, URLs and text into videos, podcasts, slides, infographics and recurring content. | |
| Designelier miguelpieras/designelier-mcp Generate matching icon sets, spot illustrations and transparent design assets for sites and apps. | |
| Memory Vault mihaibuilds/memory-vault Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT. | |
| io.github.miisodev/brainllm miisodev/brainllm Self-hosted memory for LLMs in TriliumNext, structured by the server and editable by you. | |
| text-to-model mikan-atomoki/text-to-model Turn natural language into 3D models in Fusion 360. 64 CAD tools including sketches, extrudes, fillets,and JIS standard parts. | |
| io.github.Mike25app/scaleforge-mcp-meta-ads mike25app/scaleforge-mcp-meta-ads Meta Ads MCP by ScaleForge — control Facebook & Instagram Ads via Graph API v24.0. 32 tools. | |
| io.github.MikeAshtonEILLC/usdi-mcp-server mikeashtoneillc/usdi-mcp-server Live tools for USDi: CPI-indexed exchange rate, contract/pool addresses, and mint/redeem mechanics. | |
| balldontlie-mcp mikechao/balldontlie-mcp An MCP Server implementation that integrates the Balldontlie API, to provide information about players, teams and games for the NBA, NFL and MLB. | |
| Brave Search MCP mikechao/brave-search-mcp An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities | |
| Met Museum MCP Server mikechao/metmuseum-mcp A MCP Server that lets user ask AI models to discover the collection of the Metropolitan Museum of Art. Adds the discovered art works as Resources on the server. | |
| io.github.mikeholownych/unifi-mcp mikeholownych/unifi-mcp MCP server for Ubiquiti UniFi Network and Protect. 63 tools, 16 agent skills. | |
| io.github.mikejj-creation/stocksense mikejj-creation/stocksense Financial data for AI agents: SEC filings, price history, insider trades, and more. | |
| podkop-mcp mikel38487/podkop-mcp MCP server for managing Podkop and Forkop on OpenWrt over SSH | |
| Enterprise Research Evidence Chain mikeli20221102-ux/diyan-research-mcp Read-only enterprise research MCP: frameworks, frozen snapshots, sourced results. No trading advice. | |
| io.github.mikemark78/agentmark mikemark78/agentmark Sell unused AI subscription capacity as finished work. SOL/USDC escrow on Solana, 0% fees. | |
| io.github.mikerawsonnz/traced-llm-proxy mikerawsonnz/gosce-agents Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t | |
| io.github.Mikerichardmail/clarik-mcp-server mikerichardmail/clarik-mcp-server Clarity and memory persistent workspace context manager for Claude. | |
| TubePull miketwalker/tubepull-mcp AI YouTube downloader: save YouTube, TikTok, Instagram + 10 more as MP4/MP3 from any AI chat. | |
| io.github.mikhae1/kubeview mikhae1/kubeview-mcp Read-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters. | |
| ContextDB Memory mikhailbovt/contextdb-codex Local-first durable AI memory with policy-bound recall and a typed project graph. | |
| openradar mikhailsagalaev/openradar Open base of job vacancies and freelance orders from Russian and international boards and Telegram. | |
| io.github.mikimatsub/swsd mikimatsub/swsd-mcp MCP server for SolarWinds Service Desk tickets, catalog, knowledge, ITSM operations, and workflows. | |
| Danish annual reports (CVR) mikkelmanniche-dk/dk-regnskab-mcp Key figures, history and all tagged facts from Danish companies' annual reports (XBRL). | |
| trvl mikkoparkkola/trvl Door-to-door travel MCP + CLI: flights, hotels, trains, cars, ferries. No API keys, Go binary. | |
| JMAP Email mikluko/jmap-mcp Email management via JMAP — mailboxes, messages, identities, and Sieve scripts | |
| io.github.mikusnuz/agent-link mikusnuz/agent-link-mcp Bidirectional AI agent collaboration — spawn and communicate with any agent CLI | |
| io.github.mikusnuz/iptime-mcp mikusnuz/iptime-mcp Manage ipTIME routers through a local, safety-gated MCP server with firmware-aware capabilities. | |
| BotGathering recipes mil0s2/botgathering-recipes Search, read, download and report on tested step-by-step recipes (playbooks) for AI agents. | |
| quickcast-mcp miladmet/quickcast-mcp Turn screen recordings into automated Playwright E2E reproduction tests, structured GitHub bug reports with clickable video timestamps, and SOP walkthroughs. | |
| Provenio — Art Intelligence mildo-ai/provenio Art provenance intelligence — 282K-node knowledge graph with cited answers and honest gaps. | |
| Verity Score milka974/verityscore-mcp GEO audit for Shopify: AI readiness score, recommendations, and 15 vertical checklists. | |
| Cheaplane millennialdreamer/cheaplane Offload grunt work from your premium agent to cheap models — auto-routing and billing isolation. | |
| io.github.miller-joe/comfyui-mcp miller-joe/comfyui-mcp MCP server for ComfyUI: text-to-image, variations, img2img refine, upscale, image proxy. | |
| io.github.miller-joe/shopify-mcp miller-joe/shopify-mcp MCP server for Shopify Admin API with a ComfyUI bridge for AI product image generation. | |
| io.github.miller-joe/youtube-mcp miller-joe/youtube-mcp MCP server for YouTube creator-ops with a ComfyUI bridge for AI thumbnail generation. | |
| io.github.millerchou/rocketchat-mcp millerchou/rocketchat-mcp MCP server for Rocket.Chat — messages, DMs, search, files, and channels over stdio |
13,101–13,150 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.