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 |
|---|---|
| io.github.SkyUnlimit/sinoconnection-esim-mcp skyunlimit/sinoconnection-esim-mcp China & Asia travel eSIM specialist. 200+ countries. No-VPN internet in China. | |
| Skyvern skyvern-ai/skyvern AI-powered browser automation — navigate, click, fill forms, and extract data from any website. | |
| zspace-cli skyzhao1223/zspace-cli Zero-config MCP server + CLI for ZSpace NAS: file ops and pool stats via the desktop client. | |
| navette — the browser for agents slabbdev/navette A 659 KB Rust binary driving the OS WebView — no Chromium. 16 MCP tools for AI agents. | |
| io.github.SlambertDK/shelfatlas-catalog slambertdk/shelfatlas-mcp Danish grocery catalog as MCP tools: live offers across all major chains, stores, EAN lookup, stock. | |
| Cowork slashman413/cowork Self-hosted MCP task inbox shared by Claude Code, Codex, Gemini CLI and local LLMs. | |
| io.github.SLAtech-IL/mediora-mcp slatech-il/mediora-mcp Doctor-reviewed blood-test markers, conditions & symptoms as agent tools. EN/RU/HE. Hosted. | |
| io.telemost/telemost-mcp-server slava01011910-ops/telemost-mcp-server Telegram channel analytics and statistics for AI agents, pay-per-call in USDC via x402. | |
| CellarTracker slavins-co/cellartracker-mcp Read-only access to your CellarTracker wine cellar: inventory, drinking windows, purchases, notes. | |
| io.github.slee1996/pillowfort slee1996/pillowfort Private encrypted rooms for agents and people to invite, chat, draw, and play. Local and hosted MCP. | |
| Sleek sleekdotdesign/mcp Design your mobile app UI with AI, then have your coding agent build the real app from it. | |
| Calculator slettmayer/calc-mcp-server Exact arithmetic: one calculator tool over an AST allowlist, with integers exact at any size. | |
| GeoSphere Austria Weather slettmayer/geosphere-mcp-server High-resolution GeoSphere Austria weather, storms and air quality. Austria and the Alps only. | |
| OeBB (Austrian Railways) slettmayer/oebb-mcp-server OeBB (Austrian Railways) train data: stations, departures, connections, service alerts. | |
| ai.smithery/slhad-aha-mcp slhad/aha-mcp A TypeScript MCP server for Home Assistant, enabling programmatic management of entities, automati… | |
| com.slickfast/mcp slickfast/slickfast JSON in. Chart or Page out. Same picture forever. Scientific plots included. | |
| Slideless slideless-ai/mcp List, share, upload, and manage Slideless HTML presentations from any MCP host. | |
| SlickTrip sliktrip/slicktrip-mcp Live flight, hotel and seat prices, cheapest-day calendars, and price-drop alerts. | |
| io.github.slima-ai/slima slima-ai/slima-mcp MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader. | |
| Jeero MCP slimndap/jeero-mcp Local Jeero MCP server backed by Mother and SQLite. | |
| Slingshot brand kit slingshot-fyi/brand-kit Slingshot's brand guides, design tokens and an off-brand colour check, for any MCP client. | |
| Mneme Memory slow-stack/mneme Cross-session memory for AI coding agents via six tools; local-first SQLite store. | |
| Slowave slowave-ai/slowave Local adaptive memory for AI coding agents through a five-tool MCP lifecycle. | |
| io.github.Slowper/anylens slowper/anylens Turn videos, PDFs, screenshots, and articles into anchored, cached understanding for agents. | |
| Guitar Practice Routine App — Chord Charts slshults/gpra-chord-charts-mcp Look up a guitar chord by name and get a text chord diagram. 12,708 standard-tuning names. | |
| io.github.sluyasu/openinsurance-wiki sluyasu/openinsurance Open, source-cited knowledge base of Belgian insurance products: search, compare, verify, overlaps. | |
| Modisign slvdev/modisign-mcp Make animated overlays and edit short videos with Modisign. Everything renders on your computer. | |
| sift slymnysr/sift Runs a command, keeps every byte on disk, returns only the lines that matter | |
| io.github.SMABoundless/crossref smaboundless/crossref-mcp-server Search and retrieve scholarly metadata from the Crossref REST API | |
| io.github.SMABoundless/orcid smaboundless/orcid-mcp-server Search ORCID researcher profiles, retrieve works, and export citations | |
| io.github.SMABoundless/scopus smaboundless/scopus-mcp-server Search Scopus abstracts, authors, and export citations via Elsevier API | |
| io.github.SMABoundless/semanticscholar smaboundless/semanticscholar-mcp-server Search 200M+ papers, authors, citations, and recommendations via Semantic Scholar | |
| io.github.SMABoundless/unpaywall smaboundless/unpaywall-mcp-server Open-access availability for 120M+ scholarly articles via the Unpaywall API | |
| ShotAPI MCP Server smallhandsome/shotapi-mcp-server Screenshot and HTML render MCP server for AI agents | |
| owlpost smankoo/owlpost IMAP/SMTP email for iCloud, Gmail, Proton Bridge and more: search, read, follow threads, send. | |
| io.github.parallelromb/smara smara-io/mcp-server Persistent cross-platform memory for AI agents with Ebbinghaus decay scoring. | |
| io.github.silversurfer562/memdocs smart-ai-memory/memdocs Git-native project memory for AI assistants with enterprise-grade audit compliance | |
| is-real-biz smart-link-t/is-real-biz Verify business legitimacy by domain or name in <2s. Trust score, verdict, evidence. x402-payable. | |
| SmartAgent CRM smartagent-ru/smartagent-mcp MCP server for SmartAgent CRM: leads, tasks, sales pipelines, property listings | |
| Stratum MCP smartmemory/stratum Structured execution for Claude Code — contracts, postconditions, gates, guardrails. | |
| REGON (Polish business register) smartmobilehouse/regon-mcp Look up Polish businesses in the GUS REGON register (BIR1) by NIP, REGON, or KRS. | |
| VAT White List (Poland) smartmobilehouse/vat-whitelist-mcp Look up Polish VAT taxpayers by NIP, REGON or bank account and verify account associations. | |
| CliDeck MCP — Network Knowledge smartroot7/clideck-mcp Free verified network knowledge for AI agents: deterministic answers, honest unknowns. | |
| io.smartroutes/smartroutes smartroutes-io/smartroutes-mcp Route optimisation, orders, booking and fleet management for a SmartRoutes depot. | |
| Senlay Physical Context smartsurfsolar/senlay-platform Physical-world evidence and operability checks with provenance and explicit data gaps. | |
| smbCloud Mail & Auth smbcloudxyz/smbcloud-cli Email infrastructure and authentication for developers: domains, inbox routes, auth apps, deploys. | |
| Math board smdesai27/math-board A local, view-only chalkboard the model draws on: equations, plots, molecules and diagrams. | |
| io.github.smeet666/mcp-lyricscom smeet666/mcp-lyricscom Search song lyrics on lyrics.com by word or by title, and fetch full lyrics. No API key required. | |
| io.github.smeet666/mcp-metacritic smeet666/mcp-metacritic Search Metacritic films, shows and games, read scores and critic reviews. No API key. | |
| io.github.smeet666/mcp-rule34 smeet666/mcp-rule34 Search rule34.xxx posts by tag through the site's own API. Needs a rule34.xxx API key. |
17,051–17,100 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.