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 |
|---|---|
| Attester Oracle maminihds/attester-mcp Verify PyPI and npm packages, symbols, and version diffs against real artifacts. Free, no account. | |
| Google Search Console mamrrez/gsc-mcp-full Google Search Console: 37 tools, every API endpoint, hourly data, history beyond 16 months. | |
| Google Trends mamrrez/gtrends-mcp-full Google Trends: Trending Now, interest over time, regions, related searches. No API key. | |
| ai.justdrop/mcp managed-digital-llc/justdrop-mcp Live, end-to-end encrypted, ephemeral file transfer between your AI agent and any device. | |
| FastMCP - FastAPI MCP Framework & Runner manas-maker/fast-mcp FastAPI-native Model Context Protocol framework and stdio runner. | |
| Web3 Signals manavaga/web3-signals-mcp AI crypto buy/sell signals for 20 assets: 6 data dimensions fused into 0-100 scores. x402 + MCP. | |
| Zero Slop manavmishra/zeroslop Zero Slop edits AI-assisted writing through MCP, reducing stock phrasing and repetition while checking grammar and flow. It returns the rewrite with writing scores and flags detected changes to names, numbers, quotations, and links. | |
| TheCrawler manchittlab/thecrawler Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support. | |
| Mandala Computer mandalacomputer/mcp Cloud desktops for AI agents: create a Linux computer, see its screen, click, type and run tasks. | |
| Mandare mandarelabs/mandare Accountability for AI agent fleets: verify a signed, hash-chained Mandare ledger, check budgets, kill an agent, and issue passports and mandates. | |
| ReturnCheck mangelmartinezfer-hue/returncheck Can this product actually be returned? The merchant's exact clause, its URL and the date. | |
| io.github.Mangomunchr/farpy mangomunchr/farpy-public FARPY routes GPU workloads to qualified compute and returns verified artifacts and receipts. | |
| TrueIcon manikumarkv/trueicon Lets AI coding assistants search the icon packages actually installed in your project. | |
| dittu manish-tamang/dittu Clone any website's frontend into Next.js or Astro and verify it with pixel diffs. | |
| LLM Provider MCP manishiitg/llm-provider-mcp Delegate asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi. | |
| line-bot-ops-mcp mankhonggarden/line-bot-ops-mcp MCP server to operate your own LINE bot: webhook queue health, failed jobs and retries, push, Rich Menu, follower insight. | |
| Space Standards manojknaikade/space-standards-mcp Cited, requirement-level Q&A over ECSS and NASA standards you supply (bring your own documents) | |
| My Next Adventure mantacodedevs/mcp-mynextadventure Create trips, compare variants side by side, and add accommodation, transport and event options. | |
| Manticore Search manticoresoftware/mcp-manticore MCP server for Manticore Search — lets AI assistants query and manage search databases. | |
| MotoGP (Race Results) manuelescrig/raceresults-mcp Live MotoGP, Moto2 and Moto3 standings, results, calendar, riders, live timing and news. | |
| io.github.manuelinuxkr/substrate-browser manuelinuxkr/substrate-b Token-first headless browser for AIs. Extracts a tiny semantic graph, cutting HTML bloat by 95%. | |
| qbt-kit manueltarouca/qbt-kit A client, CLI and MCP server for the qBittorrent WebUI API, covering all 123 endpoints on qBittorrent 5.2.3. Destructive operations require confirmation, and read-only mode blocks every mutating endpoint, including through the raw call. | |
| MemCore manuelwarland/memcore Local long-term memory shared by every AI coding assistant on one machine: a single SQLite file with FTS5 search and optional multilingual semantic search, no daemon and no cloud. | |
| OpenCode MCP Bridge manuotel/opencode-mcp-bridge Coordinate and verify OpenCode workers over MCP Streamable HTTP. | |
| io.github.manusa/podman-mcp-server manusa/podman-mcp-server A Model Context Protocol (MCP) server for container runtimes (Podman and Docker) | |
| Uruguay: datos públicos manusabbath-arch/mcp-uruguay Uruguayan public data from primary sources: BCU rates, CPI, fuel, weather, IDE.uy geocoding, RUT. | |
| Namaste America manvigallc007-spec/indousmcp Agent-first directory for Indians from India in the USA — restaurants, temples, events & more. | |
| ManyContacts - WhatsApp Business MCP manycontacts/mcp WhatsApp Business MCP: send messages, manage contacts, campaigns, and AI agents. | |
| io.github.mapbox/mcp-docs-server mapbox/mcp-docs-server AI access to Mapbox docs, API references, style specs, and guides. No token required. | |
| io.github.mapdevsaikat/quantaroute-geocoder mapdevsaikat/quantaroute-geocoder Geocode addresses, lookup administrative boundaries, and process DigiPin codes for India | |
| portview mapika/portview See what's on your ports, the processes behind them, and diagnose conflicts and leaks. | |
| maple maple-kit/maple Gives your coding agent the review comments left on a running frontend with Maple. It lists open comments with the element, source location and screenshot they point to, waits for new ones, and resolves them when the fix is in. | |
| Maplith Bridge maplith/agents Share a folder of data files read-only over MCP, and fill it from PostgreSQL under a read-only role. | |
| io.maproll/maproll maproll-io/mcp Make production-ready static maps. Every map is a URL you can embed anywhere. | |
| MapRouter maprouter-dev/maprouter-mcp Maps, geocoding and time zones for AI coding agents, on OpenStreetMap, with hard prepaid spend caps. | |
| io.github.maraventano/map maraventano/map A subtractive MCP for agent commerce: read · pay · publish. Teacher, not butler. | |
| hvac-quotes marceausolutions/hvac-quotes-mcp Enables HVAC equipment Request for Quote (RFQ) management via MCP, allowing users to submit RFQs, check status, and compare quotes from distributors. | |
| io.github.wmarceau/md-to-pdf marceausolutions/md-to-pdf-mcp Converts markdown files into professional PDF documents with automatic table of contents and interactive navigation. | |
| Rideshare Comparison MCP marceausolutions/rideshare-comparison-mcp Compare Uber and Lyft prices for any route, get supported cities, and retrieve booking links using Claude Desktop. | |
| SeedBase Test Data marcelglaeser/seedbase-node Generate realistic, FK-consistent synthetic test data for your databases from your AI assistant. | |
| io.github.marcelinero/auditoria-skills marcelinero/auditoria-skills-mcp 20 SKILLs de auditoría interna para agentes de IA según IIA, COSO, NIST, ISO, COBIT y ACFE. | |
| Spotify MCP Server marcelmarais/spotify-mcp-server A lightweight Model Context Protocol server that enables AI assistants like Cursor & Claude to control Spotify playback and manage playlists. | |
| io.github.MarcelRoozekrans/longterm-memory marcelroozekrans/longtermmemory-mcp A fully local MCP server for long-term memory with semantic search | |
| The Data Collector marcindudekdev/the-data-collector Search Hacker News, Bluesky, and Substack from a single MCP interface | |
| Staan marcinwolnyeu/staan-mcp Web search with full-page content and grounded answers from the Staan API. | |
| io.github.marcoguillermaz/tierward marcoguillermaz/tierward Read a Tierward project's governance state (doctor, team-settings, arch-audit, skills) over MCP. | |
| Substack MCP Server marcomoauro/substack-mcp Manage Substack publishing, subscribers, analytics, reader feeds, comments, and images through MCP. | |
| mq-bridge-app marcomq/mq-bridge Move data between 15+ databases, queues and files at high throughput, without it entering context | |
| io.github.marcosnovo/lexvibe marcosnovo/lexvibe-mcp One-step legal compliance for vibe-coded apps: privacy, terms, cookie banner and EU AI Act check. | |
| com.numbru/client-compass marcus160365/numbru-mcp-server Behavioral intelligence for client-facing professionals. Know who you're walking into. |
11,451–11,500 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.