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 |
|---|---|
| Virtual Filesystem lu-zhengda/mcp-virtual-fs PostgreSQL-backed virtual filesystem for agents: session isolation, shared stores, POSIX ops, RLS. | |
| io.github.luarss/alternativespe-mcp luarss/alternativespe-mcp Private-market data across Southeast Asia via the Alternatives Partner API v3 | |
| SPR (Sealed Payment Record) luca-network/spr Seal every payment your AI agent makes as a signed record, on your own machine, with your key. | |
| ShareCut QR & Short Links lucarsdeco/sharecut-mcp Short links you can re-point after printing the QR, with click analytics. Free QR, no key. | |
| diagonaldiagrams lucas19919/diagonaldiagrams Diagrams and charts for agents: Mermaid or a spec in, an audited SVG out. | |
| Firebird MCP Server lucasgabriel0802/firebird-mcp Firebird (2.5 to 5.0) MCP server with PLAN inspection and multi-database routing | |
| BigQuery MCP server lucashild/mcp-server-bigquery A Model Context Protocol server that provides access to BigQuery. This server enables LLMs to inspect database schemas and execute queries. | |
| io.github.lucaslubi/fidacy-mcp lucaslubi/fidacy-mcp AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required. | |
| lcc — Local Context Compiler lucasmartins-ai/lcc Compact agent context verbatim, offline: cut spent tool outputs, recall them by hash. | |
| LookaCrawler lucasmartins-ai/lookacrawler Free, open-source, token-efficient local alternative to Firecrawl with a native Model Context Protocol (MCP) server. Achieves >73% token reduction by pruning web noise before Markdown extraction, uses Playwright with stealth fingerprint pat | |
| io.github.lucasmella-stack/mismem lucasmella-stack/mismem Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian) | |
| Querido Diário MCP Server lucaspmgomess/querido-diario-mcp-server Unofficial, read-only MCP server for the public Querido Diário API (Brazilian municipal gazettes) | |
| Sketchdex lucasr1b/sketchdex An MCP server that lets AI agents draw hand-drawn Excalidraw diagrams as files on your machine. | |
| MCP Dados Brasil lucianoon/mcp-dados-br Servidor MCP com dados oficiais brasileiros: IBGE, Banco Central, INMET, Câmara e Senado. | |
| PJe-Calc MCP lucianumm/pjecalcmcp Monta, liquida, confere e atualiza cálculos trabalhistas no PJe-Calc Cidadão (Windows). | |
| io.github.Lucid-Systems-LLC/lucid-apple-mcp lucid-systems-llc/lucid-apple-mcp On-device Apple Intelligence as MCP tools for macOS — OCR, tables, entity detection, generation. | |
| Lucid lucidsoftware/lucid-mcp-server Lucid’s connector creates diagrams, searches, edits, shares, and retrieves docs to summarize. | |
| sota-anchor luckmanqasim/sota-anchor Finds what shipped after your coding agent's training, before it rebuilds it from scratch. | |
| Dense Knowledge lucky44k/dense-knowledge-mcp Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval. | |
| Cairn luckyjackluo/cairn Local-first file-organization tools for your AI agent: tag, query, and digest a folder. No cloud. | |
| io.github.lucle87/boo-mpp-mcp lucle87/boo-mpp-mcp Pay-per-call crypto data for AI agents. USDC.e on Tempo via MPP. No API key. | |
| io.github.lucle87/boo-x402-mcp lucle87/boo-x402-mcp Pay-per-call crypto data for AI agents. USDC on Base via x402. No API key. | |
| Lucyd lucyd-trade/mcp-server Trade Bitcoin Up/Down prediction markets on Lucyd: markets, order books, orders, positions. | |
| io.github.lucyfuur94/webnav lucyfuur94/webnav-core A zero-LLM MCP server that replays recorded site maps instead of re-exploring browser routes. | |
| mcp-national-rail lucygoodchild/mcp-national-rail An MCP server to retrieve train schedules from National Rail using the Realtime Trains API, providing tools for live departures and arrivals. | |
| io.github.ludmila-omlopes/youtube-video-analyzer ludmila-omlopes/youtube-video-analyzer-mcp MCP stdio server for analyzing YouTube videos with Google Gemini | |
| Ludo AI Game Assets ludo-ai/ludo-mcp Generate game assets with AI: sprites, animations, 3D models with rigging, video, music, SFX, voices | |
| Obsidian Vault MCP luffysolution-svg/obsidian-vault-mcp Local Zotero, MinerU, Obsidian literature workflow with transactional Analysis notes. | |
| OmniScholar luffysolution-svg/omnischolar Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents. | |
| io.github.vmedvedovskiy/luftpause luftpause/luftpause async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs | |
| aichivist luftphilipp/aichivist Clean up your files like an archivist: rename, sort, de-duplicate with plans you approve and undo. | |
| Toon Memory luiggival08/toon-memory Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM | |
| io.github.luisbretasjr/routekit luisbretasjr/routekit-mcp Route optimization API for Brazil. Routes, distance matrices, and VRP solver. | |
| Furniture Designer luisenvilla/furniture-designer-mcp Professional furniture design: specs, validation, cut optimization, BOM, and 3D reports. | |
| closure_drift luizfnsilva/closure_drift Before an agent tags a release: does that version label already name different code in the git tags? | |
| framedeck-mcp lukaris/framedeck-mcp MCP server for Framedeck — a Kanban content production manager for YouTube, Instagram, TikTok and Podcast creators. 32 tools to manage productions, stages, frames, checklists, comments, labels, and time tracking, with full MCP safety annota | |
| ai.smithery/lukaskostka99-marketing-miner-mcp lukaskostka99/marketing-miner-mcp Discover high-impact keyword ideas across Central and Eastern European and English markets. Analyz… | |
| io.github.lukasschwarz/elster-mcp-server lukasschwarz/elster-mcp-server Drive the German tax portal ELSTER via Puppeteer: submit UStVA, prepare EUER/ESt, sync inbox. | |
| io.github.luke-fairbanks/broll luke-fairbanks/broll Content studio MCP for coding agents: BYO keys, deterministic video rendering, draft-first posting | |
| io.github.lukebmandel-debug/alto-connector lukebmandel-debug/alto-connector Build an interactive timeline from your own materials — never from invented content. | |
| CalDAV MCP Server lukegskw/caldav-mcp A TypeScript MCP server for iCloud Calendar with native multi-VALARM support. | |
| Spacery lukehollis/spacery Publish 3D scans, Gaussian splats and 360 tours as shareable spaces, and build guided tours in them | |
| claude-terminal-mcp lukelamb/claude-terminal-mcp Give Claude Desktop terminal, filesystem, and background-job access on your local Linux machine. Zero-dependency MCP extension, MIT-licensed. | |
| RepoRelay lukie-81/reporelay Bounded local MCP access to one approved repository for AI read/search and structured handoffs. | |
| io.github.lulzasaur9192/agent-arcade-mcp lulzasaur9192/agent-arcade-mcp Play Chess, Go, Trading & more against AI agents on Agent Arcade with Elo rankings | |
| io.github.lumiclip/lumiclip lumiclip/lumiclip-mcp-server Turn YouTube videos into short-form clips from any AI assistant | |
| MTA:SA Documentation MCP Server luminaire1337/mtasa-docs-mcp MCP server for MTA:SA documentation with intelligent search and caching | |
| Code Guardian luminarisoftwares/code-guardian A deterministic A-F grade for a repo without running it, plus a verify loop: plan, fix, diff. | |
| Context Guardian luminarisoftwares/context-guardian Compacting proxy for OpenAI-compatible backends, with MCP tools to search the archived history. | |
| Stack Guardian luminarisoftwares/stack-guardian Health doctor for a home AI stack: Ollama nodes, GPUs and tailnet, with graded confidence. |
11,151–11,200 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.