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
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| Rasterloom — Artwork, Vector & PDF Editing (Alpha) lemberalla/tinythings-mcp-connectors Local artwork, vector, PDF and moodboard editing. Requires Rasterloom 0.4.1 alpha or later. | |
| Disk Inventory MCP lemmalemming/disk-inventory-mcp Read-only macOS disk analysis with bounded scans, size queries, and extension breakdowns. | |
| io.github.lemmaoracle/mcp lemmaoracle/lemma Verifiable provenance for AI agents — ZK proofs over confidential documents, no plaintext exposure. | |
| LemMeBuyIt lemmebuyit/cloudflare-mcp Live product prices, promotions, price history and UPC/ASIN matching across 100+ U.S. retailers. | |
| FAQai lemuran/faqai-app Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host. | |
| com.zeltser/website-search lennyzeltser/zeltser-website-mcp-server Improve security writing, score it against rubrics, plan IR, CTI, vuln, and product strategy. | |
| Leo Training leo-runningcoach/coachleo Running, trail and triathlon coach. Reads Strava, Garmin, COROS, Suunto, Polar. Adapts to your feel. | |
| Shaka leocode09/shaka Company email for Rwanda. Read and send mail from a Shaka mailbox over OAuth or an API key. | |
| io.github.leohoudinisanders-byte/forensics-mcp leohoudinisanders-byte/forensics-mcp x402-payable on-chain forensics tools: token verdicts, settle-safe RWA screens, wallet trust screens | |
| MISSING leoleon506/missing Fallback capability resolver for AI agents with replay-verified discovery and x402 paid execution. | |
| NeuroFlow MCP leonardocesca/neuroflow Local-first MCP server for guided goals, microtasks, and lower cognitive-load flows. | |
| io.github.leonardomso/luca-mcp leonardomso/luca Work your Luca workspace from any MCP client: 67 tools for leads, conversations, and campaigns. | |
| Leonida Lab: GTA 6 facts, official or not leonidalab/gta6-mcp Unofficial GTA 6 facts tagged official or reported. Not affiliated with Rockstar Games or Take-Two. | |
| Songbrain leonuli/songbrain Song in, video plan out: beat grid, best moments, timed lyrics, story and a beat-synced shot plan. | |
| Ranomics Platform leowan7/ranomics-mcp Wet-lab triage for AI binder-design agents. Yeast display, mammalian display, DMS at library scale. | |
| ThabangVision leparalamapara/thabangvisionaistudios Rent camera and production gear in South Africa and find ID-checked creators. | |
| io.github.lesofi/handinloop-mcp-server lesofi/handinloop Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail. | |
| Webhook Studio lestertww/webhookstudio Keyless webhook endpoints: capture, wait, replay, forward, and generate types from real traffic. | |
| io.github.let-sunny/canicode let-sunny/canicode Analyze Figma designs for dev & AI readiness. 39 rules, scoring, HTML reports. | |
| MoneyMatter letehaha/moneymatter Personal finance tracker: accounts, transactions, budgets, investments and analytics over OAuth. | |
| LetKite letkite/letkite-router Run commands and manage files on your own machines. Needs a LetKite account; OAuth sign-in. | |
| io.github.rosekamallove/letmepost letmepost/letmepost.dev MCP server for letmepost.dev. Publish across 8 social platforms from any agent. | |
| SHIP letsship/mcp Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests. | |
| com.letta/memory-mcp letta-ai/memory-mcp MCP server for AI memory management using Letta - Standard MCP format | |
| Letterly letterlyapp/letterly-mcp Bring Letterly voice notes and meetings into your AI chat to search, rewrite, translate, and more. | |
| Levels.fyi levels-fyi/levels-fyi-plugin Salary, level and job data from 1M+ pay reports. Benchmark pay, evaluate offers, search open jobs. | |
| Context Atlas levin-staudt/contextatlas Find llms.txt, docs, MCP servers, skills and CLIs for a tech stack, for coding agents. | |
| Levirge Brain levirge/brain Shared MCP memory for AI agents: knowledge base, skills, todos and agent-to-agent handoffs. | |
| Levirge Search levirge/search Web search and page reading for AI agents, including JSON APIs, RSS feeds and YouTube. | |
| Hex SSH levnikolaevich/claude-code-skills Token-efficient SSH MCP with hash-verified files and persistent tmux sessions. 14 tools. | |
| Google News lewisdonovan/google-news-scraper Search Google News, get top stories and read articles. No API key or headless browser. | |
| TableJourney food travel lewismvaughan/tablejourney-mcp Food travel in 224 cities: verified places, festivals, tours. Agents earn 50% via partner tools. | |
| Probe V0 lexbritten/probe-mcp Experimental MCP server for current empirical verification of explicit public HTTPS endpoint claims. | |
| io.github.lexsocket/mcp-eurlex lexsocket/mcp-eurlex Eurlex MCP client: Access EU law & Official Journal. https://www.lexsocket.ai/ | |
| io.github.lexsocket/mcp-ted lexsocket/mcp-ted TED MCP Server: Real-time EU public tenders access. https://www.lexsocket.ai/ | |
| io.github.lexwhiting/settlegrid-discovery lexwhiting/settlegrid Discover monetized AI tools on SettleGrid. Search by category, get pricing. | |
| Contaí — Calculadoras Fiscais Brasileiras lfhillesheim/calculadora 32 ferramentas MCP de cálculo fiscal/trabalhista BR (CLT, INSS, IRRF, PJ, finanças, saúde). | |
| ComplianceCN — toys, batteries, cosmetics, food contact: CE, GPSR, UN 38.3, CPC/GCC and more liamohtee/agentcn Source-cited EU/UK/US/AU market-access checks for Amazon and cross-border product compliance. | |
| 世福源供应链 · 企业官网开放数据 MCP liaooyao/company-site-mcp 海南世福源冻品火锅食材供应链官网开放数据：全站检索、企业概况、产品矩阵、成功案例、FAQ、招聘 6 个只读工具，API Key 官网自助申请。 | |
| covdbg liasoft/covdbg-mcp C++ code coverage on Windows for AI agents. Find uncovered code from PDBs, no rebuild. | |
| com.rubrkit/rubrkit liberat0r/react-rubrkit MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output. | |
| io.github.library-x/tuney library-x/tuney_mcp Royalty-free music fitted to your length: find, generate, adjust and download tracks and stems. | |
| tmux libtmux/libtmux-go Drive one tmux server: sessions, windows, panes, and the output they produce. | |
| Licensy licensyai/licensyai-mcp Real-time U.S. medical license verification across all 50 states + DC. | |
| Korea Company Data lichtsalz/korea-data Korean company identity, registration status and monthly payroll-based employment, in English. | |
| Transpic Image Translator lickfeng88888/transpic.ai Translate text inside images while preserving layout; OCR extraction. Free API key. | |
| nomue Record Verifier licklider-ai/nomue-mcp Local verification of nomue Protocol Records; current release supports the Release 1 Welch bundle. | |
| AKD VaultPDF lifeabundantly/akd-vaultpdf-mcp On-device PDF, resume and CSV tools. Files never leave your machine. Refuses rather than guessing. | |
| io.github.auroracapital/claude-ops-telegram-server lifecycle-innovations-limited/claude-ops Telegram personal-account MCP (MTProto user-auth). Read DMs, send messages, search across chats. | |
| BabyNews (베이비뉴스) lifenplanner/babynews-gemini-extension Korean pregnancy, birth and parenting news, Q&A and regional childbirth support. Read-only. |
25,101–25,150 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.