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 |
|---|---|
| Company Lookup (GLEIF) alex-dev-web-c-de/company-lookup-mcp GLEIF LEI and legal entity lookup for AI agents. 20K entities. | |
| Compliance Engine alex-dev-web-c-de/compliance-engine-mcp Sanctions screening (OFAC/UK/EU/UN) + PEP + GLEIF entities via Compliance Engine. | |
| Creator Engine alex-dev-web-c-de/creator-engine Promise extraction and alignment from contracts, NDAs, and legal documents. | |
| Docs-to-JSON alex-dev-web-c-de/document-to-json-mcp Convert documents to structured JSON (invoices, receipts, contracts) in 2 seconds | |
| Finance Validators alex-dev-web-c-de/finance-validators-mcp Validate IBAN, VAT, SWIFT, LEI, and credit card numbers | |
| HS Codes Classifier alex-dev-web-c-de/hs-codes-mcp AI-powered HS customs code classifier. Product description to 6-digit HS code. | |
| PEP Screening alex-dev-web-c-de/pep-screening-mcp Politically Exposed Persons screening for AI agents. 19K PEP records. | |
| io.github.Alex-Dev-Web-C-DE/scopeguard alex-dev-web-c-de/scopeguard-mcp Sanctions scope monitoring. Track entities for changes in OFAC/UK/EU/UN lists. | |
| Watch Engine alex-dev-web-c-de/watch-engine-mcp Currency rates, VAT rates, and tariff rates via Watch Engine. 203 monitors. | |
| io.github.alex-feel/mcp-context-server alex-feel/mcp-context-server An MCP server that provides persistent multimodal context storage for LLM agents. | |
| ai.atdev/supershopping alex-hoyeol-choi/headless-commerce 나만을 위한 AI 쇼핑 MCP — 상품을 자연어로 검색·비교·추천해 사용자의 효과적인 쇼핑을 돕습니다. | |
| DeFi Garden alex0xhodler/defi_garden Underwritten DeFi yield discovery & goal planning for AI agents on Base & EVM. | |
| OpenProject alex13slem/openproject-codex-plugin Manage OpenProject projects, work packages, files, relations, boards, users, and notifications. | |
| io.github.alex3000-ai/ootlebook-explorer alex3000-ai/ootlebook Read the Tari base layer (Minotari): chain tip, blocks and miners' coinbase data. Read-only. | |
| Clarigrid alexanderhoogsteyn/clarigrid Read-only electricity, gas, and weather data with structured provenance and units. | |
| UISandbox alexanderkaan/uisandbox Test your design on the real thing: load a built web app, turn its knobs, verify 1:1, export. | |
| BOFiP — Doctrine fiscale française alexandrecyber/bofip Doctrine fiscale française (BOFiP) : recherche, veille et graphe doctrinal. Etalab 2.0. | |
| Attested Memory Market alexar76/attested-memory Attestable memory, truth, provenance. Hybrid Ed25519 + ML-DSA-65 receipts; USDC settlement on Base. | |
| EMPORION — business facts from public registers alexar76/emporion EU VAT and EORI checks, sanctions screening, company and LEI lookup, ECB rates. Free, no key. | |
| Live weather and air quality (GAIA) alexar76/gaia Weather, air quality and nearest live sensors anywhere, each with a signed receipt. Free, no key. | |
| io.github.alexboissAV/artefact-revenue-intelligence alexboissav/artefact-mcp-server Revenue intelligence MCP: RFM analysis, 14.5-point ICP scoring, pipeline health. HubSpot. | |
| Veabird: ski & beach trip planner alexchouck-hash/bluebird Ski & beach trip planning: resort matching, snow and sargassum forecasts, lodging and flights. | |
| Groki MCP alexclmy/groki-mcp Create and refine nine private, editable meme directions from one brief in any AI agent. | |
| NeuralBrain alexcurpan-cloud/neuralbrain NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments | |
| Rebbel alexdaltonmccoy/rebbel-gemini-extension Designed posts from your website, for Facebook, Instagram, X, Threads and more. | |
| io.github.AlexDeMichieli/weather alexdemichieli/mcp-weather-server An MCP server for weather information. | |
| io.github.alexeibespalov/trident alexeibespalov/tridentpublic Create and edit collaborative architecture diagrams with any AI assistant using the Trident 2D DSL. | |
| io.github.Alexendros/proton-mail-mcp alexendros/proton-mail-mcp Proton Mail MCP via Bridge (IMAP/SMTP) · 13 tools · dual transport stdio + HTTP. | |
| Clevername alexfloyd13/clevername AI agent governance — security scanning, BYOK routing, audit logging, and Council approvals. | |
| io.github.alexgaoth/escalate-anything alexgaoth/escalate-anything Get the upper hand on any big US company: contacts, playbooks and escalation paths. | |
| io.github.AlexikM/gibil alexikm/gibil Spawns an ephemeral Ubuntu VM with project clone, shell exec, file I/O, and auto-destroy on TTL. | |
| net.zzboard/zzboard alexjacobs08/zzboard-board A message board for AI agents. Agents post via MCP; humans get a read-only website. | |
| Dictionary of Applied Machine Learning alexjungaalto/dictionaryofml Look up, search and cross-reference machine-learning terms from dictionaryofml.org. | |
| io.github.alexkirienko/safebot-chat alexkirienko/safebot-chat End-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs. | |
| io.github.alexmeckes/gifgif alexmeckes/gifgif Fit a video or GIF to its destination's size limit at measured quality, and share a link. | |
| AgentMade Print on Demand alexmensak/agentmade-print-on-demand Print on demand for AI agents. No sign-up. Picture, words or logo on a tee, hoodie or tote. | |
| com.marutap/marutap alexqueue/maruchit Agent requests a purchase, the human taps approve, the agent gets a card scoped to it. | |
| own-words alexslkgit/own-words Turn notes into a study deck: answer each card in your own words, then compare. | |
| Italian Bus and Rail Search MCP Server alexxanddr/italian-bus-search Read-only Italian bus searches and local NeTEx rail schedules. | |
| AlfaNest Relay alfanestlabs/alfanest-relay Hosted bus for AI agents: lock, events, reject. Publish/apply stay on the sidecar. | |
| Alfanous - Quranic Search Engine alfanous-team/alfanous Search and explore the Holy Qur'an with Arabic text, transliteration, and advanced search support. | |
| Yo alfongj-com/yo-plugin Let agents send content-free push notifications to a paired phone via MCP. | |
| Mantis alfred768/prediction-router-portal Cross-venue prediction market routing for AI agents with arbitrage, quotes, history, and signals. | |
| Universal DB (read-only) alghanim/universal-db-mcp Read-only, guarded SQL access for AI agents: PostgreSQL, MySQL, ClickHouse, Oracle, SQL Server, Db2 | |
| io.github.algolayertechnologies/mapsi-mcp algolayer/mapsi-mcp Geocoding, routing, isochrone, H3, elevation and 13 more geospatial tools via OpenStreetMap. | |
| Agents Commons algorerthym/agentscommons Help desk for agents. Search questions and answers first. Read-only MCP. | |
| StatementSure alhogeiri2025/statementsure-mcp Bank statement PDFs to verified QuickBooks, Xero, OFX, CSV and Excel files. Runs locally. | |
| Cloudprice alialbaker/cloudprice-mcp Compare on-demand compute + storage pricing across AWS, Azure, and GCP. Bulk workload compare. | |
| Hares — MCP security scanner alialrikabi313/hares Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration) | |
| Enoch alias8818/enoch-mcp Operate an Enoch control plane through MCP tools |
20,151–20,200 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.