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.junct-bot/coingecko-mcp junct-bot/coingecko-mcp Coingecko - 36 tools for data, metrics, and on-chain analytics | |
| io.github.junct-bot/coinmarketcap-mcp junct-bot/coinmarketcap-mcp Coinmarketcap - 30 tools for data, metrics, and on-chain analytics | |
| io.github.junct-bot/compound-mcp junct-bot/compound-mcp Compound - 8 tools for lending rates, supply, and borrow data | |
| io.github.junct-bot/curve-mcp junct-bot/curve-mcp Curve - 43 tools for swap quotes, liquidity pools, and trading data | |
| io.github.junct-bot/eigenlayer-mcp junct-bot/eigenlayer-mcp Eigenlayer - 8 tools for staking, delegation, and rewards data | |
| io.github.junct-bot/ens-mcp junct-bot/ens-mcp Ens - 23 tools for name resolution and reverse lookups | |
| io.github.junct-bot/etherscan-api-mcp junct-bot/etherscan-api-mcp Etherscan Api - 71 tools for data, metrics, and on-chain analytics | |
| io.github.junct-bot/euler-mcp junct-bot/euler-mcp Euler - 39 tools for lending rates, supply, and borrow data | |
| io.github.junct-bot/gmx-mcp junct-bot/gmx-mcp Gmx - 139 tools for perpetuals, options, and position data | |
| io.github.junct-bot/hyperliquid-mcp junct-bot/hyperliquid-mcp Hyperliquid - 2 tools for perpetuals, options, and position data | |
| io.github.junct-bot/jupiter-mcp junct-bot/jupiter-mcp Jupiter - 4 tools for swap quotes, liquidity pools, and trading data | |
| io.github.junct-bot/lido-mcp junct-bot/lido-mcp Lido - 6 tools for staking, delegation, and rewards data | |
| io.github.junct-bot/maker-mcp junct-bot/maker-mcp Maker - 10 tools for lending rates, supply, and borrow data | |
| io.github.junct-bot/stargate-mcp junct-bot/stargate-mcp Stargate - 42 tools for cross-chain transfers and bridge data | |
| io.github.junct-bot/synthetix-mcp junct-bot/synthetix-mcp Synthetix - 22 tools for data, metrics, and on-chain analytics | |
| io.github.junct-bot/uniswap-mcp junct-bot/uniswap-mcp Uniswap - 17 tools for swap quotes, liquidity pools, and trading data | |
| Junê junemind/june-mcp Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions | |
| Usercall junetic/usercall-mcp Give your AI agents the ability to ask real users why. | |
| jungle-grid-mcp-server jungle-grid/mcp-server Jungle Grid MCP Server lets AI agents submit, estimate, monitor, and retrieve logs for GPU workloads through Jungle Grid. It enables agentic execution for inference, training, fine-tuning, and batch jobs without manually choosing GPU provid | |
| DEEPBOM junhwan-kwon/deepbom Browser-local and CLI static evidence for deployed AI model artifacts. | |
| Juniper Routing Director MCP Server juniper/routing-director-mcp-server MCP server to integrate with Juniper Routing Director | |
| Junipr MCP Server junipr-labs/mcp-server Enables AI assistants to capture webpage screenshots, generate PDFs from URLs or HTML, and extract rich metadata like Open Graph and JSON-LD data. It provides tools for web-to-image/PDF conversion and structured data extraction through the | |
| io.github.JUNKDOGE-JOE/ae-mcp junkdoge-joe/after-effects-mcp A stdio connector for the local ae-mcp After Effects panel; install the AE extension separately. | |
| ai.smithery/JunoJunHyun-festival-finder-mcp junojunhyun/festival-finder-mcp Discover festivals worldwide by location, date, and genre. Compare options with key details like d… | |
| Algeria Payments (Chargily Pay — EDAHABIA / CIB) junter1989k-ai/algeria-payments-mcp Algeria payments for AI agents — EDAHABIA / CIB via Chargily Pay. Never holds funds. | |
| Argentina Payments (Mercado Pago — Mercado Pago wallet / cuotas) junter1989k-ai/argentina-payments-mcp Argentina payments for AI agents — Mercado Pago wallet / cuotas via Mercado Pago. Never holds funds. | |
| Australia Logistics (buy Aramex + more labels + tracking via Shippo) junter1989k-ai/australia-logistics-mcp Australia shipping labels for AI agents: buy Aramex and more, track and refund via Shippo. | |
| Australia Payments (Stripe — cards / Apple Pay) junter1989k-ai/australia-payments-mcp Australia payments for AI agents — cards / Apple Pay via Stripe. Never holds funds. | |
| Austria Payments (Stripe — EPS) junter1989k-ai/austria-payments-mcp Austria payments for AI agents — EPS via Stripe. Never holds funds. | |
| Bahrain Payments (Tap Payments — Benefit) junter1989k-ai/bahrain-payments-mcp Bahrain payments for AI agents — Benefit via Tap Payments. Never holds funds. | |
| Bangladesh Payments (SSLCommerz — bKash / Nagad) junter1989k-ai/bangladesh-payments-mcp Bangladesh payments for AI agents — bKash / Nagad via SSLCommerz. Never holds funds. | |
| Belgium Invoices (Peppol BIS 3.0 via Storecove) junter1989k-ai/belgium-invoice-mcp Belgium Peppol BIS 3.0 e-invoices for AI agents: send, check recipient, get delivery proof. | |
| Belgium Payments (Mollie — Bancontact) junter1989k-ai/belgium-payments-mcp Belgium payments for AI agents — Bancontact via Mollie. Never holds funds. | |
| Brazil Invoices (NFS-e nota fiscal de serviço) junter1989k-ai/brazil-invoice-mcp Brazil NFS-e service invoices for AI agents via Focus NFe and NFe.io. Stateless, never stores data. | |
| Brazil Payments (Mercado Pago — Pix / cards / boleto) junter1989k-ai/brazil-payments-mcp Brazil payments for AI agents — Pix, cards, boleto via Mercado Pago. Never holds funds. | |
| Bulgaria Payments (Stripe — cards / Apple Pay) junter1989k-ai/bulgaria-payments-mcp Bulgaria payments for AI agents — cards / Apple Pay via Stripe. Never holds funds. | |
| Canada Payments (Stripe — cards / Apple Pay) junter1989k-ai/canada-payments-mcp Canada payments for AI agents — cards / Apple Pay via Stripe. Never holds funds. | |
| Chile Invoices (DTE boleta/factura electrónica via OpenFactura) junter1989k-ai/chile-invoice-mcp Chile DTE for AI agents - boleta/factura electronica via OpenFactura or LibreDTE. Stateless BYO. | |
| Chile Payments (Mercado Pago — Mercado Pago wallet) junter1989k-ai/chile-payments-mcp Chile payments for AI agents — Mercado Pago wallet via Mercado Pago. Never holds funds. | |
| Colombia Invoices (DIAN factura electronica via Matias API) junter1989k-ai/colombia-invoice-mcp Colombia DIAN factura electronica: AI agents issue and query e-invoices, stateless BYO. | |
| Colombia Payments (Mercado Pago — PSE / Nequi) junter1989k-ai/colombia-payments-mcp Colombia payments for AI agents — PSE / Nequi via Mercado Pago. Never holds funds. | |
| Costa Rica Invoices (Hacienda comprobante electronico v4.4) junter1989k-ai/costa-rica-invoice-mcp Costa Rica Hacienda v4.4: AI agents submit and query electronic invoices, stateless BYO. | |
| Costa Rica Payments (ONVO Pay — SINPE Movil) junter1989k-ai/costa-rica-payments-mcp Costa Rica payments for AI agents — SINPE Movil via ONVO Pay. Never holds funds. | |
| Croatia Payments (Stripe — cards / Apple Pay) junter1989k-ai/croatia-payments-mcp Croatia payments for AI agents — cards / Apple Pay via Stripe. Never holds funds. | |
| Cyprus Payments (Stripe — cards / Apple Pay) junter1989k-ai/cyprus-payments-mcp Cyprus payments for AI agents — cards / Apple Pay via Stripe. Never holds funds. | |
| Czechia Payments (Stripe — cards / Apple Pay) junter1989k-ai/czechia-payments-mcp Czechia payments for AI agents — cards / Apple Pay via Stripe. Never holds funds. | |
| Denmark Invoices (Peppol / NemHandel via Storecove) junter1989k-ai/denmark-invoice-mcp Denmark Peppol/NemHandel e-invoices for AI agents: send, check recipient, get delivery proof. | |
| Denmark Payments (Stripe — MobilePay) junter1989k-ai/denmark-payments-mcp Denmark payments for AI agents — MobilePay via Stripe. Never holds funds. | |
| Dominican Republic Invoices (DGII e-CF facturacion electronica) junter1989k-ai/dominican-republic-invoice-mcp Dominican Republic DGII e-CF: AI agents authenticate and submit electronic invoices, stateless BYO. | |
| Egypt Payments (Paymob — cards / mobile wallets) junter1989k-ai/egypt-payments-mcp Egypt payments for AI agents — cards / mobile wallets via Paymob. Never holds funds. |
10,001–10,050 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.