Ask your AI about an IP
HoneyLabs runs a Model Context Protocol server. Add it to Claude, Cursor or another MCP client, and the assistant looks up addresses, CVEs and fingerprints in the sensors' records when you ask.
Add it to your AI tool
Pick your client. Cursor and VS Code install from a button, and the others take a command, an address or a settings block.
Run this in a terminal, with an API key from your dashboard.
claude mcp add honeylabs \
--transport http \
https://mcp.honeylabs.net/mcp \
--header "Authorization: Bearer <hlk_...>"To sign in with OAuth on first use, leave out the --header line.
The button opens Cursor with the server filled in. You sign in with OAuth on first use, so there is no key to paste.
Add to CursorThe button opens VS Code with the server filled in. You sign in with OAuth on first use, so there is no key to paste.
Install in VS CodeIn Claude Desktop or on claude.ai, open Customize, then Connectors, then Add connector. Paste this address and sign in.
https://mcp.honeylabs.net/mcpThe server speaks streamable HTTP at https://mcp.honeylabs.net/mcp. Most clients take this block in their MCP settings file.
{
"mcpServers": {
"honeylabs": {
"type": "http",
"url": "https://mcp.honeylabs.net/mcp",
"headers": {
"Authorization": "Bearer <hlk_...>"
}
}
}
}Replace <hlk_...> with a key from your dashboard. Without the Authorization header the client connects and lists the tools, and the first query fails. A client that supports OAuth 2.1 with PKCE can leave out the headers block and sign in on first use.
Example prompts
Questions the server can answer. Click one to copy it.
Tools the server exposes
The assistant picks the tool from your question. The list shows what it can look up.
| Tool | What it does |
|---|---|
| ioc_lookup | Start here. An IP or domain with our verdict, whether it is a recognised benign scanner, and the CVEs it probed. |
| cve_lookup | Who is probing a named CVE: severity, KEV status, top actors, fingerprints, daily timeline. |
| top_attackers | Leaderboard of source IPs, ASNs, countries, ports, user-agents, or CVEs (by='cve'). |
| search_events | Raw events with every field. Use when you want fingerprints in the response. |
| payload_search | Substring search across request paths, bodies and headers. Never a CVE id. |
| attack_timeline | Hourly or daily attack volume over a window. |
| asn_enrich | Full profile for an ASN: top sources, ports, paths, fingerprints. |
| fingerprint_search | Find activity by TLS, HTTP, or SSH fingerprint. |
| fingerprint_population | The population behind one fingerprint: how many IPs carry it and where they sit. |
| fingerprint_similar | Akin request shapes within a few headers of one fingerprint, and the family it belongs to. |
| udp_activity | UDP datagrams: DNS questions, QUIC client fingerprints and other probes. Source addresses unverified. |
| interactive_credentials | Logins tried against the interactive sensors: the pairs tried most per service, and whether the password was ever sent. |
| interactive_files | Files clients handed to the interactive sensors, by SHA-256, with the VirusTotal verdict when there is one. |
| interactive_sessions | Sessions one address or range held with the interactive sensors: verdicts, services posed as, ports and what the client did. |