Domain intelligence in one call — composes DNS (A/AAAA/MX/NS/TXT), WHOIS/RDAP (registrar, dates, status, nameservers, DNSSEC), and the live TLS certificate (issuer, validity, SANs, fingerprint) for a domain. Returns a summary (resolves, has MX, registrar, domain expiry, HTTPS valid, days to cert ...
AI agents call domain.intel to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs passive reconnaissance by querying publicly available DNS, WHOIS, and TLS certificate data. It has no side effects and does not alter any system state. The intended use cases (domain due diligence, security recon, expiry monitoring) are all read-only operations.
From the tool's definition Tool description states it 'composes DNS...WHOIS/RDAP...and the live TLS certificate' and returns 'a summary...per section'. All verbs describe retrieval and aggregation of public information: DNS queries, WHOIS lookups, TLS certificate inspection.
Attacks that exploit this kind of access
Domain intelligence in one call — composes DNS (A/AAAA/MX/NS/TXT), WHOIS/RDAP (registrar, dates, status, nameservers, DNSSEC), and the live TLS certificate (issuer, validity, SANs, fingerprint) for a domain. Returns a summary (resolves, has MX, registrar, domain expiry, HTTPS valid, days to cert expiry) plus a found/error block per section. For domain due diligence, security recon, and expiry monitoring. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for domain.intel: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
domain.intel is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the domain.intel rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for domain.intel. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
domain.intel is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →