Skip to main content
Glama

DNS Record Lookup

dns
Read-onlyIdempotent

Resolve a DNS name's records: A, AAAA, MX, NS, TXT, CNAME and SOA. Underscore-prefixed names work too, such as _dmarc. or ._domainkey..

A domain offered for sale may publish an RFC 10023 record at _for-sale.: read only the TXT strings starting with v=FORSALE1;, and treat what they say as the holder's own unverified claim.

Related: whois, ns_reverse.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "domain": "<domain>"
    },
    "name": "dns"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainYesThe DNS name to resolve, as a bare hostname: a registrable domain such as example.com, or a fuller name such as _dmarc.example.com or mail.example.com. No protocol (https://), path, or port; internationalized names in punycode (xn--...).

Output Schema

NameRequiredDescriptionDefault
errorNo
domainNo
messageNoSet when the name has no DNS records; records is then empty
recordsNoDNS records grouped by type
successNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedOutput schema / required
      Removed value: -[
      -  "success"
      -]
  2. Changed1 schema field changed
    • changedOutput schema / properties / records / properties / CAA / description
      Previous value: -"Certification Authority Authorization records. If this field is omitted, the upstream DNS service did not provide CAA data; omission is not proof that no CAA record exists."New value: +"Certification Authority Authorization records. If this field is omitted, no CAA data was returned; omission is not proof that no CAA record exists."
  3. Changed2 schema fields changed
    • changedInput schema / properties / domain / description
      Previous value: -"The DNS name to resolve. A registrable domain such as example.com, or a fuller name such as _dmarc.example.com or mail.example.com."New value: +"The DNS name to resolve, as a bare hostname: a registrable domain such as example.com, or a fuller name such as _dmarc.example.com or mail.example.com. No protocol (https://), path, or port; internationalized names in punycode (xn--...)."
    • addedOutput schema / properties / message
      Added value: +{
      +  "description": "Set when the name has no DNS records; records is then empty",
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • changedInput schema / properties / domain / description
      Previous value: -"Domain name"New value: +"The DNS name to resolve. A registrable domain such as example.com, or a fuller name such as _dmarc.example.com or mail.example.com."
  5. Added

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so safety is covered; the description goes further by disclosing that underscore-prefixed names are supported and that _for-sale TXT strings are an unverified holder claim that must be filtered by the 'v=FORSALE1;' prefix. That epistemic caveat is genuine context an agent could not get from structured fields. It stops short of covering NXDOMAIN/empty-answer behavior or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core capability, then two compact follow-on paragraphs for edge cases. Every sentence carries information, though the dedicated for-sale paragraph is narrow enough that it slightly outweighs the general guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With rich annotations, a fully described single parameter, and an output schema, the description need not explain return values and correctly doesn't. It covers the notable input edge cases (underscore prefixes, for-sale records), leaving only error/empty-result handling unaddressed, which is minor for a read-only lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'domain' parameter is already documented in detail (bare hostname, no protocol/path/port, punycode for IDNs). The description's only added parameter meaning is confirming underscore-prefixed names like _dmarc.<domain> or <selector>._domainkey.<domain> are valid input, which the schema partly covers. Baseline 3 applies since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Resolve a DNS name's records') and enumerates exactly which record types are returned (A, AAAA, MX, NS, TXT, CNAME, SOA). An agent immediately knows this is a live DNS resolution tool, not a WHOIS or availability check.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the record-type list and the trailing 'Related: whois, ns_reverse' line, and the description carves out one concrete scenario (checking _for-sale.<domain> for RFC 10023 claims). However, it never states when to prefer whois, ns_reverse, or ip_lookup over this tool, so the sibling routing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.