Skip to main content
Glama
oschwald

MaxMindDB MCP Server

by oschwald
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

Compare databases

compare_databases
Read-onlyIdempotent

Compare lookup answers in two loaded MaxMind databases within a CIDR to find added, removed, and changed IP ranges before and after an update.

Instructions

Compare lookup answers in two loaded databases within a CIDR, for example before and after an update. Returns paginated added, removed, and changed address ranges. Equal answers with different network boundaries are unchanged. Pages scan at most 10,000 segments and can contain no changes while has_more is true. Continue until has_more is false.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
networkYesCIDR to compare. Use an IPv4 prefix length of 8 or greater, or a native IPv6 prefix length of 32 or greater. Repeat on each page.
max_resultsNoMaximum changed address ranges to return on this page.
new_databaseYesComparison database's exact filename from list_databases. Supplies the after values. Both databases must be loaded.
old_databaseYesBaseline database's exact filename from list_databases. Supplies the before values.
resume_tokenNoToken from the previous page. Omit on the first request. Repeat both database names and network. If either loaded database changed, start a new comparison.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
changesYes
has_moreYes
resume_tokenYes
scanned_segmentsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.3.1
    • addedInput schema / properties / max_results / description
      Added value: +"Maximum changed address ranges to return on this page."
    • changedInput schema / properties / network / description
      Previous value: -"IPv4 /8 or smaller, or IPv6 /32 or smaller"New value: +"CIDR to compare. Use an IPv4 prefix length of 8 or greater, or a native IPv6 prefix length of 32 or greater. Repeat on each page."
    • addedInput schema / properties / new_database / description
      Added value: +"Comparison database's exact filename from list_databases. Supplies the after values. Both databases must be loaded."
    • addedInput schema / properties / old_database / description
      Added value: +"Baseline database's exact filename from list_databases. Supplies the before values."
    • addedInput schema / properties / resume_token / description
      Added value: +"Token from the previous page. Omit on the first request. Repeat both database names and network. If either loaded database changed, start a new comparison."
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, yet the description still adds non-obvious context: pages scan at most 10,000 segments, may legitimately return no changes while has_more is true, and equal answers with differing network boundaries count as unchanged. These are exactly the pitfalls an agent would otherwise misread as failure.

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-loads the purpose and then layers result and pagination semantics efficiently. The closing 'Continue until has_more is false' slightly overlaps the preceding sentence about has_more being true, a small redundancy in an otherwise tight definition.

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

Completeness5/5

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

An output schema exists, so return values need no enumeration, yet the description still characterizes the result (added, removed, changed ranges, unchanged on boundary differences) and the pagination contract. Nothing needed to invoke it correctly is missing.

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%, so every parameter (network, max_results, both database names, resume_token) is already fully documented with constraints and restart rules. The description's 'before and after' framing restates the old/new semantics rather than extending them, so the baseline 3 applies.

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 ('compare'), a precise resource ('lookup answers in two loaded databases within a CIDR'), and the motivating scenario ('before and after an update'). This is unmistakably distinct from the lookup_*, inspect_database, and verify_database siblings.

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

Usage Guidelines4/5

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

Gives a clear motivating context ('for example before and after an update') and operational guidance for iterating pages. It stops short of naming when to pick verify_database or inspect_database instead, so the when-not side is left implicit.

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

Deploy Server

Other Tools