Drupal MCP Server

Export Taxonomy

export_taxonomy

Export Drupal taxonomy terms to CSV or Excel with usage counts, referencing fields, and safe-to-delete status; limit by vocabulary or export all terms.

Instructions

Export taxonomy terms to a CSV or Excel file on disk.

One row per term: id, vocabulary, name, description, weight, status, and - with include_usage (the default) - how many entities reference the term, through which fields, and a safe_to_delete verdict ("yes" only when nothing references it, and withheld entirely whenever some field could not be counted). Usage comes from one COUNT query per field storage targeting taxonomy terms, so a 5,000-term vocabulary costs a handful of queries, not 5,000.

vocabulary limits the export to one vocabulary machine name (for example "tags"). When Drush is unavailable the export still succeeds and says the usage columns are empty.

Input Schema

TableJSON Schema

Name	Required	Default
`limit`	No
`format`	No	csv
`vocabulary`	No
`output_path`	No
`include_usage`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.3.1Oct 17, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so richly: exact column set per row, the safe_to_delete verdict semantics ('yes' only when nothing references the term, withheld when any field could not be counted), the cost profile (one COUNT query per field storage rather than per term), and graceful degradation when Drush is unavailable. This is well beyond anything the schema or annotations state.

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

Conciseness5/5

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

Front-loaded with purpose and row shape, then the usage-column semantics, then the cost/scoping caveats. Every sentence earns its place — even the performance note and the Drush fallback note are actionable for an agent.

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 not be re-explained; the description still supplies the non-obvious verdict semantics that a schema cannot convey. Degradation behavior, cost, and scoping are all covered, leaving nothing an agent needs to call this correctly.

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 0%, so the description must compensate for five undocumented parameters. It explains vocabulary ('limits the export to one vocabulary machine name, e.g. "tags"'), include_usage, and the CSV/Excel format and on-disk destination, but says nothing about limit or output_path semantics, leaving two of five parameters opaque.

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 (export), resource (taxonomy terms), and artifact (CSV or Excel file on disk), plus the exact row shape. An agent can distinguish this from list_terms (returns terms, no file), migrate_taxonomy (migration), and export_nodes/users/media (different resources) without opening a schema.

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 artifact ('export ... to a file on disk') and by the include_usage default, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. list_terms for in-memory reads, migrate_taxonomy for migrations). The agent must infer the selection context.

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

Deploy Server