MCP Drupal
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DRUPAL_USER | Yes | Restricted Drupal username for the bot (e.g., mcp_bot) | |
| DRUPAL_BASE_URL | Yes | Base URL of the Drupal site, e.g., https://www.tudominio.es | |
| DRUPAL_PASSWORD | Yes | Password for the Drupal user |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_resource_typesA | Lista los tipos de recurso JSON:API disponibles en el sitio Drupal (content types, taxonomías, etc.) |
| list_nodesA | Lista nodos de un content type del sitio Drupal, con paginación y filtro opcional por título |
| get_nodeB | Obtiene un nodo concreto del sitio Drupal por su UUID |
| create_nodeA | Crea un nodo nuevo en el sitio Drupal. Requiere que el usuario mcp_agent tenga permiso de creación en ese content type |
| update_nodeA | Actualiza campos de un nodo existente en el sitio Drupal. Requiere permiso de edición en ese content type |
| list_sheet_rowsB | Lista las filas del Google Sheet de contenidos (columnas: keyword, titular, tipo, documento, slug, cliente) |
| get_article_content_from_docA | Descarga y extrae de un Google Doc el título, meta título, meta descripción, intro y body (HTML listo para Drupal, tablas convertidas a listas) |
| mark_sheet_row_doneA | Pinta de verde claro una fila del Sheet para marcarla como ya subida |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a clearly distinct resource and action: Drupal nodes, Drupal resource types, Google Sheet rows, and Google Doc extraction are all unambiguous. No two tools could reasonably be confused for the same operation.
All tool names follow a consistent snake_case verb-first pattern such as list_nodes, create_node, update_node, list_sheet_rows, and mark_sheet_row_done. The naming is predictable and easy to remember.
With 8 tools, the server is well scoped for its purpose: it covers Drupal node operations, content type discovery, and the Google Sheets/Docs content-import pipeline. Each tool earns its place.
The core ingestion workflow is well covered: read from Sheet and Doc, create/update Drupal nodes, list types, and mark rows done. The main gap is the lack of a delete_node operation, which would make full content lifecycle management more complete.