AI agents use drupal_update_node to create or update resources in Drupal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Drupal environment.
This tool modifies existing content reversibly (updates/patches rather than deletes). It does not execute arbitrary code, delete data irreversibly, or move money. However, the severity is elevated to 'high' because unauthorized modification of Drupal nodes could impact published content, user data, or site functionality, and an AI agent with this capability could make unintended changes at scale across a production…
From the tool's definition Tool description states 'Patch an existing node' and 'Pass only the attributes / relationships you want to change', indicating reversible modification of data. The server enables 'CRUD operations on nodes' including updates.
Attacks that exploit this kind of access
Patch an existing node by UUID. Pass only the attributes / relationships you want to change. It is categorised as a Write tool in the Drupal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Drupal MCP server in PolicyLayer and add a rule for drupal_update_node: 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 Drupal. Nothing to install.
drupal_update_node is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the drupal_update_node 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 drupal_update_node. 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.
drupal_update_node is provided by the Drupal MCP server (lucaspretti/drupal-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 →