AI agents use gtm_create_tag to create or update resources in Gtm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gtm environment.
This tool creates new tags in GTM containers, which modifies the tracking and analytics configuration of web properties. While reversible (tags can be deleted or unpublished), the creation of tags can significantly impact data collection, user tracking, and potentially affect website behavior depending on tag configuration.
From the tool's definition Tool name is 'gtm_create_tag' and description states 'Create a new tag in a GTM container'. The server description indicates this enables 'creation, update, and publishing' of tags within Google Tag Manager.
Attacks that exploit this kind of access
Create a new tag in a GTM container. It is categorised as a Write tool in the Gtm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gtm MCP server in PolicyLayer and add a rule for gtm_create_tag: 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 Gtm. Nothing to install.
gtm_create_tag 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 gtm_create_tag 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 gtm_create_tag. 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.
gtm_create_tag is provided by the Gtm MCP server (tijevlam/gtm-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 →