AI agents use gtm_update_version 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 modifies existing data in Google Tag Manager by updating container version metadata. The changes are reversible—metadata like names, descriptions, and notes can be edited back to previous states. This makes it a Write operation rather than Destructive.
From the tool's definition Tool description states 'Update metadata of a container version (name, description, notes)'. The verb 'Update' and the reversible nature of metadata changes (name, description, notes can be changed back) classify this as a Write operation.
Attacks that exploit this kind of access
Update metadata of a container version (name, description, notes). 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_update_version: 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_update_version 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_update_version 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_update_version. 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_update_version 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 →