Performs variable operations: get, list, create, update, delete.
AI agents call gtm_variable to permanently remove resources in Google Tag Manager MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool supports multiple operations (get, list, create, update, delete), the presence of 'delete' capability makes it Destructive rather than Write. Deleting variables in GTM cannot be undone and affects tracking/measurement configuration. This is more severe than Write (reversible changes).
From the tool's definition Tool description states it performs 'delete' operations on variables, which are irreversible modifications to Google Tag Manager configuration.
Attacks that exploit this kind of access
Performs variable operations: get, list, create, update, delete. It is categorised as a Destructive tool in the Google Tag Manager MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Google Tag Manager MCP Server MCP server in PolicyLayer and add a rule for gtm_variable: 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 Google Tag Manager MCP Server. Nothing to install.
gtm_variable is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the gtm_variable 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_variable. 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_variable is provided by the Google Tag Manager MCP Server MCP server (metkamedia/gtm-mcp-server). 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 →