Performs all client operations: create, get, list, update, remove, revert. The
AI agents call gtm_client to permanently remove resources in Unboundai Gtm — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool includes 'remove' which is a destructive/irreversible deletion operation on GTM clients. Since the tool spans multiple categories and 'remove' (Destructive) is the most severe applicable category, it takes precedence over Write, Read, and Execute. Misuse could delete GTM client configurations, disrupting tag management and data collection pipelines.
From the tool's definition Performs all client operations: create, get, list, update, remove, revert
Attacks that exploit this kind of access
Performs all client operations: create, get, list, update, remove, revert. The. It is categorised as a Destructive tool in the Unboundai Gtm MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Unboundai Gtm MCP server in PolicyLayer and add a rule for gtm_client: 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 Unboundai Gtm. Nothing to install.
gtm_client 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_client 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_client. 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_client is provided by the Unboundai Gtm MCP server (tijevlam/unboundai-google-tag-manager-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 →