AI agents call gtm_get_tag to retrieve information from Gtm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves tag configuration data without creating, modifying, deleting, or executing any operations. It is a simple data retrieval function with no side effects. The read of sensitive GTM configuration is low severity since it only exposes existing settings without enabling unauthorized changes or actions.
From the tool's definition The tool name is 'gtm_get_tag' and the description states it will 'Get detailed configuration of a specific tag'. The verb 'Get' and the absence of any modification language clearly indicate a read-only operation.
Attacks that exploit this kind of access
Get detailed configuration of a specific tag. It is categorised as a Read tool in the Gtm MCP Server, which means it retrieves data without modifying state.
Register the Gtm MCP server in PolicyLayer and add a rule for gtm_get_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_get_tag is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gtm_get_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_get_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_get_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 →