gtm_destination · Unboundai Gtm MCP: Risk & Policy

WHAT IT DOES

What gtm_destination does on Unboundai Gtm

AI agents use gtm_destination to create or update resources in Unboundai Gtm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unboundai Gtm environment.

WHY IT NEEDS A POLICY

Why gtm_destination needs a policy

The tool supports both read operations (get, list) and write/destructive operations (link, unlink). Linking and unlinking destinations in Google Tag Manager can affect tracking configurations across web properties. The most severe applicable category is Write (link/unlink are reversible modifications), though unlinking could have significant operational impact.

From the tool's definition Performs all destination operations: get, list, link, unlink

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gtm_destination Rate-limited

gtm_destination stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "gtm_destination": {
      "limits": [
        {
          "counter": "gtm_destination_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Unboundai Gtm, so you can run agents against it safely.

FAQ

Questions about gtm_destination

What does the gtm_destination tool do? +

Performs all destination operations: get, list, link, unlink. The. It is categorised as a Write tool in the Unboundai Gtm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on gtm_destination? +

Register the Unboundai Gtm MCP server in PolicyLayer and add a rule for gtm_destination: 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.

What risk level is gtm_destination? +

gtm_destination is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit gtm_destination? +

Yes. Add a rate_limit block to the gtm_destination 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.

How do I block gtm_destination completely? +

Set action: deny in the PolicyLayer policy for gtm_destination. 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.

What MCP server provides gtm_destination? +

gtm_destination 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.