AI agents call gtm_accounts to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about GTM accounts associated with a Google account. While it performs no mutations or destructive actions, the medium severity reflects that account enumeration could enable follow-on attacks via sibling tools (gtm_containers, gtm_tags) that might modify analytics tracking or expose sensitive configuration.
From the tool's definition Tool name 'gtm_accounts' and description 'List all Google Tag Manager accounts' indicates a query/retrieval operation. The verb 'List' and phrase 'get account IDs needed by' confirm this is a discovery/lookup action with no side effects.
Attacks that exploit this kind of access
List all Google Tag Manager accounts accessible by the specified Google account. Use this first to get account IDs needed by gtm_containers and gtm_tags. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for gtm_accounts: 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 Access. Nothing to install.
gtm_accounts 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_accounts 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_accounts. 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_accounts is provided by the Access MCP server (scottpedia0/access). 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 →