AI agents use add_doc_tab to create or update resources in Google — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google environment.
Adding a tab modifies document structure but does not delete or irreversibly destroy data, nor does it execute arbitrary code or move money. It is a creation/modification action (Write category). Severity is medium because an agent could spam tabs or clutter a document, but the change is easily undone and does not affect data integrity or permanence.
From the tool's definition "Add a new tab to a Google Doc" — the tool creates a new tab, which is a structural modification to the document that is reversible (the tab can be deleted).
Attacks that exploit this kind of access
Add a new tab to a Google Doc. It is categorised as a Write tool in the Google MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google MCP server in PolicyLayer and add a rule for add_doc_tab: 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. Nothing to install.
add_doc_tab is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_doc_tab 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 add_doc_tab. 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.
add_doc_tab is provided by the Google MCP server (ztgluis/google-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 →