AI agents use create_doc 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.
Creating a new Google Doc is a write operation that adds persistent data to the user's account. While not destructive (the document can be deleted separately) and not financial, it modifies the user's document store. The severity is medium because an agent could spam document creation or create documents with sensitive/misleading content, but the damage is reversible and localized to the user's own workspace.
From the tool's definition Tool description states 'Create a new Google Doc' — this is irreversible creation of a new document resource. The server description confirms 'write access to Google Docs.'
Attacks that exploit this kind of access
Create a new Google Doc with optional body text. Returns the doc ID and URL. 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 create_doc: 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.
create_doc 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 create_doc 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 create_doc. 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.
create_doc 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 →