AI agents use format_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.
This tool modifies document formatting and styling, which is a Write operation—it changes document state reversibly without executing code, deleting data, or moving money. The severity is medium because misuse could corrupt document formatting at scale across multiple docs, but changes are undoable via Google Docs' revision history. Confidence is high based on clear description of formatting-only scope.
From the tool's definition Tool description states it 'Format text or paragraphs in a Google Doc' with support for styling operations (bold, italic, underline, strikethrough, font size/family, colors, heading styles, alignment, spacing).
Attacks that exploit this kind of access
Format text or paragraphs in a Google Doc. Supports bold, italic, underline, strikethrough, font size/family, colors, heading styles, alignment, and spacing. 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 format_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.
format_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 format_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 format_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.
format_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 →