AI agents use update_section_style 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 structure and formatting in a reversible manner. While it changes document state, style updates can be undone/reverted (unlike destructive deletions). The blast radius is medium because malicious use could corrupt document layout or make content unreadable, but the changes are not permanent and can be corrected. This is clearly a Write operation rather than Execute or Destructive.
From the tool's definition The tool updates section-level style properties in a Google Doc including columns, margins, and headers/footers. The verb 'update' and the description of modifying document formatting properties indicate this is a reversible modification operation.
Attacks that exploit this kind of access
Update section-level style in a Google Doc (columns, margins, headers/footers). 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 update_section_style: 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.
update_section_style 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 update_section_style 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 update_section_style. 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.
update_section_style 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 →