AI agents use update_list 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 creates or modifies document content (list formatting) reversibly. It does not execute code, delete data, or trigger financial transactions. The severity is medium because misuse could alter document structure or formatting in ways requiring cleanup, but the changes are easily undone via undo functionality or reformatting.
From the tool's definition Tool description states 'Apply or remove bulleted/numbered list formatting on a range of paragraphs in a Google Doc' — this modifies document structure and formatting, which is reversible and non-destructive.
Attacks that exploit this kind of access
Apply or remove bulleted/numbered list formatting on a range of paragraphs in 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 update_list: 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_list 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_list 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_list. 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_list 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 →