AI agents use add_sheet to create or update resources in Gg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gg environment.
This tool creates a new sheet/tab in a spreadsheet, which is a reversible modification. It does not delete data (thus not Destructive), does not execute arbitrary code (thus not Execute), and does not involve financial transactions (thus not Financial). The severity is medium because misconfigured agent use could create unwanted sheets, but the action is easily reversible by deletion.
From the tool's definition Tool name 'add_sheet' and description 'Add a new sheet/tab to an existing spreadsheet' indicate creation of new data structure within a spreadsheet.
Attacks that exploit this kind of access
Add a new sheet/tab to an existing spreadsheet. It is categorised as a Write tool in the Gg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gg MCP server in PolicyLayer and add a rule for add_sheet: 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 Gg. Nothing to install.
add_sheet 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_sheet 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_sheet. 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_sheet is provided by the Gg MCP server (tannht/google-cloud-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 →