AI agents use create_label to create or update resources in Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail environment.
Creating a label is a write operation that modifies Gmail's organizational structure by adding new metadata/categorization. It is reversible (labels can be deleted) and has minimal blast radius even if invoked incorrectly by an AI agent. The tool does not execute code, delete data, or move money, so Write is the appropriate category with low severity.
From the tool's definition Tool creates a new Gmail label, as stated in description: 'Create a new Gmail label with optional visibility settings.' This is a reversible creation operation with no destructive effects.
Attacks that exploit this kind of access
Create a new Gmail label with optional visibility settings. It is categorised as a Write tool in the Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail MCP server in PolicyLayer and add a rule for create_label: 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 Gmail. Nothing to install.
create_label 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_label 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_label. 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_label is provided by the Gmail MCP server (ndungukamami-sketch/gmail-mcp-server). 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 →