AI agents use get_or_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.
This tool performs a read (get) or write (create) operation depending on whether the label exists. Since it may create a new label, the most severe applicable category is Write. Creating a label is a reversible operation (labels can be deleted), so it does not qualify as Destructive. Severity is medium because misuse could clutter or alter Gmail label organization, but the blast radius is limited.
From the tool's definition Gets an existing label by name or creates it if it doesn't exist
Attacks that exploit this kind of access
Gets an existing label by name or creates it if it doesn\. 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 get_or_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.
get_or_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 get_or_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 get_or_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.
get_or_create_label is provided by the Gmail MCP server (pouyanafisi/gmail-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 →