AI agents use create_filter_from_template 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 an email filter is a write operation that modifies account settings reversibly. While filters affect email behavior (routing, labeling, deletion), the action itself can be undone by deleting the filter. The severity is high because a misconfigured filter applied by an agent could inadvertently hide, mislabel, or auto-delete important emails, causing significant disruption.
From the tool's definition Tool name includes 'create' and description states 'Creates a filter' — this modifies Gmail account configuration by adding a new filter rule.
Attacks that exploit this kind of access
Creates a filter using a pre-defined template for common scenarios. 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_filter_from_template: 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_filter_from_template 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_filter_from_template 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_filter_from_template. 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_filter_from_template 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 →