AI agents call list_filters to retrieve information from Gmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns existing filter metadata without any side effects. It does not create, modify, delete, or execute filters. The verb 'retrieves' confirms read-only semantics. Despite the broader Gmail integration supporting destructive operations (delete_filter, delete_email, batch_delete_emails), this specific tool is restricted to retrieval.
From the tool's definition Tool name is 'list_filters' and description states it 'Retrieves all Gmail filters' — a pure read operation with no modification, deletion, or execution of filters.
Attacks that exploit this kind of access
Retrieves all Gmail filters. It is categorised as a Read tool in the Gmail MCP Server, which means it retrieves data without modifying state.
Register the Gmail MCP server in PolicyLayer and add a rule for list_filters: 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.
list_filters is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_filters 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 list_filters. 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.
list_filters 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 →