Searches for invoice/bill emails with attachments
AI agents call search_invoices to retrieve information from Gmail AutoAuth MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only searches and queries existing data in Gmail without creating, modifying, deleting, or executing operations. The search operation has no side effects beyond data retrieval. Severity is low because search operations on email have minimal blast radius—the worst outcome is information disclosure of invoice emails the user has access to.
From the tool's definition Tool performs 'searches for invoice/bill emails' with no modification, deletion, or execution capabilities. It retrieves/queries data from Gmail using search functionality.
Attacks that exploit this kind of access
Searches for invoice/bill emails with attachments. It is categorised as a Read tool in the Gmail AutoAuth MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gmail AutoAuth MCP Server MCP server in PolicyLayer and add a rule for search_invoices: 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 AutoAuth MCP Server. Nothing to install.
search_invoices 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 search_invoices 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 search_invoices. 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.
search_invoices is provided by the Gmail AutoAuth MCP Server MCP server (rmcaccounting/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 →