Searches for emails using Gmail search syntax
AI agents call search_emails 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.
The search_emails tool performs read-only retrieval of email data based on search criteria. While it does not modify or delete data, the medium severity reflects the sensitivity of email content (potentially containing PII, credentials, or confidential information) and the risk that an AI agent could over-search or leak results. However, it is fundamentally a Read operation with no side effects.
From the tool's definition Tool description states 'Searches for emails using Gmail search syntax' — a query operation that retrieves data without modifying it.
Attacks that exploit this kind of access
Searches for emails using Gmail search syntax. 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_emails: 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_emails 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_emails 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_emails. 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_emails is provided by the Gmail AutoAuth MCP Server MCP server (stephenlreed/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 →