Search messages with Gmail's query syntax (e.g. 'from:foo subject:bar').
AI agents call gmail_search to retrieve information from Google Workspace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries email messages based on search criteria. It has no side effects—it does not create, modify, delete, or execute any external operations. The query syntax is explicitly for searching, which is a read-only operation.
From the tool's definition Tool name 'gmail_search' and description 'Search messages with Gmail's query syntax' indicate a retrieval operation that queries email data without modifying or deleting it.
Attacks that exploit this kind of access
Search messages with Gmail's query syntax (e.g. 'from:foo subject:bar'). It is categorised as a Read tool in the Google Workspace MCP Server, which means it retrieves data without modifying state.
Register the Google Workspace MCP server in PolicyLayer and add a rule for gmail_search: 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 Google Workspace. Nothing to install.
gmail_search 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 gmail_search 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 gmail_search. 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.
gmail_search is provided by the Google Workspace MCP server (rajool/google-workspace-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 →