Search Gmail messages. Uses Gmail search syntax (e.g.
AI agents call gmail_search to retrieve information from Mariana Google MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries email data with no side effects. It matches the Read category definition: retrieves data via search with no ability to modify, delete, or execute actions. The server's safety-first design and mention of draft-only and soft-delete protections for other tools further confirms this is read-only.
From the tool's definition Tool name is 'gmail_search' and description states 'Search Gmail messages'. No mutation, deletion, or external action is described. Uses Gmail search syntax for querying only.
Attacks that exploit this kind of access
Search Gmail messages. Uses Gmail search syntax (e.g. It is categorised as a Read tool in the Mariana Google MCP MCP Server, which means it retrieves data without modifying state.
Register the Mariana Google 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 Mariana Google MCP. 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 Mariana Google MCP server (marianasmall/mariana-google-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 →