Read a specific Gmail message by ID. Returns full message content.
AI agents call gmail_read 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 existing Gmail message content without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with minimal blast radius even if misused by an AI agent—at worst, it could expose message contents the agent shouldn't see, but causes no data loss or external effects.
From the tool's definition Tool name 'gmail_read' and description 'Read a specific Gmail message by ID. Returns full message content' indicate retrieval of email data with no modification or side effects.
Attacks that exploit this kind of access
Read a specific Gmail message by ID. Returns full message content. 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_read: 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_read 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_read 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_read. 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_read 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 →