Get attachment data from a Gmail message.
AI agents call get_gmail_attachment to retrieve information from Google Connections without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves attachment data from an existing Gmail message without creating, modifying, or deleting any data. It is a read-only operation with minimal blast radius—the worst case is exposure of data the user already has access to through Gmail. No financial, destructive, or side effects are involved.
From the tool's definition Tool name 'get_gmail_attachment' and description 'Get attachment data from a Gmail message' indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Get attachment data from a Gmail message. It is categorised as a Read tool in the Google Connections MCP Server, which means it retrieves data without modifying state.
Register the Google Connections MCP server in PolicyLayer and add a rule for get_gmail_attachment: 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 Connections. Nothing to install.
get_gmail_attachment 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 get_gmail_attachment 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 get_gmail_attachment. 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.
get_gmail_attachment is provided by the Google Connections MCP server (michaelzrork/google-connections-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 →