AI agents call gmail_attachment_get to retrieve information from Mcp Gmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/fetches an email attachment by its ID. Downloading existing data is a read operation with no side effects—the attachment is not modified, deleted, or used to trigger external operations. The blast radius of misuse is limited to unauthorized access to existing attachments, which is a confidentiality concern but not destructive or executable in nature.
From the tool's definition Tool name is 'gmail_attachment_get' with description 'Download an attachment by id.' The verb 'download' and 'get' indicate retrieval of data with no modifications.
Attacks that exploit this kind of access
Download an attachment by id. With. It is categorised as a Read tool in the Mcp Gmail MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for gmail_attachment_get: 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 Mcp Gmail. Nothing to install.
gmail_attachment_get 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_attachment_get 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_attachment_get. 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_attachment_get is provided by the Mcp Gmail MCP server (knowledgeislands/mcp-gmail). 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 →