read_gmail_attachment
AI agents call read_gmail_attachment to retrieve information from Gmail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context indicate this retrieves/accesses email attachment content without modifying or deleting data. Despite the empty description, the naming pattern and sibling tools strongly suggest a Read operation. Severity is low because reading attachments has minimal blast radius—no side effects, data destruction, or financial impact.
From the tool's definition Tool name 'read_gmail_attachment' indicates retrieval of attachment data; server description states 'read' emails; sibling tool 'list_gmail_attachments' is clearly a Read operation, suggesting this tool performs similar non-destructive data access.
Attacks that exploit this kind of access
read_gmail_attachment. It is categorised as a Read tool in the Gmail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gmail MCP Server MCP server in PolicyLayer and add a rule for read_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 Gmail MCP Server. Nothing to install.
read_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 read_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 read_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.
read_gmail_attachment is provided by the Gmail MCP Server MCP server (stevesimpson418/gmail-mcp-server). 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 →