AI agents call gmail_drafts_list 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 a list of draft messages from Gmail, optionally filtered by a query. It has no side effects—it does not create, modify, delete, or send messages. It is purely a data retrieval operation, fitting squarely into the Read category. Low severity because exposure would only allow an agent to view the user's draft messages, not take actions on them or access sent/received mail.
From the tool's definition Tool name 'gmail_drafts_list' and description 'List drafts' indicate a read operation that retrieves draft messages without modifying them. No deletion, creation, sending, or destructive capability is described.
Attacks that exploit this kind of access
List drafts (optionally filtered by a Gmail query). Returns. 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_drafts_list: 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_drafts_list 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_drafts_list 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_drafts_list. 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_drafts_list 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 →