AI agents use gmail_draft_create to create or update resources in Mcp Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Gmail environment.
This tool creates new data (draft emails) reversibly; the user can delete or modify drafts. It does not send messages, delete data irreversibly, execute code, or handle finances. While it modifies the user's mailbox state, drafts are not published and can be undone, placing it firmly in Write rather than Execute or Destructive.
From the tool's definition Tool description states 'Create a draft email in the user' — a create operation that modifies the user's Gmail account by adding a new draft message.
Attacks that exploit this kind of access
Create a draft email in the user\. It is categorised as a Write tool in the Mcp Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for gmail_draft_create: 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_draft_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gmail_draft_create 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_draft_create. 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_draft_create 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 →