Draft a new email
AI agents use draft_email to create or update resources in Gmail AutoAuth MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail AutoAuth MCP Server environment.
Drafting an email creates new data (the draft message) without immediately sending or permanently modifying existing data. This is a Write operation. Severity is medium because while drafts are reversible, an AI agent could create numerous unwanted drafts or draft emails with sensitive/inappropriate content that a user must manually clean up.
From the tool's definition Tool name 'draft_email' and description 'Draft a new email' indicate creation of email content. This is a reversible write operation—drafts can be deleted or modified before sending.
Attacks that exploit this kind of access
Draft a new email. It is categorised as a Write tool in the Gmail AutoAuth MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail AutoAuth MCP Server MCP server in PolicyLayer and add a rule for draft_email: 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 AutoAuth MCP Server. Nothing to install.
draft_email 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 draft_email 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 draft_email. 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.
draft_email is provided by the Gmail AutoAuth MCP Server MCP server (stephenlreed/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 →