AI agents use create_draft_reply 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 (writes) draft email replies but does not send them, making it reversible—drafts can be edited or deleted before sending. It qualifies as Write rather than Execute because it generates content rather than executing arbitrary code. Severity is medium because misuse could involve impersonation or spam draft generation, but the impact is limited since drafts require human review/action to send.
From the tool's definition Tool name 'create_draft_reply' and server description stating 'create draft replies programmatically' indicates the tool creates new email drafts. The server description confirms this is a write operation that 'creates' email content.
Attacks that exploit this kind of access
create_draft_reply. 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 create_draft_reply: 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.
create_draft_reply 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 create_draft_reply 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 create_draft_reply. 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.
create_draft_reply is provided by the Mcp Gmail MCP server (martingaston/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 →