Send an existing draft email
AI agents use send_draft to create or update resources in Gmail MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail MCP Server environment.
Sending email is a write operation that creates a persistent communication record and delivers messages to recipients. While not destructive (it can theoretically be recalled or the consequences are reversible to some extent), it modifies email system state irreversibly from the sender's perspective.
From the tool's definition The tool sends an existing draft email, which creates and transmits new email messages. This modifies the state of the email system by moving a draft to sent status and delivering the message to recipients.
Attacks that exploit this kind of access
Send an existing draft email. It is categorised as a Write tool in the Gmail MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail MCP Server MCP server in PolicyLayer and add a rule for send_draft: 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.
send_draft 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 send_draft 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 send_draft. 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.
send_draft is provided by the Gmail MCP Server MCP server (samarth2001/gmail-mcp). 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 →