Send a previously created Gmail draft.
AI agents use send_gmail_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.
This tool creates and sends email messages, which are persistent data modifications. While not destructive (emails can be recalled/deleted), and not financial, sending emails on behalf of a user represents a high-severity write operation because it can communicate misinformation, leak sensitive data, or perform social engineering attacks if misused by an AI agent.
From the tool's definition Tool description states 'Send a previously created Gmail draft.' Sending emails is a write operation that creates new messages and initiates external communication with email recipients.
Attacks that exploit this kind of access
Send a previously created Gmail draft. 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_gmail_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_gmail_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_gmail_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_gmail_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_gmail_draft is provided by the Gmail MCP Server MCP server (stevesimpson418/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 →