Send an email via Gmail
AI agents use gmail_send_email to create or update resources in Gmail & PostgreSQL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail & PostgreSQL MCP Server environment.
The tool creates new email messages and sends them, which modifies state in Gmail (adds sent emails, potentially affects recipients). This is a Write operation rather than Read (no data retrieval), Execute (not running arbitrary code), Destructive (emails can be deleted), or Financial (no money movement).
From the tool's definition Tool name is 'gmail_send_email' and description states 'Send an email via Gmail' — this creates and transmits new email messages, a reversible write operation.
Attacks that exploit this kind of access
Send an email via Gmail. It is categorised as a Write tool in the Gmail & PostgreSQL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail & PostgreSQL MCP Server MCP server in PolicyLayer and add a rule for gmail_send_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 & PostgreSQL MCP Server. Nothing to install.
gmail_send_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 gmail_send_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 gmail_send_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.
gmail_send_email is provided by the Gmail & PostgreSQL MCP Server MCP server (marouanemkm/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 →