Send an email from Gmail account
AI agents use send_gmail_email to create or update resources in MCP Email Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Email Server environment.
This tool creates new email messages and delivers them to recipients, making it a Write action (creates/modifies data reversibly). Severity is high because misuse could enable spam, phishing, impersonation, or social engineering attacks at scale if an AI agent is compromised or misdirected. However, it does not move money (not Financial), delete data (not Destructive), or execute arbitrary code (not Execute).
From the tool's definition Tool name 'send_gmail_email' and description 'Send an email from Gmail account' indicate the tool creates and sends emails, which are new messages that persist in recipient inboxes.
Attacks that exploit this kind of access
Send an email from Gmail account. It is categorised as a Write tool in the MCP Email Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Email Server MCP server in PolicyLayer and add a rule for send_gmail_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 MCP Email Server. Nothing to install.
send_gmail_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 send_gmail_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 send_gmail_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.
send_gmail_email is provided by the MCP Email Server MCP server (kentaroh7777/mcp-email-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 →