Send a new email or save as draft
AI agents use send-email 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 new email messages and transmits them through the Gmail service, which is a reversible write operation (emails can be recalled, deleted, or marked as spam). However, it does not delete data irreversibly, move money, or execute arbitrary code—it is constrained to email composition and transmission.
From the tool's definition Tool description states 'Send a new email or save as draft', indicating it creates and transmits new email messages. The server description confirms 'send emails' capability through Gmail API.
Attacks that exploit this kind of access
Send a new email or save as 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-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 MCP Server. Nothing to install.
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 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 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.
send-email is provided by the Gmail MCP Server MCP server (solonabot/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 →