send_gmail
AI agents use send_gmail 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.
The send_gmail tool creates and sends new email messages, which modifies data (adds messages to recipient inboxes) but is reversible through deletion/recall mechanisms in Gmail. This qualifies as Write rather than Execute because it performs a specific, well-defined action (sending) rather than arbitrary code execution.
From the tool's definition Tool name 'send_gmail' combined with server description stating the server 'allows Claude to search, read, send, and manage emails using the Gmail API.' The tool is explicitly listed as a capability for sending emails.
Attacks that exploit this kind of access
send_gmail. 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: 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 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 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. 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 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 →