AI agents use compose_email to create or update resources in Mcp Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Gmail environment.
The tool name 'compose_email' strongly implies creating/drafting an email (a Write operation). The server description explicitly lists 'compose' as a capability. Since a separate 'send_email' tool exists, this likely creates a draft rather than sending, keeping it in Write rather than Execute. However, the empty description lowers confidence — if compose also sends, severity would be higher.
From the tool's definition Tool name 'compose_email' on a server described as enabling Gmail access to 'read, compose, and send emails'; sibling tool 'send_email' exists separately, suggesting compose may draft without sending.
Documented attack patterns abuse exactly the kind of access compose_email gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Gmail, and nothing reaches the server without passing your rules. This is the rule we recommend for compose_email:
{
"version": "1",
"default": "deny",
"tools": {
"compose_email": {
"limits": [
{
"counter": "compose_email_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}compose_email stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
compose_email. It is categorised as a Write tool in the Mcp Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for compose_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 Gmail. Nothing to install.
compose_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 compose_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 compose_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.
compose_email is provided by the Mcp Gmail MCP server (jeremyjordan/mcp-gmail). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Gmail, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Mcp Gmail tools catalogued and risk-classified — across an index of 43,000+ MCP servers.