Forward an existing email message to a new recipient
AI agents use gmail_forward_message to create or update resources in Sage MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sage MCP environment.
Forwarding an email creates a new outbound email to a third party, which is a write/send operation. While reversible in principle (the email can't be 'unsent'), the act of forwarding potentially sensitive email content to unintended recipients poses a high blast radius risk if misused by an AI agent — e.g., leaking confidential information.
From the tool's definition Forward an existing email message to a new recipient
Documented attack patterns abuse exactly the kind of access gmail_forward_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for gmail_forward_message:
{
"version": "1",
"default": "deny",
"tools": {
"gmail_forward_message": {
"limits": [
{
"counter": "gmail_forward_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}gmail_forward_message 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.
Forward an existing email message to a new recipient. It is categorised as a Write tool in the Sage MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sage MCP server in PolicyLayer and add a rule for gmail_forward_message: 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 Sage MCP. Nothing to install.
gmail_forward_message 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_forward_message 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_forward_message. 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_forward_message is provided by the Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.