AI agents use mail__forward_message to create or update resources in Proton-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Proton-MCP environment.
Forwarding an email sends an existing message to a new recipient. This is a Write/send action that creates outbound communication. It could lead to data leakage if misused (e.g., forwarding sensitive emails to unintended parties), making severity high. It is not Destructive as the original message remains intact.
From the tool's definition Forward an email to another recipient
Documented attack patterns abuse exactly the kind of access mail__forward_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Proton-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for mail__forward_message:
{
"version": "1",
"default": "deny",
"tools": {
"mail__forward_message": {
"limits": [
{
"counter": "mail__forward_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mail__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 email to another recipient. It is categorised as a Write tool in the Proton-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Proton- MCP server in PolicyLayer and add a rule for mail__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 Proton-MCP. Nothing to install.
mail__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 mail__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 mail__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.
mail__forward_message is provided by the Proton- MCP server (jorgenclaw/proton-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Proton-MCP, 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.
36 Proton-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.