AI agents call mail__get_unread to retrieve information from Proton-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves email data without side effects. It is a read-only query of the user's inbox. Severity is medium rather than low because email contents may contain sensitive personal or financial information that, if accessed by a compromised agent, could lead to privacy violations or information disclosure, even though the tool itself performs no destructive action.
From the tool's definition Tool name 'mail__get_unread' and description 'Get unread emails from Proton Mail inbox' indicate a retrieval operation with no modification or deletion of data.
Documented attack patterns abuse exactly the kind of access mail__get_unread 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__get_unread:
{
"version": "1",
"default": "deny",
"tools": {
"mail__get_unread": {}
}
}mail__get_unread is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get unread emails from Proton Mail inbox. It is categorised as a Read tool in the Proton-MCP MCP Server, which means it retrieves data without modifying state.
Register the Proton- MCP server in PolicyLayer and add a rule for mail__get_unread: 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__get_unread is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mail__get_unread 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__get_unread. 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__get_unread 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.