AI agents call mail__search_messages 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 performs email search/retrieval functionality with no side effects. It queries existing email data based on keywords but does not create, modify, delete, or execute any operations. The blast radius of misuse is limited to potential information disclosure of email contents that the authenticated user already has access to read.
From the tool's definition Tool name 'mail__search_messages' and description 'Search emails by keyword in subject and body' indicate a query operation that retrieves data without modification.
Documented attack patterns abuse exactly the kind of access mail__search_messages 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__search_messages:
{
"version": "1",
"default": "deny",
"tools": {
"mail__search_messages": {}
}
}mail__search_messages 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.
Search emails by keyword in subject and body. 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__search_messages: 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__search_messages 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__search_messages 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__search_messages. 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__search_messages 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.