mail__get_message

THE RISK

Low Risk

Why mail__get_message needs a policy

This tool retrieves a single email message by its ID, which is a query operation with no side effects. It does not create, modify, delete, or execute any actions—it only reads and returns existing data. The inclusion of 'threading headers' further confirms it is informational retrieval.

From the tool's definition Tool name 'mail__get_message' and description 'Get a single email by message ID' indicates retrieval without modification. The verb 'Get' and context of fetching by identifier are characteristic of read-only operations.

Documented attack patterns abuse exactly the kind of access mail__get_message gives an agent:

POLICY

How to control mail__get_message

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_message:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mail__get_message": {}
  }
}

mail__get_message is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Proton-MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Proton-MCP tools

Destructive calendar__delete_event Delete a calendar event Destructive drive__delete Delete a file or folder from Proton Drive Destructive mail__delete_message Permanently delete an email from inbox Destructive pass__trash_item Move a credential to the trash in Proton Pass Write mail__forward_message Forward an email to another recipient Write mail__star_message Star or unstar an email Write calendar__create_event Create a calendar event. Use for reminders, follow-ups, and deadlines. Write calendar__update_event Update an existing calendar event

All 36 Proton-MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about mail__get_message

What does the mail__get_message tool do? +

Get a single email by message ID (sequence number). Includes threading headers. It is categorised as a Read tool in the Proton-MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on mail__get_message? +

Register the Proton- MCP server in PolicyLayer and add a rule for mail__get_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.

What risk level is mail__get_message? +

mail__get_message is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit mail__get_message? +

Yes. Add a rate_limit block to the mail__get_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.

How do I block mail__get_message completely? +

Set action: deny in the PolicyLayer policy for mail__get_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.

What MCP server provides mail__get_message? +

mail__get_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.

Enforce policy on every Proton-MCP tool call.

Start from Proton-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →