mail_mark_email_read · Pyfastmail MCP: Risk & Policy

WHAT IT DOES

What mail_mark_email_read does on Pyfastmail

AI agents use mail_mark_email_read to create or update resources in Pyfastmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pyfastmail environment.

WHY IT NEEDS A POLICY

Why mail_mark_email_read needs a policy

This tool modifies email state (the $seen flag) but does not create, delete, or permanently alter email content. The change is reversible—emails can be marked unread and read again. While not destructive, it is a Write operation that changes data properties. Given the server's full account access and that bulk operations could affect many emails, the severity is medium rather than low.

From the tool's definition Tool name 'mail_mark_email_read' and description 'Set or unset the $seen flag on one or more emails' indicates modification of email metadata state. The $seen flag is a reversible property that can be toggled on or off.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mail_mark_email_read Rate-limited

mail_mark_email_read 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mail_mark_email_read": {
      "limits": [
        {
          "counter": "mail_mark_email_read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Pyfastmail, so you can run agents against it safely.

FAQ

Questions about mail_mark_email_read

What does the mail_mark_email_read tool do? +

Set or unset the $seen flag on one or more emails. It is categorised as a Write tool in the Pyfastmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mail_mark_email_read? +

Register the Pyfastmail MCP server in PolicyLayer and add a rule for mail_mark_email_read: 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 Pyfastmail. Nothing to install.

What risk level is mail_mark_email_read? +

mail_mark_email_read is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mail_mark_email_read? +

Yes. Add a rate_limit block to the mail_mark_email_read 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_mark_email_read completely? +

Set action: deny in the PolicyLayer policy for mail_mark_email_read. 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_mark_email_read? +

mail_mark_email_read is provided by the Pyfastmail MCP server (pjosols/pyfastmail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.