update-sandbox-message · Mcp Mailtrap MCP: Risk & Policy

WHAT IT DOES

What update-sandbox-message does on Mcp Mailtrap

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

WHY IT NEEDS A POLICY

Why update-sandbox-message needs a policy

This tool modifies the state of a message (read/unread status) reversibly without deleting or executing external operations. It qualifies as Write rather than Read because it changes data state. Severity is low because toggling read/unread status has minimal blast radius—it affects only message metadata visibility and does not impact core data integrity, financial systems, or destructive operations.

From the tool's definition Tool description states it 'Mark[s] a sandbox message as read or unread', which is a metadata update operation on an existing message.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update-sandbox-message Rate-limited

update-sandbox-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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update-sandbox-message": {
      "limits": [
        {
          "counter": "update-sandbox-message_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 Mcp Mailtrap, so you can run agents against it safely.

FAQ

Questions about update-sandbox-message

What does the update-sandbox-message tool do? +

Mark a sandbox message as read or unread. It is categorised as a Write tool in the Mcp Mailtrap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update-sandbox-message? +

Register the Mcp Mailtrap MCP server in PolicyLayer and add a rule for update-sandbox-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 Mcp Mailtrap. Nothing to install.

What risk level is update-sandbox-message? +

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

Can I rate-limit update-sandbox-message? +

Yes. Add a rate_limit block to the update-sandbox-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 update-sandbox-message completely? +

Set action: deny in the PolicyLayer policy for update-sandbox-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 update-sandbox-message? +

update-sandbox-message is provided by the Mcp Mailtrap MCP server (mcp-mailtrap). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.