upload_sieve_script · TrekMail MCP Server MCP: Risk & Policy

WHAT IT DOES

What upload_sieve_script does on TrekMail MCP Server

AI agents invoke upload_sieve_script to trigger actions in TrekMail MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why upload_sieve_script needs a policy

Sieve scripts are executable programs that run server-side to filter, redirect, or manipulate email. Uploading and activating one constitutes running code on the mail server. It also irreversibly replaces existing visual filters, though the script itself can be overwritten again.

From the tool's definition 'Upload and activate a custom Sieve script for a mailbox. This replaces any visual filters.' — uploads and activates executable mail-filtering logic; 'The server validates syntax before activating' confirms code execution path.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upload_sieve_script Rate-limited

upload_sieve_script stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "upload_sieve_script": {
      "limits": [
        {
          "counter": "upload_sieve_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about upload_sieve_script

What does the upload_sieve_script tool do? +

Upload and activate a custom Sieve script for a mailbox. This replaces any visual filters. The server validates syntax before activating. Agency plan only. Dangerous extensions (vnd.dovecot.pipe, vnd.dovecot.execute, vnd.dovecot.filter) are blocked. It is categorised as a Execute tool in the TrekMail MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on upload_sieve_script? +

Register the TrekMail MCP Server MCP server in PolicyLayer and add a rule for upload_sieve_script: 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 TrekMail MCP Server. Nothing to install.

What risk level is upload_sieve_script? +

upload_sieve_script is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit upload_sieve_script? +

Yes. Add a rate_limit block to the upload_sieve_script 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 upload_sieve_script completely? +

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

upload_sieve_script is provided by the TrekMail MCP Server MCP server (trekmail/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.