Get the current Sieve script for a mailbox. Returns the auto-generated script built from visual filters and auto-reply settings. Use this to inspect what is running on the server.
AI agents call get_sieve_script to retrieve information from TrekMail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries the current Sieve script configuration for a mailbox without modifying, executing, or deleting any data. It is purely informational inspection of existing infrastructure state. The low severity reflects minimal blast radius even if misused by an agent, as it only exposes script contents without the ability to modify, execute, or delete them.
From the tool's definition Tool name 'get_sieve_script' and description 'Get the current Sieve script for a mailbox. Returns the auto-generated script...' - uses 'Get' verb and returns/retrieves data with 'no side effects' as stated in the description ('inspect what is running').
Attacks that exploit this kind of access
Get the current Sieve script for a mailbox. Returns the auto-generated script built from visual filters and auto-reply settings. Use this to inspect what is running on the server. It is categorised as a Read tool in the TrekMail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TrekMail MCP Server MCP server in PolicyLayer and add a rule for get_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.
get_sieve_script 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 get_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.
Set action: deny in the PolicyLayer policy for get_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.
get_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →