AI agents call get_config to retrieve information from Mailcow 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 configuration information for inspection purposes only. There are no side effects, no data modification, no code execution, and no destructive operations. The sanitization note reduces potential information disclosure risk. Although this is within an email server management context (high-value target), the tool itself performs only a passive read operation, making it low-severity even in context.
From the tool's definition Tool name 'get_config' and description 'Get current server configuration (sanitized)' clearly indicate a retrieval operation with no modification or execution capability. The note about 'sanitized' output further suggests defensive filtering of sensitive data.
Documented attack patterns abuse exactly the kind of access get_config gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mailcow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_config:
{
"version": "1",
"default": "deny",
"tools": {
"get_config": {}
}
}get_config is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get current server configuration (sanitized). It is categorised as a Read tool in the Mailcow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mailcow MCP Server MCP server in PolicyLayer and add a rule for get_config: 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 Mailcow MCP Server. Nothing to install.
get_config 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_config 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_config. 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_config is provided by the Mailcow MCP Server MCP server (leolilley/mailcow_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mailcow MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Mailcow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.