AI agents call test_api_connection 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 performs a read-only connectivity test against the API endpoint. It retrieves or queries the status of the API connection without causing any side effects, data modifications, or triggering external operations. The blast radius of misuse is minimal—an agent could only repeatedly test connectivity, which has no destructive or operational impact.
From the tool's definition Tool name 'test_api_connection' and description 'Test connectivity to the Mailcow API' indicate a diagnostic operation that checks connectivity without modifying, executing, or deleting any resources.
Documented attack patterns abuse exactly the kind of access test_api_connection 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 test_api_connection:
{
"version": "1",
"default": "deny",
"tools": {
"test_api_connection": {}
}
}test_api_connection 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.
Test connectivity to the Mailcow API. 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 test_api_connection: 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.
test_api_connection 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 test_api_connection 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 test_api_connection. 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.
test_api_connection 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.