Retrieves all the unhandled problems for all the hosts and services
AI agents call get_unhandled_problems to retrieve information from Nagios without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns monitoring status data from Nagios without side effects. It is a read-only retrieval operation analogous to the sibling tools (get_alerts, get_host_status, etc.) on the same server. There is no indication of data modification, deletion, or code execution. The low severity reflects that exposure of monitoring alert data has minimal blast radius compared to other risk categories.
From the tool's definition Tool name is 'get_unhandled_problems' and description states it 'Retrieves all the unhandled problems' - uses retrieval language with no modification, deletion, or execution semantics.
Documented attack patterns abuse exactly the kind of access get_unhandled_problems gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nagios, and nothing reaches the server without passing your rules. This is the rule we recommend for get_unhandled_problems:
{
"version": "1",
"default": "deny",
"tools": {
"get_unhandled_problems": {}
}
}get_unhandled_problems 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.
Retrieves all the unhandled problems for all the hosts and services. It is categorised as a Read tool in the Nagios MCP Server, which means it retrieves data without modifying state.
Register the Nagios MCP server in PolicyLayer and add a rule for get_unhandled_problems: 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 Nagios. Nothing to install.
get_unhandled_problems 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_unhandled_problems 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_unhandled_problems. 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_unhandled_problems is provided by the Nagios MCP server (prospire-technology-services/nagios-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nagios, 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.
17 Nagios tools catalogued and risk-classified — across an index of 43,000+ MCP servers.