ALWAYS use this tool when asked about codebase health, code quality, dead code, god files, duplicates, or infrastructure stats. Returns full stats for ALL node types (files, functions, classes, routes, DB tables, env vars, queues, metrics, spans, topics, security issues, etc.), plus optional dead...
AI agents call nm_health to retrieve information from NOMIK without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes metadata about a codebase stored in a Neo4j knowledge graph. It queries statistics, identifies patterns (dead code, duplicates, god files), and reports findings—all read-only operations with no side effects on the codebase itself. While comprehensive in scope, it poses minimal risk as it neither executes code, modifies data, nor triggers external operations.
From the tool's definition Tool description explicitly states it 'Returns full stats' and performs 'analysis' of codebase properties. No modification, deletion, or execution capabilities mentioned.
Documented attack patterns abuse exactly the kind of access nm_health gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NOMIK, and nothing reaches the server without passing your rules. This is the rule we recommend for nm_health:
{
"version": "1",
"default": "deny",
"tools": {
"nm_health": {}
}
}nm_health 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.
ALWAYS use this tool when asked about codebase health, code quality, dead code, god files, duplicates, or infrastructure stats. Returns full stats for ALL node types (files, functions, classes, routes, DB tables, env vars, queues, metrics, spans, topics, security issues, etc.), plus optional dead code/god object/god file/duplicate analysis with edge type distribution. It is categorised as a Read tool in the NOMIK MCP Server, which means it retrieves data without modifying state.
Register the NOMIK MCP server in PolicyLayer and add a rule for nm_health: 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 NOMIK. Nothing to install.
nm_health 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 nm_health 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 nm_health. 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.
nm_health is provided by the NOMIK MCP server (willfreed1/nomik). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NOMIK, 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.
21 NOMIK tools catalogued and risk-classified — across an index of 43,000+ MCP servers.