ALWAYS use this tool when asked about architecture rules, code quality policies, or whether the codebase follows best practices. Evaluates 9 configurable rules: dead code, god files, duplicates, high-fan-in, DB writes per route, circular imports, long functions, long files, security issues. Retur...
AI agents call nm_rules 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.
nm_rules is a query/analysis tool that examines a codebase against configurable rules and reports violations. It retrieves and evaluates information from the Neo4j knowledge graph without creating, modifying, or deleting data. The tool has no side effects beyond reading the graph. This is a Read operation with low severity since misuse would only result in incorrect analysis, not system damage or data loss.
From the tool's definition Tool description states it 'Evaluates' and 'Returns pass/fail per rule with violations' — the verb 'evaluates' and the pattern of returning assessment results indicates querying/analyzing existing data.
Documented attack patterns abuse exactly the kind of access nm_rules 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_rules:
{
"version": "1",
"default": "deny",
"tools": {
"nm_rules": {}
}
}nm_rules 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 architecture rules, code quality policies, or whether the codebase follows best practices. Evaluates 9 configurable rules: dead code, god files, duplicates, high-fan-in, DB writes per route, circular imports, long functions, long files, security issues. Returns pass/fail per rule with violations. 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_rules: 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_rules 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_rules 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_rules. 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_rules 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.