ALWAYS use this tool when asked to describe, summarize, or understand a codebase. Returns a full briefing: stats (functions, files, classes, routes), language distribution, DB tables, external APIs, env vars, high-risk functions, and health summary. Do NOT manually inspect files — this tool alrea...
AI agents call nm_onboard 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_onboard retrieves and aggregates metadata from a persistent Neo4j knowledge graph about code structure, dependencies, and configuration. While it is purely a read operation, the severity is elevated to medium because the tool exposes sensitive information (external APIs, environment variables, high-risk functions) that could inform an adversary about system architecture and vulnerabilities.
From the tool's definition Tool returns data about codebase structure: 'stats (functions, files, classes, routes), language distribution, DB tables, external APIs, env vars, high-risk functions, and health summary.' No modification, deletion, or execution of code is described.
Documented attack patterns abuse exactly the kind of access nm_onboard 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_onboard:
{
"version": "1",
"default": "deny",
"tools": {
"nm_onboard": {}
}
}nm_onboard 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 to describe, summarize, or understand a codebase. Returns a full briefing: stats (functions, files, classes, routes), language distribution, DB tables, external APIs, env vars, high-risk functions, and health summary. Do NOT manually inspect files — this tool already has the complete picture. 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_onboard: 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_onboard 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_onboard 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_onboard. 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_onboard 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.