Low Risk

nm_search

ALWAYS use this tool when the user mentions

How to control nm_search ↓

What nm_search does on NOMIK

AI agents call nm_search 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.

Low Risk

Why nm_search needs a policy

This tool queries an existing knowledge graph to retrieve information about code structure, dependencies, and relationships. It retrieves data without modifying or executing anything, making it a Read operation. The blast radius is minimal—worst case, an agent retrieves incorrect or sensitive code information, but cannot modify systems or execute code.

From the tool's definition Tool name 'nm_search' and context as a code intelligence graph query tool that 'searches' or retrieves data from a Neo4j knowledge graph of codebase information.

Documented attack patterns abuse exactly the kind of access nm_search gives an agent:

How to control nm_search

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_search:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "nm_search": {}
  }
}

nm_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register NOMIK — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about nm_search

What does the nm_search tool do? +

ALWAYS use this tool when the user mentions. It is categorised as a Read tool in the NOMIK MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on nm_search? +

Register the NOMIK MCP server in PolicyLayer and add a rule for nm_search: 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.

What risk level is nm_search? +

nm_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit nm_search? +

Yes. Add a rate_limit block to the nm_search 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.

How do I block nm_search completely? +

Set action: deny in the PolicyLayer policy for nm_search. 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.

What MCP server provides nm_search? +

nm_search 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.

Enforce policy on every NOMIK tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.