ALWAYS use this tool when asked about a specific file or function context — what it contains, calls, is called by, and imports. Returns the complete context from the knowledge graph. Do NOT read the source file manually to understand its role — this tool already has the graph-level view.
AI agents call nm_context 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.
The nm_context tool retrieves information from the persistent knowledge graph stored in Neo4j. It queries and returns code context data (file/function relationships, dependencies, call chains) without creating, modifying, deleting, or executing anything. The guidance to use it 'when asked about a specific file or function context' and the emphasis on the 'graph-level view' confirms this is a data retrieval mechanism.
From the tool's definition Tool description explicitly states it 'Returns the complete context from the knowledge graph' and performs querying operations like 'what it contains, calls, is called by, and imports' — all read-only retrieval operations with no side effects.
Documented attack patterns abuse exactly the kind of access nm_context 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_context:
{
"version": "1",
"default": "deny",
"tools": {
"nm_context": {}
}
}nm_context 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 a specific file or function context — what it contains, calls, is called by, and imports. Returns the complete context from the knowledge graph. Do NOT read the source file manually to understand its role — this tool already has the graph-level view. 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_context: 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_context 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_context 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_context. 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_context 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.