Low Risk

main

main

How to control main ↓

AI agents call main to retrieve information from Mcp Nixos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Even though main only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

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

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Nixos, and nothing reaches the server without passing your rules. This is the rule we recommend for main:

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

main 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 Mcp Nixos — 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.

Go deeper

What does the main tool do? +

main. It is categorised as a Read tool in the Mcp Nixos MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on main? +

Register the Mcp Nixos MCP server in PolicyLayer and add a rule for main: 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 Mcp Nixos. Nothing to install.

What risk level is main? +

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

Can I rate-limit main? +

Yes. Add a rate_limit block to the main 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 main completely? +

Set action: deny in the PolicyLayer policy for main. 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 main? +

main is provided by the Mcp Nixos MCP server (utensils/mcp-nixos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Nixos tool call.

Deterministic rules across all 3 Mcp Nixos tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

3 Mcp Nixos tools catalogued and risk-classified — across an index of 42,500+ 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.