unassign_category · Lutris MCP Server MCP: Risk & Policy

WHAT IT DOES

What unassign_category does on Lutris MCP Server

AI agents use unassign_category to create or update resources in Lutris MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lutris MCP Server environment.

WHY IT NEEDS A POLICY

Why unassign_category needs a policy

Removing a category assignment is a reversible write operation. The game itself is not deleted, and the category can be reassigned at any time. This is a standard data modification with low blast radius.

From the tool's definition 'Remove a game from a category' — this modifies the association between a game and a category, which is reversible (the game can be reassigned)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

unassign_category Rate-limited

unassign_category stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "unassign_category": {
      "limits": [
        {
          "counter": "unassign_category_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Lutris MCP Server, so you can run agents against it safely.

FAQ

Questions about unassign_category

What does the unassign_category tool do? +

Remove a game from a category. It is categorised as a Write tool in the Lutris MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on unassign_category? +

Register the Lutris MCP Server MCP server in PolicyLayer and add a rule for unassign_category: 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 Lutris MCP Server. Nothing to install.

What risk level is unassign_category? +

unassign_category is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit unassign_category? +

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

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

unassign_category is provided by the Lutris MCP Server MCP server (praeses0/lutris-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.