assign_worker · Baselings MCP: Risk & Policy

WHAT IT DOES

What assign_worker does on Baselings

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

WHY IT NEEDS A POLICY

Why assign_worker needs a policy

This tool creates or modifies data (baseling worker assignment) without permanently destroying it or executing arbitrary code. The assignment appears reversible (a baseling can be reassigned), making it a Write action rather than Destructive or Execute. The severity is medium because misuse could disrupt game strategy and resource accumulation, but the effects are contained within the game and reversible.

From the tool's definition Tool description states 'Put a baseling to work' which modifies the state of a baseling by assigning it to a role (garden, pp, nanny, or hauler). This is a reversible state change operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

assign_worker Rate-limited

assign_worker 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": {
    "assign_worker": {
      "limits": [
        {
          "counter": "assign_worker_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 Baselings, so you can run agents against it safely.

FAQ

Questions about assign_worker

What does the assign_worker tool do? +

Put a baseling to work (garden, pp, nanny, or hauler). It is categorised as a Write tool in the Baselings MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on assign_worker? +

Register the Baselings MCP server in PolicyLayer and add a rule for assign_worker: 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 Baselings. Nothing to install.

What risk level is assign_worker? +

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

Can I rate-limit assign_worker? +

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

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

assign_worker is provided by the Baselings MCP server (jimbo530/baselings-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.