set_model_tool · Interview Prep MCP: Risk & Policy

WHAT IT DOES

What set_model_tool does on Interview Prep

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

WHY IT NEEDS A POLICY

Why set_model_tool needs a policy

This tool creates or modifies application configuration data (the active model setting). While the change persists to config, it is reversible — the user can call set_model_tool again with a different model. This makes it Write rather than Destructive.

From the tool's definition Tool description states 'Set the active model (persists to config)' — this modifies configuration state persistently. The tool changes which AI model is active for the interview preparation server, which is a reversible configuration change.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_model_tool Rate-limited

set_model_tool 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": {
    "set_model_tool": {
      "limits": [
        {
          "counter": "set_model_tool_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 Interview Prep, so you can run agents against it safely.

FAQ

Questions about set_model_tool

What does the set_model_tool tool do? +

Set the active model (persists to config). Requires the matching API key. It is categorised as a Write tool in the Interview Prep MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_model_tool? +

Register the Interview Prep MCP server in PolicyLayer and add a rule for set_model_tool: 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 Interview Prep. Nothing to install.

What risk level is set_model_tool? +

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

Can I rate-limit set_model_tool? +

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

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

set_model_tool is provided by the Interview Prep MCP server (shenmali/interview-mcp-first). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.