switch_active_model · Vault Memory MCP: Risk & Policy

WHAT IT DOES

What switch_active_model does on Vault Memory

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

WHY IT NEEDS A POLICY

Why switch_active_model needs a policy

This tool changes system configuration/state by promoting a registered model to active status. This is Write category (creates or modifies data reversibly) rather than Execute because it's not running arbitrary operations—it's changing a configuration setting.

From the tool's definition Tool name 'switch_active_model' combined with 'promote a registered model to active' indicates modifying state by changing which model is active.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

switch_active_model Rate-limited

switch_active_model 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": {
    "switch_active_model": {
      "limits": [
        {
          "counter": "switch_active_model_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 Vault Memory, so you can run agents against it safely.

FAQ

Questions about switch_active_model

What does the switch_active_model tool do? +

Atomically promote a registered model to active. Fails with. It is categorised as a Write tool in the Vault Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on switch_active_model? +

Register the Vault Memory MCP server in PolicyLayer and add a rule for switch_active_model: 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 Vault Memory. Nothing to install.

What risk level is switch_active_model? +

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

Can I rate-limit switch_active_model? +

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

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

switch_active_model is provided by the Vault Memory MCP server (owrede/vault-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.