kef_set_source · Kef MCP: Risk & Policy

WHAT IT DOES

What kef_set_source does on Kef

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

WHY IT NEEDS A POLICY

Why kef_set_source needs a policy

This tool changes the active input source on a KEF speaker, which is a reversible configuration change (can be switched back at any time). It modifies device state but causes no data loss, financial impact, or irreversible effects.

From the tool's definition Switch the KEF input source

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kef_set_source Rate-limited

kef_set_source 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": {
    "kef_set_source": {
      "limits": [
        {
          "counter": "kef_set_source_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 Kef, so you can run agents against it safely.

FAQ

Questions about kef_set_source

What does the kef_set_source tool do? +

Switch the KEF input source. It is categorised as a Write tool in the Kef MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on kef_set_source? +

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

What risk level is kef_set_source? +

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

Can I rate-limit kef_set_source? +

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

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

kef_set_source is provided by the Kef MCP server (nqrwhal/kef-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.