dj_speak · Claude DJ MCP: Risk & Policy

WHAT IT DOES

What dj_speak does on Claude DJ MCP

AI agents invoke dj_speak to trigger actions in Claude DJ MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why dj_speak needs a policy

This tool executes system commands (say/espeak-ng) to generate and broadcast audio output to an active listener base. While not destructive or financial, it is Execute-category because it runs external processes with side effects that depend on user-supplied arguments.

From the tool's definition The tool 'dj_speak' performs text-to-speech synthesis and broadcasts announcements to all listeners in an audio stream. It triggers external operations (macOS 'say' command or Linux 'espeak-ng') whose effects depend on the input text argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dj_speak Rate-limited

dj_speak stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "dj_speak": {
      "limits": [
        {
          "counter": "dj_speak_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about dj_speak

What does the dj_speak tool do? +

Use text-to-speech to announce over the music. All listeners hear the announcement in the stream. Works on macOS (say) and Linux (espeak-ng). It is categorised as a Execute tool in the Claude DJ MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on dj_speak? +

Register the Claude DJ MCP server in PolicyLayer and add a rule for dj_speak: 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 Claude DJ MCP. Nothing to install.

What risk level is dj_speak? +

dj_speak is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit dj_speak? +

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

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

dj_speak is provided by the Claude DJ MCP server (uetuluk/claude-dj-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.