broadcast · Claude IPC MCP: Risk & Policy

WHAT IT DOES

What broadcast does on Claude IPC MCP

AI agents invoke broadcast to trigger actions in Claude IPC 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 broadcast needs a policy

Broadcasting a message to all other Claude instances triggers external operations across multiple AI processes simultaneously. This is not a simple write operation — it actively causes other AI agents to receive and potentially act on the message, making it an Execute-category action.

From the tool's definition Broadcast a message to all other Claude instances

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

broadcast Rate-limited

broadcast 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": {
    "broadcast": {
      "limits": [
        {
          "counter": "broadcast_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 IPC MCP, so you can run agents against it safely.

FAQ

Questions about broadcast

What does the broadcast tool do? +

Broadcast a message to all other Claude instances. It is categorised as a Execute tool in the Claude IPC 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 broadcast? +

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

What risk level is broadcast? +

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

Can I rate-limit broadcast? +

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

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

broadcast is provided by the Claude IPC MCP server (jdez427/claude-ipc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.