zeph_broadcast · Zeph To MCP: Risk & Policy

WHAT IT DOES

What zeph_broadcast does on Zeph To

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

WHY IT NEEDS A POLICY

Why zeph_broadcast needs a policy

This tool sends notifications to users, which is a reversible write operation (notifications can be dismissed or archived). It does not execute arbitrary code, delete data, or move money. While it affects multiple users across a channel, the severity is medium rather than high because notifications are non-destructive and the primary blast radius is unwanted communications rather than data loss or system compromise.

From the tool's definition The tool description explicitly states 'Send a push notification to all subscribers of a channel', which creates/modifies state by delivering a notification to multiple recipients. This is a write operation that creates new notification records/events.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

zeph_broadcast Rate-limited

zeph_broadcast 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": {
    "zeph_broadcast": {
      "limits": [
        {
          "counter": "zeph_broadcast_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 Zeph To, so you can run agents against it safely.

FAQ

Questions about zeph_broadcast

What does the zeph_broadcast tool do? +

Send a push notification to all subscribers of a channel. Use zeph://channels resource to find available channels. It is categorised as a Write tool in the Zeph To MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on zeph_broadcast? +

Register the Zeph To MCP server in PolicyLayer and add a rule for zeph_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 Zeph To. Nothing to install.

What risk level is zeph_broadcast? +

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

Can I rate-limit zeph_broadcast? +

Yes. Add a rate_limit block to the zeph_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 zeph_broadcast completely? +

Set action: deny in the PolicyLayer policy for zeph_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 zeph_broadcast? +

zeph_broadcast is provided by the Zeph To MCP server (zeph-to/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.