zeph_prompt · Zeph To MCP: Risk & Policy

WHAT IT DOES

What zeph_prompt does on Zeph To

AI agents use zeph_prompt 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_prompt needs a policy

zeph_prompt solicits and collects user responses, modifying the interaction state between agent and user. While it retrieves a user's choice (Read-like), the primary action is requesting and recording user input into an interactive workflow. The blocking behavior until response suggests state mutation.

From the tool's definition Tool description states it blocks execution 'until the user responds' and enables the AI agent to collect user input via predefined options. This represents interactive user engagement where the agent writes/commits a pending confirmation/choice state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

zeph_prompt Rate-limited

zeph_prompt 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_prompt": {
      "limits": [
        {
          "counter": "zeph_prompt_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_prompt

What does the zeph_prompt tool do? +

Ask the user to choose from predefined options via push notification. The tool blocks until the user responds or the timeout is reached. Requires ZEPH_HOOK_ID environment variable. 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_prompt? +

Register the Zeph To MCP server in PolicyLayer and add a rule for zeph_prompt: 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_prompt? +

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

Can I rate-limit zeph_prompt? +

Yes. Add a rate_limit block to the zeph_prompt 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_prompt completely? +

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

zeph_prompt 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.