Ask the user a question with optional quick-reply buttons and a text input field. Combines prompt (buttons) and input (text) in a single notification. The user can either tap a button or type a response. Blocks until the user responds or the timeout is reached. Requires ZEPH_HOOK_ID environment v...
AI agents call zeph_ask to retrieve information from Zeph To without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
zeph_ask is a request-response tool that collects user input through a notification interface. While it interacts with the user and displays information, it does not execute code, modify data, trigger external operations, delete anything, or move money. The primary effect is retrieving a user response to a question.
From the tool's definition Tool description states it 'Ask[s] the user a question' and 'Blocks until the user responds', indicating it retrieves user input/response data without modifying, creating, or deleting persistent data.
Attacks that exploit this kind of access
Ask the user a question with optional quick-reply buttons and a text input field. Combines prompt (buttons) and input (text) in a single notification. The user can either tap a button or type a response. Blocks until the user responds or the timeout is reached. Requires ZEPH_HOOK_ID environment variable. It is categorised as a Read tool in the Zeph To MCP Server, which means it retrieves data without modifying state.
Register the Zeph To MCP server in PolicyLayer and add a rule for zeph_ask: 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.
zeph_ask is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the zeph_ask 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.
Set action: deny in the PolicyLayer policy for zeph_ask. 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.
zeph_ask 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →