Give customer-facing voice agents one MCP server for scheduling and order status

A company points any voice agent platform at its own MCP server so agents can book appointments and check orders for customers.

Difficulty
AdvancedOur rating
Time to build
Not reportedOur estimate
Monthly cost
Not reported
Revenue
Not reportedWe only show revenue the source states
Engagement
1 reply to HN commentComment in “Ask HN: Who is using MCP in production?” (198 points, 201 comments) · fetched Oct 15, 2026

What they did

MitziMoto’s team built a custom MCP server defining the tools and resources their customer-facing voice agents need, such as scheduling appointments and checking order status.

How it went

They can point ElevenLabs, Vapi, Pipecat or another platform at the same server and it immediately understands the tools.

Worth knowing

One MCP server avoids lock-in to a single voice platform.

Builder recipe

Our own starting point, written from the source. Adapt it to your setup.

Stack

  • Voice agent platform
  • Custom MCP server
  • Booking and order APIs

Steps

  1. Collect the incoming channel (inbox, form, tickets) into one workflow.
  2. Have the model classify and extract fields, returning structured JSON.
  3. Route or draft replies; keep a human approval step for anything customer-facing.
  4. Log results and review misclassifications weekly.

Starter prompt

You are the phone assistant for [business]. Use check_order_status and book_appointment only. Confirm name and order number before sharing details. If unsure, offer a human callback.

Tags

Read the original

Related use cases

The Daily 5.

Five real AI agent use cases each morning, each with a recipe and a source. Plus a Sunday roundup. Free.