Name: Voice Call MCP Server
Author: popcornspace

LABSCO SUMMARY

A working base to build on, and it says so plainly.

The pieces are wired end to end and the call really happens, but the project describes itself as a kick-start for your own voice work rather than a finished product - conversation history, latency and error recovery are on its own wish list. Two costs meter while the call runs, Twilio's and OpenAI's, so call duration is a budget line.

What it is

A starting point for AI phone calling. The server places an outbound call through Twilio, streams the audio to OpenAI's realtime model and the reply back to the line, so the two-way conversation continues until the call ends.

What you get

Outbound calls placed through your own Twilio number
Call audio processed live by the realtime model, in both directions
Language switching during the call, so it can start in one and continue in another
Prompts shipped for common scenarios such as booking a restaurant table
An ngrok tunnel set up automatically, because Twilio has to reach your server for the webhooks
Optional call recording behind a flag

Requirements

Node.js 22 or newer, cloned and built locally. Three accounts: Twilio with an account SID, auth token and a number, an OpenAI key, and an ngrok authtoken. All five go in the environment, plus an optional recording flag. Phone numbers must be in E.164 format - a leading plus and country code - or the call is rejected. The ngrok tunnel puts your server on the public internet on a random URL protected by a random secret.

Setup effort

Build from source — git clone https://github.com/popcornspace/voice-call-mcp-server.git

See installation options

USE CASES

01

Making a routine call you keep putting off

Give it the number and the goal - a reservation, a reschedule - and let it hold the conversation.

02

Calling in a language you do not speak

State the language in the request; the model can also switch mid-call if the person answers in another one.

03

Building your own calling agent

Fork it and extend the prompts and models - the Twilio, realtime-audio and tunnelling plumbing is already connected.

BEFORE YOU INSTALL

What to know first

Requires

Node.js >= 22
TWILIO_ACCOUNT_SID in your environment
TWILIO_AUTH_TOKEN in your environment
OPENAI_API_KEY in your environment
TWILIO_NUMBER in your environment
NGROK_AUTHTOKEN in your environment

Where it runs

The documented client runs the server on your machine.

INSTALLATION

Connect your client

You clone and build this one yourself.

Server setup

TERMINAL

git clone https://github.com/popcornspace/voice-call-mcp-server.git
cd voice-call-mcp-server
npm install
npm run build

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "voice-call": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_VOICE_CALL_MCP_SERVER>/dist/start-all.cjs"
      ],
      "env": {
        "TWILIO_ACCOUNT_SID": "<YOUR_TWILIO_ACCOUNT_SID>",
        "TWILIO_AUTH_TOKEN": "<YOUR_TWILIO_AUTH_TOKEN>",
        "TWILIO_NUMBER": "<YOUR_TWILIO_NUMBER>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "NGROK_AUTHTOKEN": "<YOUR_NGROK_AUTHTOKEN>"
      }
    }
  }
}

Voice Call MCP Server