Voice Call MCP Server

@lukaskai

Repository

Basic information

About Voice Call MCP Server

No overview available yet

Voice Call MCP Server config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Voice Call MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Voice Call MCP Server?

Voice Call MCP Server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to initiate and manage outbound phone calls using Twilio and the OpenAI GPT-4o Realtime model. It is designed for developers who want to build AI-powered voice calling applications.

How to use Voice Call MCP Server?

Clone the repository, install dependencies (npm install && npm run build), set required environment variables (Twilio credentials, OpenAI API key, ngrok authtoken), and configure Claude Desktop to use the server by adding it to the MCP servers config. After restarting Claude Desktop, you can ask Claude to make voice calls using natural language commands.

Key features of Voice Call MCP Server

Make outbound phone calls via Twilio
Process call audio in real-time with GPT-4o Realtime model
Real-time language switching during calls
Pre-built prompts for common calling scenarios (e.g., restaurant reservations)
Automatic public URL tunneling with ngrok
Secure handling of credentials

Use cases of Voice Call MCP Server

Notify someone you’ll be late for a meeting via a phone call
Make restaurant reservations and specify language preferences
Reschedule appointments by calling a business and speaking with a receptionist

Frequently asked questions

What phone number format is required?

All phone numbers must be in E.164 format (e.g., +11234567890).

What are the runtime dependencies?

Node.js >= 22, a Twilio account with API credentials, an OpenAI API key, and an ngrok authtoken are required.

Where does the call audio flow?

Audio is forwarded from Twilio to OpenAI’s realtime model and then streamed back to the destination phone through Twilio. An ngrok tunnel exposes your server publicly for Twilio webhooks.

Are there any rate limits or costs to be aware of?

Yes, be aware of your Twilio and OpenAI account’s rate limits and pricing. Call durations affect costs for both services.

How is the server secured?

Credentials are stored in environment variables. The ngrok tunnel uses a random URL protected by a random secret, but public exposure should still be considered.

Comments

More Other MCP servers

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K