What is the Voice Call MCP Server?

The Voice Call MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude to initiate and manage voice calls using Twilio and OpenAI (GPT-4o Realtime model).

What is MCP?

MCP stands for Model Context Protocol. It is an open protocol that standardizes how applications provide context to LLMs, enabling seamless communication between AI models and external data sources.

What are the key features of the Voice Call MCP Server?

The key features include making outbound phone calls via Twilio, processing call audio in real-time with GPT-4o Realtime model, real-time language switching, pre-built prompts, automatic public URL tunneling with ngrok, and secure handling of credentials.

What are the requirements to run the Voice Call MCP Server?

You need Node.js >= 22, a Twilio account with API credentials, an OpenAI API key, and an Ngrok Authtoken.

How do I install the Voice Call MCP Server?

Clone the repository, install dependencies with npm install, and build the project with npm run build.

How do I configure the server?

You need to set environment variables for Twilio account SID, auth token, phone number, OpenAI API key, and Ngrok Authtoken.

How do I use it with Claude Desktop?

Add the server configuration to your Claude Desktop configuration file and restart Claude Desktop.

What phone number format should I use?

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

What should I do if I encounter an “Invalid credentials” error?

Double-check your TWILIO_ACCOUNT_SID and TWILIO_AUTH_TOKEN from the Twilio Console.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform that helps businesses orchestrate AI Agents, connect them with enterprise data, and build custom AI Agents with LLM models and Multi-Agent Systems.

How does UBOS integrate with the Voice Call MCP Server?

UBOS can integrate with the Voice Call MCP Server to build sophisticated AI Agents that can initiate and manage voice calls, access real-time data, and perform complex tasks within the UBOS platform.