How do I install Telephony MCP Server?

Follow the setup instructions on the Telephony GitHub repository, then add the server configuration to your AI client.

What category is Telephony MCP Server?

Telephony is categorized under Communication. Browse more servers in these categories on MCPgee.

Telephony

Name: Telephony MCP Server
Author: khan2a

v1.0.0•Communication•stable

A very simple no-fuss minimalist MCP Server with telephony tools like voice call and sms. This MCP Server can be integrated with LLM applications. Vonage API is used for calls, SMS, Speech-to-Text and Speech Recognition.

mcpmcp-serverpythontelephonyvonage

Stars

Downloads

Weekly

0/5

View on GitHub

What is Telephony?

Telephony is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to very simple no-fuss minimalist mcp server with telephony tools like voice call and sms. this mcp server can be integrated with llm applications. vonage api is used for calls, sms, speech-to-text and s...

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

A very simple no-fuss minimalist MCP Server with telephony t

Use Cases

Make voice calls and send SMS messages through Vonage API.

Automate telephony operations including speech-to-text and voice recognition.

Integrate telephony capabilities into LLM applications.

khan2a

Maintainer

LicenseMIT

Languagepython

Versionv1.0.0

UpdatedDec 31, 2025

Statushealthy

Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

View Source Browse All Servers

Installation

Manual Installation

npx telephony

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms

ThroughputMedium

Resource Usage

Memory UsageLow

CPU UsageLow

How to Set Up and Use Telephony

Telephony MCP Server is a minimalist Python MCP server that brings voice call and SMS capabilities into LLM applications via the Vonage API, supporting outbound calls with configurable language and accent, SMS messaging, speech-to-text, and a webhook callback server for receiving Vonage events.

Prerequisites

Python 3.13+ installed
Valid Vonage account with API key, API secret, application ID, and a provisioned virtual phone number (LVN)
Vonage private key file downloaded from the Vonage dashboard
Public HTTPS URL for Vonage callbacks — use ngrok for local development
pip, Poetry, or Docker Compose for dependency installation

Clone the Repository

Clone the telephony MCP server repository to your local machine.

git clone https://github.com/khan2a/telephony-mcp-server.git
cd telephony-mcp-server

Install Dependencies

Install the required Python packages. Choose pip, Poetry, or Docker Compose depending on your workflow.

# pip
pip install -r requirements.txt

# Poetry
poetry install

# Docker Compose
docker compose up --build

Create and Populate the .env File

Create a .env file in the project root with your Vonage credentials. All six variables are required. CALLBACK_SERVER_URL must be publicly reachable by Vonage — use an ngrok tunnel for local development.

VONAGE_API_KEY=your_api_key
VONAGE_API_SECRET=your_api_secret
VONAGE_APPLICATION_ID=your_application_id
VONAGE_PRIVATE_KEY_PATH=/absolute/path/to/private.key
VONAGE_LVN=+15551234567
VONAGE_API_URL=https://api.nexmo.com/v1/calls
VONAGE_SMS_URL=https://rest.nexmo.com/sms/json
CALLBACK_SERVER_URL=https://your-ngrok-id.ngrok.io

Start an ngrok Tunnel for Local Development

Vonage needs a public HTTPS URL to deliver call and SMS event webhooks. Start ngrok on port 8080 (the callback server port) and paste the HTTPS URL into your .env file as CALLBACK_SERVER_URL.

ngrok http 8080

Configure Claude Desktop

Add the telephony server to your Claude Desktop MCP config so the voice_call and send_sms tools become available in the chat interface.

{
  "mcpServers": {
    "telephony": {
      "command": "python",
      "args": ["-m", "telephony_mcp_server"],
      "cwd": "/path/to/telephony-mcp-server",
      "env": {
        "VONAGE_API_KEY": "your_api_key",
        "VONAGE_API_SECRET": "your_api_secret",
        "VONAGE_APPLICATION_ID": "your_application_id",
        "VONAGE_PRIVATE_KEY_PATH": "/path/to/private.key",
        "VONAGE_LVN": "+15551234567",
        "CALLBACK_SERVER_URL": "https://your-ngrok-id.ngrok.io"
      }
    }
  }
}

Test the Connection

Ask Claude to make a test call or send an SMS to a number you control. The callback server running on port 8080 will receive Vonage events and expose them at GET /events.

Telephony Examples

Client configuration

Claude Desktop config connecting to the Telephony MCP server with Vonage credentials passed as environment variables.

{
  "mcpServers": {
    "telephony": {
      "command": "python",
      "args": ["-m", "telephony_mcp_server"],
      "cwd": "/path/to/telephony-mcp-server",
      "env": {
        "VONAGE_API_KEY": "abc123",
        "VONAGE_API_SECRET": "secretXYZ",
        "VONAGE_APPLICATION_ID": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
        "VONAGE_PRIVATE_KEY_PATH": "/Users/yourname/.vonage/private.key",
        "VONAGE_LVN": "+15551234567",
        "VONAGE_API_URL": "https://api.nexmo.com/v1/calls",
        "VONAGE_SMS_URL": "https://rest.nexmo.com/sms/json",
        "CALLBACK_SERVER_URL": "https://abc123.ngrok.io"
      }
    }
  }
}

Prompts to try

Natural-language instructions you can give Claude once the Telephony MCP server is connected.

- "Call +15559876543 and say 'Your package has been delivered'."
- "Send an SMS to +15559876543 saying 'Meeting starts in 10 minutes'."
- "Call the number using a British English accent and read today's weather forecast."
- "What Vonage callback events have been received so far?"
- "Send a text message with a confirmation code to +15559876543."

Troubleshooting Telephony

Vonage returns 401 Unauthorized on voice call attempts

Check that VONAGE_APPLICATION_ID matches the application you created in the Vonage dashboard, and that VONAGE_PRIVATE_KEY_PATH points to the exact private.key file downloaded for that application. The API key and secret alone are not sufficient for voice calls — they require application-level JWT authentication.

Calls connect but Vonage cannot deliver webhook events

CALLBACK_SERVER_URL must be a publicly reachable HTTPS URL. Restart ngrok if the tunnel expired and update the CALLBACK_SERVER_URL value. Also verify the callback server is running on port 8080 and that your Vonage application's answer and event URLs point to the ngrok domain.

ImportError for mcp, fastapi, or pyjwt on startup

Run 'pip install -r requirements.txt' again from the project root and confirm you are using Python 3.13+. The server requires specific versions of FastAPI, pyjwt, and the MCP SDK that may not be installed in older environments.

Frequently Asked Questions about Telephony

What is Telephony?

Telephony is a Model Context Protocol (MCP) server that very simple no-fuss minimalist mcp server with telephony tools like voice call and sms. this mcp server can be integrated with llm applications. vonage api is used for calls, sms, speech-to-text and speech recognition. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Telephony?

Follow the installation instructions on the Telephony GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Telephony?

Telephony works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Telephony free to use?

Yes, Telephony is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Telephony Alternatives — Similar Communication Servers

Looking for alternatives to Telephony? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.

Slack

★ 86.1k

Enables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl

LibreChat

★ 37.3k

Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA

Note Gen

★ 11.9k

A cross-platform Markdown AI note-taking software.

DeepChat

★ 5.8k

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

WhatsApp MCP

★ 5.7k

Connects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without

Apple

★ 3.1k

Enables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Communication Browse All Servers

Set Up Telephony in Your Editor

Choose your AI client for step-by-step setup instructions.

🖥️

Claude Desktop

macOS & Windows app

⌨️

Claude Code

CLI & terminal

📝

Cursor

AI-first code editor

💻

VS Code

GitHub Copilot MCP

🏄

Windsurf

Codeium AI editor

🔌

Cline

VS Code extension

Quick Config Preview

{
  "mcpServers": {
    "telephony": {
      "command": "npx",
      "args": ["-y", "telephony"]
    }
  }
}

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Telephony?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides

Explore All Servers Read Our Guides