Last updated 27 May 2025
The Telnyx Local MCP (Model Context Protocol) Server streamlines your workflow and enhances your capabilities when handling real-time communications and AI assistance. This guide walks you through the step-by-step process of setting up and using Telnyx MCP server effectively.
To start, ensure you have the following prerequisites:
First, clone the Telnyx MCP server repository from GitHub:
git clone https://github.com/team-telnyx/telnyx-mcp-server.git
cd telnyx-mcp-server
Next, install the necessary dependencies using Python’s package manager. If you don't have it yet, install UPX with Homebrew:
brew install uv
Additionally, ensure UVX (Python package manager) is installed via Curl or Homebrew:
Using Curl:
curl -sSL https://install.uvx.sh | sh
Using Homebrew:
brew install uv
You'll need to modify Claude's config.json file with your Telnyx API key:
Start the MCP server and ensure it integrates correctly with Claude desktop. Test its functionality by making requests directly through Claude.
For example, search for a Telnyx phone number:
Claude can directly interact with Telnyx’s API to purchase phone numbers and configure them for use with Telnyx AI Assistants. For instance:
Use Claude to refine the assistant's prompt and instructions if initial testing indicates issues (e.g., incorrect time formatting).
Upon completion, you should have a fully functional, Telnyx-powered AI assistant capable of:
Integrating Telnyx MCP server with Claude desktop simplifies the process, enabling quick iterations and improvements without extensive prompting expertise.
Related articles