How to integrate Telnyx MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Telnyx Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Telnyx to AutoGen using the Composio tool router. By the end, you'll have a working Telnyx agent that can check current telnyx account balance, list recent audit logs for last week, create new sms notification channel, delete a notification profile by id through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Telnyx account through Composio's Telnyx MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Telnyx
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Telnyx tools
  • Run a live chat loop where you ask the agent to perform Telnyx operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Telnyx MCP server, and what's possible with it?

The Telnyx MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Telnyx account. It provides structured and secure access to your Telnyx communications platform, so your agent can manage networks, handle notification channels, monitor usage, and review account activities on your behalf.

  • Network provisioning and management: Easily create or delete network resources, allowing your agent to spin up new networks or remove unused ones as needed.
  • Notification channel automation: Set up, configure, or remove notification channels—including SMS, voice, email, or webhook endpoints—so your agent can handle event-driven communications flexibly.
  • Notification profile and settings control: Group and configure notification profiles and settings, enabling your agent to define how and when notifications are delivered for different events.
  • Real-time balance monitoring: Retrieve your current account balance and credit details, helping your agent keep tabs on usage and alert you before credits run low.
  • Comprehensive audit log access: Review detailed audit logs so your agent can surface recent changes, track resource modifications, and help maintain compliance or troubleshoot issues quickly.

Supported Tools & Triggers

Tools
Create NetworkTool to create a new network.
Create Notification ChannelTool to create a notification channel.
Create Notification ProfileTool to create a notification profile.
Create Notification SettingTool to add a notification setting.
Delete NetworkTool to delete a network by id.
Delete Notification ChannelTool to delete a notification channel by id.
Delete Notification ProfileTool to delete a notification profile by id.
Delete Notification SettingTool to delete a notification setting by id.
Get User BalanceTool to retrieve the current user account balance and credit details.
List Audit LogsTool to retrieve a list of audit log entries for your account.
List ConnectionsTool to retrieve all connections in your account.
List Dynamic Emergency EndpointsTool to list dynamic emergency endpoints.
List Messaging ProfilesTool to list messaging profiles.
List Messaging URL DomainsTool to list configured messaging url domains.
List Mobile Network OperatorsTool to list available mobile network operators.
List Network InterfacesTool to list all network interfaces for a specified network.
List NetworksTool to list all networks in your account.
List Notification ChannelsTool to list all notification channels.
List Notification Event ConditionsTool to list all notification event conditions.
List Notification EventsTool to list all notification events.
List Notification ProfilesTool to list all notification profiles.
List Phone NumbersTool to list phone numbers associated with your account.
List SSO Authentication ProvidersTool to retrieve all configured sso authentication providers.
Retrieve NetworkTool to retrieve details of a specific network by id.
Retrieve Notification ChannelTool to retrieve a notification channel by id.
Retrieve Notification ProfileTool to retrieve a notification profile by id.
Retrieve Notification SettingTool to retrieve a notification setting by id.
Update NetworkTool to update details of an existing network.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Telnyx account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Telnyx via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Telnyx connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Telnyx session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["telnyx"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Telnyx tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Telnyx assistant agent with MCP tools
    agent = AssistantAgent(
        name="telnyx_assistant",
        description="An AI assistant that helps with Telnyx operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Telnyx tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Telnyx related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Telnyx tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Telnyx and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Telnyx session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["telnyx"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Telnyx assistant agent with MCP tools
        agent = AssistantAgent(
            name="telnyx_assistant",
            description="An AI assistant that helps with Telnyx operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Telnyx related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Telnyx through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Telnyx, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Telnyx MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Telnyx MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Telnyx MCP with Claude Agent SDK

Google ADK

Google ADK

Use Telnyx MCP with Google ADK

LangChain

LangChain

Use Telnyx MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Telnyx MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Telnyx MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Telnyx MCP with LlamaIndex

CrewAI

CrewAI

Use Telnyx MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Telnyx MCP?

With a standalone Telnyx MCP server, the agents and LLMs can only access a fixed set of Telnyx tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Telnyx and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Telnyx tools.

Can I manage the permissions and scopes for Telnyx while using Tool Router?

Yes, absolutely. You can configure which Telnyx scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Telnyx data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free