How to integrate Teltel MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Teltel logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Teltel to AutoGen using the Composio tool router. By the end, you'll have a working Teltel agent that can retrieve all missed calls from today, list all sms messages from specific number, show teltel users added this week through natural language commands.

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

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

Also integrate Teltel with

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 Teltel
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Teltel tools
  • Run a live chat loop where you ask the agent to perform Teltel 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 Teltel MCP server, and what's possible with it?

The Teltel MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Teltel account. It provides structured and secure access to your telecom data, so your agent can retrieve call logs, manage SMS messages, access user records, and handle inbound SMS events automatically.

  • Comprehensive call log retrieval: Quickly fetch and filter detailed lists of your recent and historical calls, including duration, status, and time for easy reporting or analysis.
  • SMS message management: Effortlessly access sent and received SMS logs, filter messages by sender, recipient, status, or date, and keep your communications organized.
  • User directory synchronization: Retrieve up-to-date lists of all users in your Teltel account, making it simple to manage contact center agents or team members.
  • Automated inbound SMS handling: Set up your agent to receive and process incoming SMS via webhook, so you never miss an important customer message or support request.

Supported Tools & Triggers

Tools
Create Autodialer Custom StatusTool to create a custom status for autodialer contacts.
Create CallTool to create a call between two participants.
Create User StatusTool to create a user status in TelTel.
Delete Autodialer Custom StatusTool to delete an autodialer custom status by ID.
Delete User StatusTool to delete a user status by ID.
Get Account BalanceTool to retrieve the account balance for your TelTel account.
Get Call ListTool to retrieve a list of calls with details (duration, time, status).
Get CountryTool to retrieve country resource information by ID from TelTel.
Get SMS ListTool to retrieve a list of sent (outbox) or received (inbox) SMS messages from TelTel.
Get User Caller ID GroupsTool to retrieve caller ID groups for a specific user.
Get Users ListTool to retrieve a list of users from your TelTel account.
List Autodialer ActionsTool to retrieve the action history for an autodialer campaign.
List Autodialer ContactsTool to retrieve the contact list for an autodialer campaign.
List Autodialer Custom StatusesTool to retrieve list of autodialer custom statuses.
List Autodialer CampaignsTool to retrieve a list of autodialer campaigns from TelTel.
List Available CountriesTool to get the list of countries where DID numbers are available for purchase.
List Country Price GroupsTool to retrieve phone number price groups available in a specific country.
List DevicesTool to retrieve a list of devices from your TelTel account.
List My NumbersTool to retrieve a list of phone numbers (DIDs) owned by the account.
List DID OrdersTool to retrieve a list of DID (phone number) orders from TelTel.
List User StatusesTool to retrieve a list of all user statuses in TelTel.
Lookup Phone NumberTool to perform HLR (Home Location Register) lookup for phone numbers via TelTel API.
Receive Inbound SMSTool to process inbound SMS webhook data from TelTel.
Set User StatusTool to set a user's status in TelTel.
Update Autodialer Custom StatusTool to update an autodialer custom status value by ID.
Update User StatusTool to update an existing user status in TelTel.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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 Teltel 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 Teltel 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 Teltel 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 Teltel session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["teltel"]
    )
    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 Teltel 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 Teltel assistant agent with MCP tools
    agent = AssistantAgent(
        name="teltel_assistant",
        description="An AI assistant that helps with Teltel 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 Teltel 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 Teltel 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 Teltel 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 Teltel 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 Teltel session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["teltel"]
    )
    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 Teltel assistant agent with MCP tools
        agent = AssistantAgent(
            name="teltel_assistant",
            description="An AI assistant that helps with Teltel 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 Teltel 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 Teltel 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 Teltel, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Teltel MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Teltel MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Teltel MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Teltel MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Teltel MCP with Claude Cowork

Codex logo

Codex

Use Teltel MCP with Codex

OpenClaw logo

OpenClaw

Use Teltel MCP with OpenClaw

Hermes logo

Hermes

Use Teltel MCP with Hermes

CLI logo

CLI

Use Teltel MCP with CLI

Google ADK logo

Google ADK

Use Teltel MCP with Google ADK

LangChain logo

LangChain

Use Teltel MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Teltel MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Teltel MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Teltel MCP with LlamaIndex

CrewAI logo

CrewAI

Use Teltel MCP with CrewAI

FAQ

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

With a standalone Teltel MCP server, the agents and LLMs can only access a fixed set of Teltel tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Teltel 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 Teltel tools.

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

Yes, absolutely. You can configure which Teltel 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 Teltel data and credentials are handled as safely as possible.

Used by agents from

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

Get started for freeGet a demo↗