SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Msg91 MCP with Pydantic AI

Connect Pydantic AI to Msg91 MCP. Send sms to new customer leads, list all ongoing marketing campaigns, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Msg91 logoMsg91
Api Key

MSG91 is a cloud communication platform for sending SMS, WhatsApp, Email, and Voice notifications. It lets businesses securely reach customers across multiple channels from one unified API.

8 Tools

Introduction

This guide walks you through connecting Msg91 to Pydantic AI using the Composio tool router. By the end, you'll have a working Msg91 agent that can send and verify OTPs, send SMS via flows, list campaigns, and track failed events through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Msg91 account through Composio's Msg91 MCP server.

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Msg91 with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Msg91
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Msg91 workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Msg91 MCP server, and what's possible with it?

The Msg91 MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Msg91 account. It provides structured and secure access to your SMS, campaign, and user event data, so your agent can perform actions like sending SMS messages, tracking campaigns, recording user events, and monitoring delivery failures on your behalf.

  • Send personalized SMS messages: Let your agent dispatch SMS messages to one or multiple recipients, making customer outreach fast and automated.
  • List and track marketing campaigns: Instantly retrieve an overview of all your ongoing or past campaigns, including support for pagination.
  • Create and log user events: Easily record user actions and behaviors in Msg91 Segmento so you can automate engagement and track interactions.
  • Retrieve available event types: Ask your agent to list all defined event types to keep your analytics and segmentation organized and up to date.
  • Monitor failed events for campaigns: Quickly inspect which events failed validation for any campaign, helping you troubleshoot and optimize your communication workflows.

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

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

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.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Msg91
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Msg91
  • MCPServerStreamableHTTP connects to the Msg91 MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Msg91
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["msg91"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Msg91 tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
msg91_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[msg91_mcp],
    instructions=(
        "You are a Msg91 assistant. Use Msg91 tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Msg91 endpoint
  • The agent uses GPT-5 to interpret user commands and perform Msg91 operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Msg91.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Msg91 API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Msg91 and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Msg91
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["msg91"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    msg91_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[msg91_mcp],
        instructions=(
            "You are a Msg91 assistant. Use Msg91 tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Msg91.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

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

Conclusion

You've built a Pydantic AI agent that can interact with Msg91 through Composio's Tool Router. With this setup, your agent can perform real Msg91 actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Msg91 for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Msg91 action and event your agent gets out of the box.

Create User Events

Create and track user events in MSG91 Segmento for customer behavior analysis and segmentation.

Get Event Types

Retrieves all event types configured in MSG91 Segmento.

Get Failed Events

Retrieve failed user events from a MSG91 Segmento campaign.

List Campaigns

Tool to list all campaigns in Segmento.

Resend OTP

Resend OTP to the same mobile number via text message or voice call.

Send OTP

Tool to send OTP (One-Time Password) to a mobile number using a pre-configured MSG91 template.

Send SMS via Flow (V5)

Send SMS messages using pre-defined templates via MSG91 Flow API v5.

Verify OTP

Tool to verify an OTP (One-Time Password) sent to a mobile number.

FRAMEWORKS

How to build Msg91 MCP Agent with another framework

Claude Code logo

Claude Code

Use Msg91 MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Msg91 MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Msg91 MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Msg91 MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Msg91 MCP with Grok Bot

Codex logo

Codex

Use Msg91 MCP with Codex

OpenClaw logo

OpenClaw

Use Msg91 MCP with OpenClaw

Hermes logo

Hermes

Use Msg91 MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Msg91 MCP with Atomic Agent

Google ADK logo

Google ADK

Use Msg91 MCP with Google ADK

LangChain logo

LangChain

Use Msg91 MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Msg91 MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Msg91 MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Msg91 MCP with LlamaIndex

CrewAI logo

CrewAI

Use Msg91 MCP with CrewAI

AutoGen logo

AutoGen

Use Msg91 MCP with AutoGen

FAQ

Frequently asked questions

Start with Msg91.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Msg91 tool your agent needs.Free to start.

Start building