How to integrate Telegram MCP with Pydantic AI

This guide walks you through connecting Telegram to Pydantic AI using the Composio tool router. By the end, you'll have a working Telegram agent that can send a welcome message to new group members, forward latest announcement to all admins, get total member count of your group through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Telegram account through Composio's Telegram MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Telegram logoTelegram
Api Key

Telegram is a fast, secure cloud messaging app for individuals and groups. It offers robust privacy and real-time chat features.

18 Tools

Introduction

This guide walks you through connecting Telegram to Pydantic AI using the Composio tool router. By the end, you'll have a working Telegram agent that can send a welcome message to new group members, forward latest announcement to all admins, get total member count of your group through natural language commands.

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

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

Also integrate Telegram with

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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 Telegram
  • 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 Telegram 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 Telegram MCP server, and what's possible with it?

The Telegram MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Telegram account. It provides structured and secure access to your chats and bot functionality, so your agent can send messages, manage conversations, retrieve chat data, and interact with users or groups on your behalf.

  • Automated message sending and editing: Let your agent send new messages or edit existing ones in any chat where your bot is present, making real-time communication a breeze.
  • Chat and group management: Effortlessly manage group chats by retrieving chat details, getting administrators, exporting invite links, or counting group members.
  • Advanced chat history and message handling: Ask your agent to fetch chat history, forward messages between chats, or delete messages for streamlined moderation and record-keeping.
  • Bot and user interaction: Enable the agent to answer callback queries from inline keyboards and fetch basic bot information for smarter, context-aware responses.

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 Telegram
  • 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 Telegram
  • MCPServerStreamableHTTP connects to the Telegram 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 Telegram
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["telegram"],
    )
    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 Telegram 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
telegram_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[telegram_mcp],
    instructions=(
        "You are a Telegram assistant. Use Telegram tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Telegram endpoint
  • The agent uses GPT-5 to interpret user commands and perform Telegram 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 Telegram.\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
  • Telegram 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 Telegram 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 Telegram
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["telegram"],
    )
    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
    telegram_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[telegram_mcp],
        instructions=(
            "You are a Telegram assistant. Use Telegram 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 Telegram.\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 Telegram through Composio's Tool Router. With this setup, your agent can perform real Telegram 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 + Telegram 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 Telegram action and event your agent gets out of the box.

Answer Callback Query

Use this method to send answers to callback queries sent from inline keyboards.

Export Chat Invite Link

Generate a new primary invite link for a chat; any previously generated primary link is revoked.

Delete Message

Delete a message, including service messages.

Edit Message

Edit text messages sent by the bot.

Forward Message

Forward messages of any kind.

Get Chat Info

Get up to date information about the chat (current name of the user for one-on-one conversations, current username of a user, group or channel, etc.

Get Chat Administrators

Get a list of administrators in a chat.

Get Chat History

Get chat history messages via the getUpdates polling method, filtered by chat_id.

Get Chat Member

Get a chat member's status/role (including the bot itself) to preflight permissions and troubleshoot 403/empty-history issues.

Get Chat Members Count

Get the number of members in a chat.

Get Bot Info

Get basic information about the bot using the Bot API getMe method.

Get Updates

Use this method to receive incoming updates using long polling.

Send Document

Send general files (documents) to a Telegram chat using the Bot API.

Send Location

Send point on the map location to a Telegram chat using the Bot API.

Send Message

Send a text message to a Telegram chat using the Bot API.

Send Photo

Send photos to a Telegram chat using the Bot API.

Send Poll

Send a native poll to a Telegram chat using the Bot API.

Set Bot Commands

Use this method to change the list of the bot's commands.

FRAMEWORKS

How to build Telegram MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Telegram MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Telegram MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Telegram MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Telegram MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Telegram MCP with Claude Cowork

Codex logo

Codex

Use Telegram MCP with Codex

Cursor logo

Cursor

Use Telegram MCP with Cursor

OpenClaw logo

OpenClaw

Use Telegram MCP with OpenClaw

Hermes logo

Hermes

Use Telegram MCP with Hermes

CLI logo

CLI

Use Telegram MCP with CLI

Google ADK logo

Google ADK

Use Telegram MCP with Google ADK

LangChain logo

LangChain

Use Telegram MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Telegram MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Telegram MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Telegram MCP with LlamaIndex

CrewAI logo

CrewAI

Use Telegram MCP with CrewAI

OpenCode logo

OpenCode

Use Telegram MCP with OpenCode

VS Code logo

VS Code

Use Telegram MCP with VS Code

FAQ

Frequently asked questions

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

Yes, you can. Pydantic AI 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 Telegram tools.

Yes, absolutely. You can configure which Telegram 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.

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 Telegram data and credentials are handled as safely as possible.

Start with Telegram.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies