How to integrate Typeform MCP with Pydantic AI

GET STARTED FOR FREE
Framework Integration Gradient
Typeform Logo
Pydantic AI Logo
divider

Introduction

This guide walks you through connecting Typeform to Pydantic AI using the Composio tool router. By the end, you'll have a working Typeform agent that can list all recent responses for a form, create a new form for event signup, export submissions from my survey to csv through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Typeform account through Composio's Typeform 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:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Typeform
  • 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 Typeform 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 Typeform MCP server, and what's possible with it?

The Typeform MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Typeform account. It provides structured and secure access so your agent can perform Typeform operations on your behalf.

Supported Tools & Triggers

Tools
Create Account WorkspaceTool to create a new workspace in a specific Typeform account.
Create FormTool to create a new Typeform form with customizable fields, logic, and settings.
Create ImageTool to upload a new image to your Typeform account via base64 encoding or URL.
Create or Update WebhookTool to create a new webhook or update an existing one for a specified Typeform.
Create ThemeTool to create a new custom theme in Typeform with colors, fonts, background, and layout settings.
Create WorkspaceTool to create a new workspace in Typeform.
Delete FormTool to permanently delete a Typeform and all of its responses.
Delete ImageTool to delete an image from your Typeform account.
Delete ResponsesTool to delete specific responses from a Typeform by response IDs.
Delete ThemeTool to delete a theme from your Typeform account.
Delete WebhookTool to delete a webhook configuration from a Typeform form.
Delete WorkspaceTool to delete a workspace from your Typeform account.
Get About MeGet information about the owner account in Typeform.
Get All Response FilesTool to retrieve a compressed archive containing all files that respondents uploaded for a specified form.
Get Background By SizeTool to retrieve a background image by size from Typeform.
Get Choice Image By SizeTool to retrieve a choice image by size from Typeform.
Get FormTool to retrieve a specific form's complete configuration including fields, logic, settings, and theme.
Get Form MessagesTool to retrieve custom messages for a Typeform including button labels, error messages, and UI text.
Get Form ResponsesTool to retrieve form responses from Typeform with filtering by date, pagination, search, and response type.
Get Image By SizeTool to retrieve an image in a specific size from Typeform.
Get ThemeTool to retrieve a specific theme's configuration including colors, fonts, and layout settings.
Get WebhookTool to retrieve a single webhook by specifying both the form ID and webhook tag.
Get WorkspaceTool to retrieve detailed information about a specific workspace including its name, forms, and team members.
List FormsTool to retrieve a list of all forms in your Typeform account with filtering, pagination, and sorting options.
List ImagesTool to retrieve all images in your Typeform account in reverse-chronological order.
List Typeform ThemesTool to retrieve a paginated list of themes in your Typeform account.
List Form WebhooksTool to retrieve all webhooks associated with a specified typeform.
List WorkspacesTool to retrieve all workspaces in a Typeform account with their IDs, names, form counts, and members.
Patch FormTool to partially update a Typeform using JSON Patch operations.
Update Theme (Partial)Tool to partially update a Typeform theme by ID.
Update FormTool to update an existing Typeform by completely replacing its configuration.
Update Form MessagesTool to update custom messages for form UI elements like buttons, errors, and placeholders in Typeform.
Update ThemeTool to update a theme's complete definition in Typeform.
Update WorkspaceTool to update a workspace's name or manage team member access (add/remove members) in Typeform.
Upload VideoInitiate a video upload to Typeform by obtaining a signed upload URL.

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

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

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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

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

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

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 Typeform
  • MCPServerStreamableHTTP connects to the Typeform MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

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 Typeform
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["typeform"],
    )
    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 Typeform 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

Initialize the Pydantic AI Agent

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

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 Typeform.\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
  • Typeform API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

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 Typeform 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 Typeform
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["typeform"],
    )
    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
    typeform_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[typeform_mcp],
        instructions=(
            "You are a Typeform assistant. Use Typeform 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 Typeform.\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 Typeform through Composio's Tool Router. With this setup, your agent can perform real Typeform 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 + Typeform for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Typeform MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Typeform MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Typeform MCP with Claude Agent SDK

Google ADK

Google ADK

Use Typeform MCP with Google ADK

LangChain

LangChain

Use Typeform MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Typeform MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Typeform MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Typeform MCP with LlamaIndex

CrewAI

CrewAI

Use Typeform MCP with CrewAI

Claude Code

Claude Code

Use Typeform MCP with Claude Code

Codex

Codex

Use Typeform MCP with Codex

FAQ

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

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

Can I use Tool Router MCP with Pydantic AI?

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 Typeform tools.

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

Yes, absolutely. You can configure which Typeform 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 Typeform 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.

Book a call↗Get started for free