SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Supadata MCP with Pydantic AI

Connect Pydantic AI to Supadata MCP. Extract all urls from a competitor website, scrape the main content from a blog post, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Supadata logoSupadata
Api Key

Supadata is a web and video-to-text API that extracts structured data from videos and websites. It enables fast, automated content parsing for AI training and analysis.

20 Tools

Introduction

This guide walks you through connecting Supadata to Pydantic AI using the Composio tool router. By the end, you'll have a working Supadata agent that can fetch YouTube transcripts, translate transcripts, scrape and crawl websites, search YouTube, and pull video and channel metadata through natural language commands.

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

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

Also integrate Supadata with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentPiDeepSeek HarnessGoogle 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 Supadata
  • 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 Supadata 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 Supadata MCP server, and what's possible with it?

The Supadata MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Supadata account. It provides structured and secure access to web and video data extraction tools, so your agent can perform actions like scraping websites, mapping URLs, transcribing YouTube videos, and gathering channel or playlist metadata on your behalf.

  • Comprehensive website scraping and content extraction: Instruct your agent to pull structured content from any website, enabling programmatic parsing and analysis for research or automation.
  • Automated sitemap and URL mapping: Let your agent retrieve all URLs from a given website, making it easy to analyze site structure or perform link audits.
  • YouTube video and channel metadata retrieval: Have your agent fetch detailed metadata for any YouTube video, playlist, or channel—including titles, descriptions, stats, and more.
  • YouTube search and discovery: Empower your agent to search YouTube for videos, channels, or playlists by keyword, streamlining content discovery and curation tasks.
  • Playlist and channel video extraction: Direct your agent to list and export videos from specific YouTube channels or playlists, complete with pagination support for large collections.

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

Get Account Information

Retrieve organization details, plan information, and credit usage for the authenticated account.

Get Media Metadata

Retrieve unified metadata for supported social-media content.

Get Video Transcript

Get transcript from a video on supported platforms or from a file URL.

Get Transcript by Job ID

Get the status and results of an asynchronous transcript job by job ID.

Get Video Extraction Result

Retrieve the status and result of a video extraction job using your own Supadata connection.

Get Web Crawl Result

Poll a web crawl and retrieve its pages using your own Supadata connection.

Website URL Map

Crawl a website and extract all URLs/links found on it.

Scrape Web Page

Extract content from any webpage and convert it to Markdown format.

Get YouTube Batch Result

Poll a YouTube transcript or video metadata batch using your own Supadata connection.

Get YouTube Channel Metadata

Fetches metadata for a YouTube channel including name, description, subscriber count, video count, view count, and channel images.

Get YouTube Channel Videos

Tool to retrieve video IDs from a YouTube channel.

Get YouTube Playlist Metadata

Retrieve metadata for a YouTube playlist including title, description, video count, view count, last updated timestamp, and channel information.

Get YouTube Playlist Videos

Tool to retrieve video IDs from a YouTube playlist.

Get YouTube Video Metadata

Retrieve comprehensive metadata for a YouTube video by its ID.

Search YouTube

Search YouTube for videos, channels, or playlists by keyword.

Start Video Extraction

Start asynchronous structured extraction from public videos on supported social platforms or public media files, using a prompt, schema, or both.

Start Web Crawl

Start an asynchronous website crawl following child links under the supplied URL.

Start YouTube Transcript Batch

Start an asynchronous YouTube transcript batch from exactly one list of video IDs, playlist, or channel.

Start YouTube Video Metadata Batch

Start an asynchronous YouTube video metadata batch from exactly one list of video IDs, playlist, or channel.

Translate YouTube Transcript

Translate a YouTube transcript into a requested ISO 639-1 language.

FRAMEWORKS

How to build Supadata MCP Agent with another framework

Claude Code logo

Claude Code

Use Supadata MCP with Claude Code

Cursor logo

Cursor

Use Supadata MCP with Cursor

ChatGPT logo

ChatGPT

Use Supadata MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Supadata MCP with Claude Cowork

Antigravity logo

Antigravity

Use Supadata MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Supadata MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Supadata MCP with Claude Agent SDK

Codex logo

Codex

Use Supadata MCP with Codex

Grok Build logo

Grok Build

Use Supadata MCP with Grok Build

VS Code logo

VS Code

Use Supadata MCP with VS Code

OpenCode logo

OpenCode

Use Supadata MCP with OpenCode

OpenClaw logo

OpenClaw

Use Supadata MCP with OpenClaw

Hermes logo

Hermes

Use Supadata MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Supadata MCP with Atomic Agent

Pi logo

Pi

Use Supadata MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Supadata MCP with DeepSeek Harness

Google ADK logo

Google ADK

Use Supadata MCP with Google ADK

LangChain logo

LangChain

Use Supadata MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Supadata MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Supadata MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Supadata MCP with LlamaIndex

CrewAI logo

CrewAI

Use Supadata MCP with CrewAI

AutoGen logo

AutoGen

Use Supadata MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Supadata.It takes 30 seconds.

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

Start building