How to integrate Cradl AI MCP with Pydantic AI

This guide walks you through connecting Cradl AI to Pydantic AI using the Composio tool router. By the end, you'll have a working Cradl AI agent that can extract invoice totals from uploaded pdfs, list failed cradl ai extraction jobs, review purchase order extraction results through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Cradl AI account through Composio's Cradl AI 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
Cradl AI logoCradl AI
S2s Oauth2

Cradl AI is an API-first platform for AI-powered document extraction workflows. Use it to turn invoices, forms, and PDFs into structured data at scale.

11 Tools

Introduction

This guide walks you through connecting Cradl AI to Pydantic AI using the Composio tool router. By the end, you'll have a working Cradl AI agent that can extract invoice totals from uploaded pdfs, list failed cradl ai extraction jobs, review purchase order extraction results through natural language commands.

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

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

Also integrate Cradl AI with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle 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 Cradl AI
  • 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 Cradl AI 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 Cradl AI MCP server, and what's possible with it?

The Cradl AI MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cradl AI account. It provides structured and secure access to your document extraction workflows, so your agent can upload and process documents, start and monitor processing runs, review extracted predictions, and download results on your behalf.

  • Document processing: Have your agent submit a PDF, image, or email to a selected document processing agent for asynchronous extraction.
  • Agent and document discovery: Let the agent list available document processing agents and browse documents in your connected workspace.
  • Processing run management: Direct your agent to start processing runs, list past runs, filter them by status or time, and check their current state and outputs.
  • Prediction review: Instruct your agent to list extracted predictions and inspect their status, extracted fields, errors, and output references.
  • File retrieval: Have your agent download document content, OCR results, annotations, predictions, or processing variables returned by Cradl AI.

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

Download File

Download document, OCR, annotation, prediction, or run-variable content from a Cradl AI file URL returned by another Cradl AI tool.

Get Agent Run

Get the current state and outputs of one Cradl AI agent run.

Get Document

Get metadata, processing links, and annotations for one Cradl AI document by ID.

Get Prediction

Get one extracted prediction, including its status, fields, errors, and downloadable output references.

List Agent Runs

List processing runs for an agent, optionally filtered by status or creation/update time.

List Agents

List document-processing agents available to the connected Cradl AI workspace.

List Documents

List documents in the connected Cradl AI workspace and discover document IDs and content/output file URLs.

List Predictions

List extracted predictions, optionally filtered by model, and discover prediction IDs and output file URLs.

Process Document

Create a persistent Cradl agent run and document, then upload one document for asynchronous extraction in a single call.

Start Agent Run

Create a processing run for an existing Cradl AI agent.

Upload Document to Run

Create a document attached to a Cradl AI agent run and upload its PDF, image, or email bytes.

FRAMEWORKS

How to build Cradl AI MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Cradl AI MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Cradl AI MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Cradl AI MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Cradl AI MCP with Claude Cowork

Codex logo

Codex

Use Cradl AI MCP with Codex

OpenClaw logo

OpenClaw

Use Cradl AI MCP with OpenClaw

Hermes logo

Hermes

Use Cradl AI MCP with Hermes

CLI logo

CLI

Use Cradl AI MCP with CLI

Google ADK logo

Google ADK

Use Cradl AI MCP with Google ADK

LangChain logo

LangChain

Use Cradl AI MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Cradl AI MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Cradl AI MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Cradl AI MCP with LlamaIndex

CrewAI logo

CrewAI

Use Cradl AI MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Cradl AI.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Cradl AI 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