SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Nano nets MCP with Pydantic AI

Connect Pydantic AI to Nano nets MCP. Extract table data from recent invoices, upload new receipts for ocr model training, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Nano nets logoNano nets
Api Key

Nano nets is an AI-powered Intelligent Document Processing API for extracting structured data from unstructured documents. It boosts workflow automation by turning messy documents into clean, usable information.

11 Tools

Introduction

This guide walks you through connecting Nano nets to Pydantic AI using the Composio tool router. By the end, you'll have a working Nano nets agent that can create OCR models, upload training images, list prediction files, browse workflows and documents, and update model guidelines through natural language commands.

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

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

Also integrate Nano nets 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 Nano nets
  • 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 Nano nets 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 Nano nets MCP server, and what's possible with it?

The Nano nets MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Nano nets account. It provides structured and secure access to your intelligent document processing tools, so your agent can create, manage, and train OCR models, extract data from documents, and automate document workflows on your behalf.

  • Automated document data extraction: Let your agent process unstructured documents and pull out structured data using Nano nets' powerful AI-driven OCR models.
  • OCR model management: Easily create, update, and delete OCR models, allowing your agent to adjust to changing document types and business needs.
  • Workflow and document handling: Enable your agent to list, track, and manage documents within workflows, so you can monitor processing status and outcomes efficiently.
  • Training image uploads and model improvement: Have your agent upload new training images to OCR models, continually improving accuracy and adapting to new document formats.
  • Comprehensive model insights: Retrieve detailed information about your OCR models and their prediction files, empowering your agent to audit, debug, or optimize model performance as needed.

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

Create Model

Create a new OCR model with a list of categories or fields to extract, before uploading training images.

Delete OCR Model

Permanently deletes an OCR model from Nanonets.

Get All Models

Retrieve image classification models in the user's NanoNets account, including available model details and categories.

Get All Prediction Files

Retrieve a page of OCR prediction files for a Nanonets model, with available prediction details such as extracted text and field values.

Get OCR Model Details

Tool to retrieve details of an OCR model.

Get OCR Training Images

Retrieve a page of training images associated with an OCR model for inspection before training or analysis.

Get Workflows

Retrieve the workflows in a Nanonets account to inventory or inspect their configurations.

List Workflow Documents

Retrieve a paginated list of documents processed by a NanoNets workflow, with basic metadata, processing status, verification status, and page information.

Update Model AI Guidelines

Update AI Agent guidelines for an OCR model.

Upload Training Images by File

Tool to upload a training image file to a specified OCR model.

Upload Training Images by URL

Upload one or more publicly accessible image URLs to a specified Nanonets OCR model for training.

FRAMEWORKS

How to build Nano nets MCP Agent with another framework

Claude Code logo

Claude Code

Use Nano nets MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Nano nets MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Nano nets MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Nano nets MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Nano nets MCP with Grok Bot

Codex logo

Codex

Use Nano nets MCP with Codex

OpenClaw logo

OpenClaw

Use Nano nets MCP with OpenClaw

Hermes logo

Hermes

Use Nano nets MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Nano nets MCP with Atomic Agent

Google ADK logo

Google ADK

Use Nano nets MCP with Google ADK

LangChain logo

LangChain

Use Nano nets MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Nano nets MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Nano nets MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Nano nets MCP with LlamaIndex

CrewAI logo

CrewAI

Use Nano nets MCP with CrewAI

AutoGen logo

AutoGen

Use Nano nets MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Nano nets.It takes 30 seconds.

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

Start building