SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Ocr web service MCP with Pydantic AI

Connect Pydantic AI to Ocr web service MCP. Extract text from uploaded invoice image, check remaining ocr pages on your account, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Ocr web service logoOcr web service
Basic

Ocr web service provides powerful REST and SOAP APIs for Optical Character Recognition (OCR). Instantly convert images and scanned documents into searchable, editable text.

4 Tools

Introduction

This guide walks you through connecting Ocr web service to Pydantic AI using the Composio tool router. By the end, you'll have a working Ocr web service agent that can extract text from images and scanned documents with OCR, check your account details, and review processing logs through natural language commands.

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

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

Also integrate Ocr web service with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic 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 Ocr web service
  • 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 Ocr web service 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 Ocr web service MCP server, and what's possible with it?

The Ocr web service MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ocr web service account. It provides structured and secure access to your OCR operations, allowing your agent to process images, extract text, review account usage, and monitor processing logs automatically on your behalf.

  • Automated image-to-text recognition: Instantly have your agent perform OCR on uploaded images or documents and retrieve extracted text, including advanced output like word coordinates and formatted files.
  • Account usage monitoring: Let your agent fetch current subscription details, check remaining page credits, and stay on top of plan expiration dates for seamless workflow continuity.
  • Processing log retrieval: Ask your agent to pull detailed OCR processing logs for specific date ranges, making it easy to audit, troubleshoot, or analyze past conversions.
  • Credential and connection management: Have your agent securely extract and verify connection credentials from metadata whenever needed, ensuring safe and reliable access to OCR services.

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

Get Account Credentials

Extract OCRWebService username and license code from a quoted Basic Auth --user credential in the connection metadata.

Get Account Information

Retrieve OCRWebService account information including remaining pages, subscription plan, and expiration date.

OCR Web Service Log

Retrieve OCR processing logs for an account and date range as a single string.

OCRWebService Recognize

Tool to call SOAP Recognize operation.

FRAMEWORKS

How to build Ocr web service MCP Agent with another framework

Claude Code logo

Claude Code

Use Ocr web service MCP with Claude Code

Cursor logo

Cursor

Use Ocr web service MCP with Cursor

ChatGPT logo

ChatGPT

Use Ocr web service MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Ocr web service MCP with Claude Cowork

Antigravity logo

Antigravity

Use Ocr web service MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ocr web service MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ocr web service MCP with Claude Agent SDK

Codex logo

Codex

Use Ocr web service MCP with Codex

Grok Build logo

Grok Build

Use Ocr web service MCP with Grok Build

VS Code logo

VS Code

Use Ocr web service MCP with VS Code

OpenCode logo

OpenCode

Use Ocr web service MCP with OpenCode

OpenClaw logo

OpenClaw

Use Ocr web service MCP with OpenClaw

Hermes logo

Hermes

Use Ocr web service MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Ocr web service MCP with Atomic Agent

Google ADK logo

Google ADK

Use Ocr web service MCP with Google ADK

LangChain logo

LangChain

Use Ocr web service MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Ocr web service MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Ocr web service MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ocr web service MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ocr web service MCP with CrewAI

AutoGen logo

AutoGen

Use Ocr web service MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Ocr web service.It takes 30 seconds.

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

Start building