SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Algodocs MCP with Pydantic AI

Connect Pydantic AI to Algodocs MCP. Extract invoice totals from uploaded pdfs, pull key data fields from bank statements, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Algodocs logoAlgodocs
Api KeyBasic

Algodocs is an AI-powered platform that automates data extraction from business documents. It delivers fast, secure, and accurate processing without templates or manual training.

3 Tools

Introduction

This guide walks you through connecting Algodocs to Pydantic AI using the Composio tool router. By the end, you'll have a working Algodocs agent that can list your document extractors, browse your folders, and check your account details through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Algodocs with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic 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 Algodocs
  • 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 Algodocs 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 Algodocs MCP server, and what's possible with it?

The Algodocs MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Algodocs account. It provides structured and secure access to your user information, document data extractors, and folders, so your agent can view your account details, list available extractors, and browse your folders on your behalf.

  • Account information: Have your agent retrieve your current Algodocs user information whenever you need account context.
  • Extractor discovery: Let the agent list the document data extractors available in your Algodocs account.
  • Folder browsing: Direct your agent to list your Algodocs folders so you can see how your documents are organized.
  • Workspace overview: Instruct your agent to summarize your available extractors and folders alongside your current user information.

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

Get Current User

Tool to retrieve current user information.

List document data extractors

Tool to list document data extractors.

List folders

Tool to list folders.

FRAMEWORKS

How to build Algodocs MCP Agent with another framework

Claude Code logo

Claude Code

Use Algodocs MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Algodocs MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Algodocs MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Algodocs MCP with Claude Agent SDK

Codex logo

Codex

Use Algodocs MCP with Codex

OpenClaw logo

OpenClaw

Use Algodocs MCP with OpenClaw

Hermes logo

Hermes

Use Algodocs MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Algodocs MCP with Atomic Agent

Google ADK logo

Google ADK

Use Algodocs MCP with Google ADK

LangChain logo

LangChain

Use Algodocs MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Algodocs MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Algodocs MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Algodocs MCP with LlamaIndex

CrewAI logo

CrewAI

Use Algodocs MCP with CrewAI

AutoGen logo

AutoGen

Use Algodocs MCP with AutoGen

FAQ

Frequently asked questions

Start with Algodocs.It takes 30 seconds.

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

Start building