How to integrate One drive MCP with Pydantic AI

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

One drive logo
Pydantic AI logo
divider

Introduction

This guide walks you through connecting One drive to Pydantic AI using the Composio tool router. By the end, you'll have a working One drive agent that can share project folder with your team, download the latest version of report.docx, check who can access budget.xlsx through natural language commands.

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

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

Also integrate One drive with

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 One drive
  • 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 One drive 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 One drive MCP server, and what's possible with it?

The One drive MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your OneDrive account. It provides structured and secure access to your cloud files and folders, so your agent can perform actions like uploading documents, sharing files, managing storage, and retrieving version histories on your behalf.

  • File and folder management: Effortlessly copy, move, or delete files and folders, keeping your OneDrive organized with just a prompt.
  • Easy sharing and collaboration: Instantly generate secure sharing links for documents or folders, making collaboration with others seamless.
  • File download and preview: Have your agent fetch files or retrieve visual thumbnails for quick previews and streamlined access.
  • Access control and permissions review: Check who can view or edit any file or folder, and manage sharing permissions without manual clicks.
  • Version tracking and quota monitoring: Retrieve version histories for files and monitor your storage quota to stay on top of changes and space usage.

Supported Tools & Triggers

Tools
Triggers
Check In Drive ItemTool to check in a checked out driveItem resource, making the version of the document available to others.
Checkout Drive ItemTool to check out a driveItem to prevent others from editing it and make your changes invisible until checked in.
Copy ItemTool to copy a DriveItem (file or folder) to a new location asynchronously.
Create Drive Item PermissionTool to create a new permission on a OneDrive drive item.
Create Sharing LinkTool to create a sharing link for a DriveItem (file or folder) by its unique ID.
Delete ItemTool to delete a DriveItem (file or folder) by its unique ID from the authenticated user's OneDrive.
Permanently Delete Drive ItemTool to permanently delete a driveItem by its ID without moving it to the recycle bin.
Delete Drive Item PermissionTool to delete a permission from a drive item.
Delete Shares PermissionTool to delete the permission navigation property for a shared drive item.
Discard CheckoutTool to discard the checkout of a driveItem, releasing it and discarding any changes made while checked out.
Download a fileDownloads a file from a user's OneDrive using its item ID, which must refer to a file and not a folder.
Download file by pathDownloads the contents of a file from OneDrive by its path.
Download item as formatTool to download the contents of a driveItem converted to a specific format (e.
Download Drive Item Version ContentTool to download the contents of a specific previous version of a drive item (file).
Follow Drive ItemTool to follow a driveItem (file or folder) in OneDrive or SharePoint.
Get DriveRetrieves the properties and relationships of a Drive resource by its unique ID.
Get DriveItem by Sharing URLTool to resolve a OneDrive/SharePoint sharing URL (or shareId) to a DriveItem with driveId and itemId.
Get Drives FollowingTool to retrieve a specific followed driveItem from a drive.
Get Group DriveTool to retrieve the document library (drive) for a Microsoft 365 group.
Get Item MetadataRetrieves the metadata of a DriveItem by its unique ID.
Get Item PermissionsRetrieves the permissions of a DriveItem by its unique ID within a specific Drive.
Get Item ThumbnailsTool to retrieve the thumbnails associated with a DriveItem.
Get Item VersionsTool to retrieve the version history of a DriveItem by its unique ID.
Get Recent ItemsGet files and folders recently accessed by the user.
Get Drive Root FolderTool to retrieve metadata for the root folder of the signed-in user's OneDrive.
Get Shared Item by ShareIdTool to access a shared DriveItem or collection of shared items using a shareId or encoded sharing URL.
Get Shared ItemsTool to retrieve items shared with the authenticated user (not items the user has shared with others).
Get SharePoint List ItemsTool to get the items (list items) within a specific SharePoint list on a site.
Get Site DetailsRetrieves metadata for a specific SharePoint site by its ID.
Get SharePoint Site Page ContentGets the content of a modern SharePoint site page.
Get Drive Special FolderTool to retrieve a special folder in OneDrive by name.
Grant Shares PermissionTool to grant users access to a link represented by a permission using an encoded sharing URL.
Invite User to Drive ItemTool to invite users or grant permissions to a specific item in a OneDrive drive.
List Drive ActivitiesTool to retrieve recent activities on the authenticated user's OneDrive.
List Drive BundlesTool to retrieve a list of bundle resources from a specified drive.
List DrivesTool to retrieve a list of Drive resources available to the authenticated user, or for a specific user, group, or site.
List Folder ChildrenList the direct children (files/folders) of a OneDrive/SharePoint folder by DriveItem ID or path.
List Drive Item ActivitiesTool to list recent activities for a specific item in a OneDrive drive.
List Root Drive ChangesTool to list changes in the root of the user's primary drive using a delta token.
List Shares PermissionTool to retrieve permission details for a shared OneDrive or SharePoint item using a share ID.
List SharePoint List Items DeltaTool to track changes to items in a SharePoint list using a delta query.
List Site ColumnsTool to list all column definitions for a SharePoint site.
List Site Drive Items DeltaTool to track changes to DriveItems in the default document library of a SharePoint site.
List Site ListsTool to list all lists under a specific SharePoint site.
List Site SubsitesTool to list all subsites of a SharePoint site.
List SubscriptionsTool to list the current subscriptions for the authenticated user or app.
Move ItemTool to move a file or folder to a new parent folder in OneDrive.
Create folderCreates a new folder in the user's OneDrive, automatically renaming on conflict, optionally within a specified parent_folder (by ID or full path from root) which, if not the root, must exist and be accessible.
Create a new text fileCreates a new plain-text file with specified content in the authenticated user's personal OneDrive, using either the folder's unique ID or its absolute path relative to the user's OneDrive root (paths are automatically resolved to IDs); note that OneDrive may rename or create a new version if the filename already exists.
Find ItemNon-recursively finds an item (file or folder) in a specified OneDrive folder; if `folder` is provided as a path, it must actually exist.
Find FolderFinds folders by name within an accessible parent folder in OneDrive, or lists all its direct child folders if no name is specified.
List OneDrive itemsRetrieves all files and folders as `driveItem` resources from the root of a specified user's OneDrive, automatically handling pagination.
Upload fileUploads a file to a specified OneDrive folder, automatically creating the destination folder if it doesn't exist, renaming on conflict, and supporting large files via chunking.
Preview Drive ItemGenerates or retrieves a short-lived, permission-bound embeddable URL for a preview of a specific item.
Restore Deleted ItemTool to restore a deleted OneDrive driveItem (file or folder) from the recycle bin.
Search ItemsSearch OneDrive for files and folders by keyword.
Delete Drive FollowingTool to unfollow a driveItem by removing it from the user's followed items collection.
Update Drive Item MetadataTool to update the metadata of a specific item (file or folder) in OneDrive.
Update Drive Item PermissionsTool to update the roles of an existing permission on a OneDrive drive item.
Update File ContentTool to create an upload session for updating an existing file's content in OneDrive.

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

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

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.

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 One drive
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

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

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 One drive
  • MCPServerStreamableHTTP connects to the One drive MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

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 One drive
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["one_drive"],
    )
    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 One drive 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

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
one_drive_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[one_drive_mcp],
    instructions=(
        "You are a One drive assistant. Use One drive tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the One drive endpoint
  • The agent uses GPT-5 to interpret user commands and perform One drive operations
  • The instructions field defines the agent's role and behavior

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 One drive.\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
  • One drive API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

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 One drive 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 One drive
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["one_drive"],
    )
    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
    one_drive_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[one_drive_mcp],
        instructions=(
            "You are a One drive assistant. Use One drive 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 One drive.\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 One drive through Composio's Tool Router. With this setup, your agent can perform real One drive 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 + One drive for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build One drive MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and One drive MCP?

With a standalone One drive MCP server, the agents and LLMs can only access a fixed set of One drive tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from One drive and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Pydantic AI?

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 One drive tools.

Can I manage the permissions and scopes for One drive while using Tool Router?

Yes, absolutely. You can configure which One drive 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.

How safe is my data with Composio Tool Router?

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 One drive data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.