How to integrate One drive MCP with Vercel AI SDK v6

This guide walks you through connecting One drive to Vercel AI SDK v6 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 Vercel AI SDK 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.

Get started for freeGet a demo
One drive logoOne drive
Oauth2S2s Oauth2

OneDrive is Microsoft’s cloud storage for storing, syncing, and sharing files across devices. Access your files securely anywhere with real-time collaboration and offline support.

60 Tools9 Triggers

Introduction

This guide walks you through connecting One drive to Vercel AI SDK v6 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 Vercel AI SDK 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

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with One drive integration
  • Using Composio's Tool Router to dynamically load and access One drive tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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.

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 you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
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 required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["one_drive"],
  });

  const mcpUrl = session.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 mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all One drive-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available One drive tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to one_drive, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use One drive tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with One drive and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["one_drive"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to one_drive, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a One drive agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS & TRIGGERS

Supported Tools and Triggers

Every One drive action and event your agent gets out of the box.

Check In Drive Item

Tool to check in a checked out driveItem resource, making the version of the document available to others.

Checkout Drive Item

Tool to check out a driveItem to prevent others from editing it and make your changes invisible until checked in.

Copy Item

Tool to copy a DriveItem (file or folder) to a new location asynchronously.

Create Drive Item Permission

Tool to create a new permission on a OneDrive drive item.

Create Sharing Link

Tool to create a sharing link for a DriveItem (file or folder) by its unique ID.

Delete Item

Tool to delete a DriveItem (file or folder) by its unique ID from the authenticated user's OneDrive.

Permanently Delete Drive Item

Tool to permanently delete a driveItem by its ID without moving it to the recycle bin.

Delete Drive Item Permission

Tool to delete a permission from a drive item.

Delete Shares Permission

Tool to delete the permission navigation property for a shared drive item.

Discard Checkout

Tool to discard the checkout of a driveItem, releasing it and discarding any changes made while checked out.

Download a file

Downloads a file from a user's OneDrive using its item ID, which must refer to a file and not a folder.

Download file by path

Downloads the contents of a file from OneDrive by its path.

Download item as format

Tool to download the contents of a driveItem converted to a specific format (e.

Download Drive Item Version Content

Tool to download the contents of a specific previous version of a drive item (file).

Follow Drive Item

Tool to follow a driveItem (file or folder) in OneDrive or SharePoint.

Get Drive

Retrieves the properties and relationships of a Drive resource by its unique ID.

Get DriveItem by Sharing URL

Tool to resolve a OneDrive/SharePoint sharing URL (or shareId) to a DriveItem with driveId and itemId.

Get Drives Following

Tool to retrieve a specific followed driveItem from a drive.

Get Group Drive

Tool to retrieve the document library (drive) for a Microsoft 365 group.

Get Item Metadata

Retrieves the metadata of a DriveItem by its unique ID.

Get Item Permissions

Retrieves the permissions of a DriveItem by its unique ID within a specific Drive.

Get Item Thumbnails

Tool to retrieve the thumbnails associated with a DriveItem.

Get Item Versions

Tool to retrieve the version history of a DriveItem by its unique ID.

Get Recent Items

Get files and folders recently accessed by the user.

Get Drive Root Folder

Tool to retrieve metadata for the root folder of the signed-in user's OneDrive.

Get Shared Item by ShareId

Tool to access a shared DriveItem or collection of shared items using a shareId or encoded sharing URL.

Get Shared Items

Tool to retrieve items shared with the authenticated user (not items the user has shared with others).

Get SharePoint List Items

Tool to get the items (list items) within a specific SharePoint list on a site.

Get Site Details

Retrieves metadata for a specific SharePoint site by its ID.

Get SharePoint Site Page Content

Gets the content of a modern SharePoint site page.

Get Drive Special Folder

Tool to retrieve a special folder in OneDrive by name.

Grant Shares Permission

Tool to grant users access to a link represented by a permission using an encoded sharing URL.

Invite User to Drive Item

Tool to invite users or grant permissions to a specific item in a OneDrive drive.

List Drive Activities

Tool to retrieve recent activities on the authenticated user's OneDrive.

List Drive Bundles

Tool to retrieve a list of bundle resources from a specified drive.

List Drives

Tool to retrieve a list of Drive resources available to the authenticated user, or for a specific user, group, or site.

List Folder Children

List the direct children (files/folders) of a OneDrive/SharePoint folder by DriveItem ID or path.

List Drive Item Activities

Tool to list recent activities for a specific item in a OneDrive drive.

List Root Drive Changes

Tool to list changes in the root of the user's primary drive using a delta token.

List Shares Permission

Tool to retrieve permission details for a shared OneDrive or SharePoint item using a share ID.

List SharePoint List Items Delta

Tool to track changes to items in a SharePoint list using a delta query.

List Site Columns

Tool to list all column definitions for a SharePoint site.

List Site Drive Items Delta

Tool to track changes to DriveItems in the default document library of a SharePoint site.

List Site Lists

Tool to list all lists under a specific SharePoint site.

List Site Subsites

Tool to list all subsites of a SharePoint site.

List Subscriptions

Tool to list the current subscriptions for the authenticated user or app.

Move Item

Tool to move a file or folder to a new parent folder in OneDrive.

Create folder

Creates 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 file

Creates 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 Item

Non-recursively finds an item (file or folder) in a specified OneDrive folder; if `folder` is provided as a path, it must actually exist.

Find Folder

Finds folders by name within an accessible parent folder in OneDrive, or lists all its direct child folders if no name is specified.

List OneDrive items

Retrieves all files and folders as `driveItem` resources from the root of a specified user's OneDrive, automatically handling pagination.

Upload file

Uploads 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 Item

Generates or retrieves a short-lived, permission-bound embeddable URL for a preview of a specific item.

Restore Deleted Item

Tool to restore a deleted OneDrive driveItem (file or folder) from the recycle bin.

Search Items

Search OneDrive for files and folders by keyword.

Delete Drive Following

Tool to unfollow a driveItem by removing it from the user's followed items collection.

Update Drive Item Metadata

Tool to update the metadata of a specific item (file or folder) in OneDrive.

Update Drive Item Permissions

Tool to update the roles of an existing permission on a OneDrive drive item.

Update File Content

Tool to create an upload session for updating an existing file's content in OneDrive.

FRAMEWORKS

How to build One drive MCP Agent with another framework

ChatGPT logo

ChatGPT

Use One drive MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use One drive MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use One drive MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use One drive MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use One drive MCP with Claude Cowork

Codex logo

Codex

Use One drive MCP with Codex

Cursor logo

Cursor

Use One drive MCP with Cursor

OpenClaw logo

OpenClaw

Use One drive MCP with OpenClaw

Hermes logo

Hermes

Use One drive MCP with Hermes

CLI logo

CLI

Use One drive MCP with CLI

Google ADK logo

Google ADK

Use One drive MCP with Google ADK

LangChain logo

LangChain

Use One drive MCP with LangChain

Mastra AI logo

Mastra AI

Use One drive MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use One drive MCP with LlamaIndex

CrewAI logo

CrewAI

Use One drive MCP with CrewAI

OpenCode logo

OpenCode

Use One drive MCP with OpenCode

VS Code logo

VS Code

Use One drive MCP with VS Code

FAQ

Frequently asked questions

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.

Yes, you can. Vercel AI SDK v6 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.

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.

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.

Start with One drive.It takes 30 seconds.

Managed auth, hosted MCP servers, and every One drive 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