How to integrate One drive MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
One drive Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting One drive to Vercel AI SDK using the Composio tool router. By the end, you'll have a working One drive agent that can share project folder with my team, download the latest version of report.docx, check who can access budget.xlsx, list my remaining onedrive storage space 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.

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
  • Step Counting: Control multi-step tool execution
  • 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.

Supported Tools & Triggers

Tools
Triggers
Copy ItemTool to copy a driveitem (file or folder) to a new location asynchronously.
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.
Download a fileDownloads a file from a user's onedrive using its item id, which must refer to a file and not a folder.
Get DriveRetrieves the properties and relationships of a drive resource by its unique id.
Get Item MetadataRetrieves the metadata of a driveitem by its unique id.
Get Item PermissionsRetrieves the permissions of a driveitem by its unique id or path 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 Drive QuotaTool to retrieve the quota information for the authenticated user's onedrive.
Get Recent ItemsRetrieves a list of items that have been recently used by the authenticated user.
Get Shared ItemsTool to retrieve a list of items that have been shared with the authenticated user.
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.
Invite User to Drive ItemTool to invite users or grant permissions to a specific item in a onedrive drive.
List Drive Item ActivitiesTool to list recent activities for a specific item in a onedrive drive.
List DrivesTool to retrieve a list of drive resources available to the authenticated user, or for a specific user, group, or site.
List Root Drive ChangesTool to list changes in the root of the user's primary drive using a delta token.
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 text file with specified content in a onedrive folder, using either the folder's unique id or its absolute path (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 renaming on conflict and supporting large files via chunking.
Preview Drive ItemGenerates or retrieves a short-lived embeddable url for a preview of a specific item.
Search ItemsSearches for driveitems in onedrive that match the specified query.
Update Drive Item MetadataTool to update the metadata of a specific item (file or folder) in onedrive.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

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

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 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

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

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 { experimental_createMCPClient as 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

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

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

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

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 { experimental_createMCPClient as 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.

How to build One drive MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use One drive MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use One drive MCP with Claude Agent SDK

Google ADK

Google ADK

Use One drive MCP with Google ADK

LangChain

LangChain

Use One drive MCP with LangChain

Mastra AI

Mastra AI

Use One drive MCP with Mastra AI

LlamaIndex

LlamaIndex

Use One drive MCP with LlamaIndex

CrewAI

CrewAI

Use One drive MCP with CrewAI

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 Vercel AI SDK?

Yes, you can. Vercel AI SDK 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
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
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.

Book a call↗Get started for free