How to integrate Outlook MCP with Vercel AI SDK

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

Introduction

This guide walks you through connecting Outlook to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Outlook agent that can download latest attachments from my inbox, create new calendar for project deadlines, add rule to move newsletters to folder, get my current automatic reply settings through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Outlook account through Composio's Outlook 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 Outlook integration
  • Using Composio's Tool Router to dynamically load and access Outlook 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 Outlook MCP server, and what's possible with it?

The Outlook MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Outlook account. It provides structured and secure access to your email, calendar, and contacts, so your agent can perform actions like sending emails, organizing folders, managing your calendar, and handling attachments on your behalf.

  • Email organization and folder management: Let your agent create, delete, or organize mail folders to keep your inbox tidy and efficient.
  • Calendar and event creation: Easily have your agent set up new calendars, so you can organize meetings and events without lifting a finger.
  • Smart attachments handling: Automatically download files from your emails or add attachments to outgoing messages for seamless file management.
  • Automated rules and filtering: Direct your agent to create email rules that filter, sort, or take action on messages as they arrive.
  • Contact and category organization: Ask your agent to create new contact folders or master categories to streamline how you manage people and projects.

Supported Tools & Triggers

Tools
Triggers
Add mail attachmentTool to add an attachment to an email message.
Create calendarTool to create a new calendar in the signed-in user's mailbox.
Create contact folderTool to create a new contact folder in the user's mailbox.
Create Email RuleCreate email rule filter with conditions and actions
Create mail folderTool to create a new mail folder.
Create master categoryTool to create a new category in the user's master category list.
Delete mail folderDelete a mail folder from the user's mailbox.
Download Outlook attachmentDownloads a specific file attachment from an email message in a microsoft outlook mailbox; the attachment must contain 'contentbytes' (binary data) and not be a link or embedded item.
Get mailbox settingsTool to retrieve mailbox settings.
Get mail deltaTool to retrieve incremental changes (delta) of messages in a mailbox.
Get mail tipsTool to retrieve mail tips such as automatic replies and mailbox full status.
Get master categoriesTool to retrieve the user's master category list.
Get supported languagesTool to retrieve supported languages in the user's mailbox.
Get supported time zonesTool to retrieve supported time zones in the user's mailbox.
List Outlook calendarsTool to list calendars in the signed-in user's mailbox.
List event attachmentsTool to list attachments for a specific outlook calendar event.
List Outlook attachmentsLists metadata (like name, size, and type, but not `contentbytes`) for all attachments of a specified outlook email message.
List event remindersTool to retrieve reminders for events occurring within a specified time range.
Add event attachmentAdds an attachment to a specific outlook calendar event.
Create Calendar EventCreates a new outlook calendar event, ensuring `start datetime` is chronologically before `end datetime`.
Create contactCreates a new contact in a microsoft outlook user's contacts folder.
Create email draftCreates an outlook email draft with subject, body, recipients, and an optional attachment.
Create a draft replyCreates a draft reply in the specified user's outlook mailbox to an existing message (identified by a valid `message id`), optionally including a `comment` and cc/bcc recipients.
Delete ContactPermanently deletes an existing contact, using its `contact id` (obtainable via 'list user contacts' or 'get contact'), from the outlook contacts of the user specified by `user id`.
Delete Calendar EventDeletes an existing calendar event, identified by its unique `event id`, from a specified user's microsoft outlook calendar, with an option to send cancellation notifications to attendees.
Get contactRetrieves a specific outlook contact by its `contact id` from the contacts of a specified `user id` (defaults to 'me' for the authenticated user).
Get contact foldersTool to retrieve a list of contact folders in the signed-in user's mailbox.
Get calendar eventRetrieves the full details of a specific calendar event by its id from a user's outlook calendar, provided the event exists.
Get email messageRetrieves a specific email message by its id from the specified user's outlook mailbox.
Get Outlook profileRetrieves the microsoft outlook profile for a specified user.
Get scheduleRetrieves free/busy schedule information for specified email addresses within a defined time window.
List Outlook contactsRetrieves a user's microsoft outlook contacts, from the default or a specified contact folder.
List eventsRetrieves events from a user's outlook calendar via microsoft graph api, supporting pagination, filtering, property selection, sorting, and timezone specification.
List mail foldersTool to list a user's top-level mail folders.
List MessagesRetrieves a list of email messages from a specified mail folder in an outlook mailbox, with options for filtering (including by conversationid to get all messages in a thread), pagination, and sorting; ensure 'user id' and 'folder' are valid, and all date/time strings are in iso 8601 format.
Move message to folderMove a message to another folder within the specified user's mailbox.
Reply to EmailSends a plain text reply to an outlook email message, identified by `message id`, allowing optional cc and bcc recipients.
Search Outlook messagesSearches messages in a microsoft 365 or enterprise outlook account mailbox, supporting filters for sender, subject, attachments, pagination, and sorting by relevance or date.
Send emailSends an email with subject, body, recipients, and an optional attachment via microsoft graph api; attachments require a non-empty file with valid name and mimetype.
Update calendar eventUpdates specified fields of an existing outlook calendar event.
Update ContactUpdates an existing outlook contact, identified by `contact id` for the specified `user id`, requiring at least one other field to be modified.
Update email messageUpdates specified properties of an existing email message; `message id` must identify a valid message within the specified `user id`'s mailbox.
Update mailbox settingsTool to update mailbox settings for the signed-in user.

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: ["outlook"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Outlook 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 Outlook-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 Outlook 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 outlook, 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 Outlook 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 Outlook 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: ["outlook"],
  });

  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 outlook, 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 Outlook 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 Outlook MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Outlook MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Outlook MCP with Claude Agent SDK

Google ADK

Google ADK

Use Outlook MCP with Google ADK

LangChain

LangChain

Use Outlook MCP with LangChain

Mastra AI

Mastra AI

Use Outlook MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Outlook MCP with LlamaIndex

CrewAI

CrewAI

Use Outlook MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Outlook MCP?

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

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

Yes, absolutely. You can configure which Outlook 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 Outlook 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