How to integrate Excel MCP with Vercel AI SDK v6

This guide walks you through connecting Excel to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Excel agent that can add sales data row to q2 table, create bar chart from revenue column, share this workbook with your manager through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Excel account through Composio's Excel MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for free Get a demo

Excel

Oauth2S2s Oauth2

Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.

54 Tools

Managed auth

Connect Excel without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

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

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

Also integrate Excel with

ChatGPT OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenCode Cursor VS Code OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Excel integration
Using Composio's Tool Router to dynamically load and access Excel 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 Excel MCP server, and what's possible with it?

The Excel MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Excel account. It provides structured and secure access to your spreadsheets, so your agent can perform actions like adding data, creating tables, managing worksheets, generating charts, and sharing workbooks on your behalf.

Automated data entry and updates: Let your agent add rows, columns, or clear specific ranges in any worksheet—keeping your data fresh, organized, and accurate.
Effortless table and worksheet management: Direct your agent to create tables, add new worksheets, or organize data structures for seamless tracking and reporting.
Dynamic chart generation: Have your agent visualize your data instantly by adding charts to any worksheet for quick insights and analysis.
Advanced filtering and sorting: Ask your agent to apply filters or custom sorts to tables, making it easy to focus on what matters most in your datasets.
Secure sharing and permission control: Empower your agent to grant access or update permissions on workbooks, ensuring your team can collaborate safely and efficiently.

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:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS

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 { 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: ["excel"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Excel 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 Excel-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 Excel 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 excel, 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 Excel 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 Excel 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: ["excel"],
  });

  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 excel, 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 Excel 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

Supported Tools

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

Add Chart

Add a chart to a worksheet using Microsoft Graph API.

Add SharePoint Worksheet

Add a new worksheet to a SharePoint Excel workbook using Microsoft Graph Sites API.

Add Table

Create a new table in a worksheet using the Microsoft Graph API.

Add Table Column

Add a column to a table using Microsoft Graph API.

Add Table Row

Add a row to a table using Microsoft Graph API.

Add Workbook Permission

Tool to grant access to a workbook via invite.

Add Worksheet

Add a new worksheet to an Excel workbook using Microsoft Graph API.

Apply Table Filter

Apply a filter to a table column using Microsoft Graph API.

Apply Table Sort

Apply a sort to a table using Microsoft Graph API.

Clear Range

Tool to clear values, formats, or contents in a specified worksheet range.

Clear Table Filter

Clear a filter from a table column using Microsoft Graph API.

Close Excel Session

Tool to close an existing Excel workbook session.

Convert Table To Range

Convert a table to a range using Microsoft Graph API.

Create Workbook

Tool to create a new Excel workbook file at a specified drive path.

Delete Table Column

Delete a column from a table using Microsoft Graph API.

Delete Table Row

Delete a row from a table using Microsoft Graph API.

Delete Worksheet

Tool to delete a worksheet from the workbook.

Export Workbook to PDF

Tool to export an Excel workbook to PDF via Microsoft Graph's format conversion.

Get Chart Axis

Tool to retrieve a specific axis from a chart.

Get Chart Data Labels

Tool to retrieve the data labels object of a chart.

Get Chart Legend

Tool to retrieve the legend object of a chart.

Get Range

Get a range from a worksheet using Microsoft Graph API.

Create Excel Session

Create a session for an Excel workbook using Microsoft Graph API.

Get SharePoint Range

Get a range from a worksheet in SharePoint using Microsoft Graph Sites API.

Get SharePoint Worksheet

Get a worksheet by name or ID from a SharePoint Excel workbook using Microsoft Graph Sites API.

Get table column

Tool to retrieve a specific column from a workbook table.

Get workbook

Tool to retrieve the properties and relationships of a workbook.

Get Worksheet

Get a worksheet by name or ID from an Excel workbook using Microsoft Graph API.

Get Worksheet Used Range

Tool to retrieve a worksheet's used range (active data region) without specifying a fixed range address.

Insert Range

Tool to insert a new cell range into a worksheet, shifting existing cells down or right.

List Charts

List charts in a worksheet using Microsoft Graph API.

List Chart Series

Tool to list all data series in a chart.

List Comments

Tool to list comments in an Excel workbook.

List Drive Item Children

Tool to list immediate children (files/folders) of a folder DriveItem using driveId and itemId.

List Drive Files

List files and folders in a drive root or specified path.

List Named Items

List named items in a workbook using Microsoft Graph API.

List SharePoint Tables

List tables in a SharePoint worksheet using Microsoft Graph Sites API.

List SharePoint Worksheets

List worksheets in an Excel workbook stored in SharePoint using Microsoft Graph Sites API.

List Table Columns

List columns in a table using Microsoft Graph API.

List Table Rows

List rows in a table using Microsoft Graph API.

List Tables

List tables in a worksheet using Microsoft Graph API.

List Workbook Permissions

Tool to list permissions set on the workbook file.

List Worksheets

List worksheets in an Excel workbook using Microsoft Graph API.

Merge Cells

Merge cells in a worksheet range using Microsoft Graph API.

Protect Worksheet

Tool to protect a worksheet using optional protection options.

Search Drive Files

Tool to search OneDrive drive items by query to discover Excel workbook IDs.

Sort Range

Sort a range in a worksheet using Microsoft Graph API.

Update Chart

Update a chart in a worksheet using Microsoft Graph API.

Update Chart Legend

Tool to update formatting or position of a chart legend.

Update Range

Update a range in a worksheet using Microsoft Graph API.

Update SharePoint Range

Update a range in a SharePoint worksheet using Microsoft Graph Sites API.

Update Table

Update a table in a workbook using Microsoft Graph API.

Update Worksheet

Update worksheet properties (name, position) in an Excel workbook using Microsoft Graph API.

Upload Workbook from URL

Tool to upload an external Excel file from a URL into OneDrive/SharePoint.

FRAMEWORKS

How to build Excel MCP Agent with another framework

ChatGPT

Use Excel MCP with ChatGPT

OpenAI Agents SDK

Use Excel MCP with OpenAI Agents SDK

Claude Agent SDK

Use Excel MCP with Claude Agent SDK

Claude Code

Use Excel MCP with Claude Code

Claude Cowork

Use Excel MCP with Claude Cowork

Codex

Use Excel MCP with Codex

Cursor

Use Excel MCP with Cursor

OpenClaw

Use Excel MCP with OpenClaw

Hermes

Use Excel MCP with Hermes

CLI

Use Excel MCP with CLI

Google ADK

Use Excel MCP with Google ADK

LangChain

Use Excel MCP with LangChain

Mastra AI

Use Excel MCP with Mastra AI

LlamaIndex

Use Excel MCP with LlamaIndex

CrewAI

Use Excel MCP with CrewAI

OpenCode

Use Excel MCP with OpenCode

VS Code

Use Excel MCP with VS Code

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

21risk

Api Key

21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.

Abstract

Api Key

Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.

Addressfinder

Api Key

Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.

Agentql

Api Key

Agentql is a toolkit that connects AI agents to the web using a specialized query language. It enables structured web interaction and data extraction for smarter automations.

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Excel 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 Excel data and credentials are handled as safely as possible.

Start with Excel.It takes 30 seconds.

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

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

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

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

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

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

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

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

Co-Founder, Ingram Technologies

How to integrate Excel MCP with Vercel AI SDK v6

Connect Excel without auth hassles

Introduction

Also integrate Excel with

TL;DR

What is Vercel AI SDK?

What is the Excel MCP server, and what's possible with it?

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

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

Complete Code

Conclusion

Supported Tools

How to build Excel MCP Agent with another framework

ChatGPT

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

Cursor

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

OpenCode

VS Code

Explore Other Toolkits

21risk

Abstract

Addressfinder

Agentql

Frequently asked questions

What are the differences in Tool Router MCP and Excel MCP?+

Can I use Tool Router MCP with Vercel AI SDK v6?+

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

How safe is my data with Composio Tool Router?+

Start with Excel.It takes 30 seconds.

Teams ship real agents on Composio