How to integrate Google Sheets MCP with Vercel AI SDK

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

Introduction

This guide walks you through connecting Google Sheets to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Google Sheets agent that can add a new sheet named 'q3 sales', update all rows where status is 'pending', create a pie chart of expenses by category, clear values in the 'drafts' worksheet through natural language commands.

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

The Google Sheets MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Sheets account. It provides structured and secure access to your spreadsheets, so your agent can perform actions like creating new sheets, updating data, generating charts, and automating spreadsheet workflows on your behalf.

  • Spreadsheet creation and management: Instantly create new Google Sheets and add new worksheets (tabs) to existing spreadsheets whenever you need extra space or organization.
  • Bulk data reading and updating: Retrieve specific data ranges, aggregate column data, or update multiple rows and cells at once—perfect for reporting or syncing external data.
  • Automated chart generation: Direct your agent to build charts from selected data, making visualization and analysis faster and easier right inside your sheets.
  • Smart filtering and data cleanup: Have the agent clear filters, remove cell contents, or append rows and columns to keep your sheets tidy and up to date.
  • Dynamic data manipulation: Use advanced features like batch updates with data filters and aggregate operations to transform, filter, or summarize spreadsheet data efficiently.

Supported Tools & Triggers

Tools
Triggers
Add Sheet to SpreadsheetAdds a new sheet (worksheet) to a spreadsheet.
Aggregate Column DataSearches for rows where a specific column matches a value and performs mathematical operations on data from another column.
Append DimensionTool to append new rows or columns to a sheet, increasing its size.
Batch get spreadsheetRetrieves data from specified cell ranges in a google spreadsheet; ensure the spreadsheet has at least one worksheet and any explicitly referenced sheet names in ranges exist.
Batch update spreadsheetUpdates a specified range in a google sheet with given values, or appends them as new rows if `first cell location` is omitted; ensure the target sheet exists and the spreadsheet contains at least one worksheet.
Batch Update Values by Data FilterTool to update values in ranges matching data filters.
Clear Basic FilterTool to clear the basic filter from a sheet.
Clear spreadsheet valuesClears cell content (preserving formatting and notes) from a specified a1 notation range in a google spreadsheet; the range must correspond to an existing sheet and cells.
Create Chart in Google SheetsCreate a chart in a google sheets spreadsheet using the specified data range and chart type.
Create a Google SheetCreates a new google spreadsheet in google drive using the provided title.
Create spreadsheet columnCreates a new column in a google spreadsheet, requiring a valid `spreadsheet id` and an existing `sheet id`; an out-of-bounds `insert index` may append/prepend the column.
Create spreadsheet rowInserts a new, empty row into a specified sheet of a google spreadsheet at a given index, optionally inheriting formatting from the row above.
Delete Dimension (Rows/Columns)Tool to delete specified rows or columns from a sheet in a google spreadsheet.
Delete SheetTool to delete a sheet (worksheet) from a spreadsheet.
Execute SQL on SpreadsheetExecute sql queries against google sheets tables.
Find worksheet by titleFinds a worksheet by its exact, case-sensitive title within a google spreadsheet; returns a boolean indicating if found and the complete metadata of the entire spreadsheet, regardless of whether the target worksheet is found.
Format cellApplies text and background cell formatting to a specified range in a google sheets worksheet.
Get sheet namesLists all worksheet names from a specified google spreadsheet (which must exist), useful for discovering sheets before further operations.
Get Spreadsheet by Data FilterReturns the spreadsheet at the given id, filtered by the specified data filters.
Get spreadsheet infoRetrieves comprehensive metadata for a google spreadsheet using its id, excluding cell data.
Get Table SchemaThis action is used to get the schema of a table in a google spreadsheet, call this action to get the schema of a table in a spreadsheet before you query the table.
Insert Dimension in Google SheetTool to insert new rows or columns into a sheet at a specified location.
List Tables in SpreadsheetThis action is used to list all tables in a google spreadsheet, call this action to get the list of tables in a spreadsheet.
Look up spreadsheet rowFinds the first row in a google spreadsheet where a cell's entire content exactly matches the query string, searching within a specified a1 notation range or the first sheet by default.
Query Spreadsheet TableThis action is used to query a table in a google spreadsheet, call this action to query a table in a spreadsheet.
Search Developer MetadataTool to search for developer metadata in a spreadsheet.
Search SpreadsheetsSearch for google spreadsheets using various filters including name, content, date ranges, and more.
Set Basic FilterTool to set a basic filter on a sheet in a google spreadsheet.
Create sheet from JSONCreates a new google spreadsheet and populates its first worksheet from `sheet json`, which must be non-empty as its first item's keys establish the headers.
Copy Sheet to Another SpreadsheetTool to copy a single sheet from a spreadsheet to another spreadsheet.
Append Values to SpreadsheetTool to append values to a spreadsheet.
Batch Clear Spreadsheet ValuesTool to clear one or more ranges of values from a spreadsheet.
Batch Clear Values By Data FilterClears one or more ranges of values from a spreadsheet using data filters.
Batch Get Spreadsheet Values by Data FilterTool to return one or more ranges of values from a spreadsheet that match the specified data filters.
Update Sheet PropertiesTool to update properties of a sheet (worksheet) within a google spreadsheet, such as its title, index, visibility, tab color, or grid properties.
Update Spreadsheet PropertiesTool to update properties of a spreadsheet, such as its title, locale, or auto-recalculation settings.

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: ["googlesheets"],
  });

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

  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 googlesheets, 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 Google Sheets 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 Google Sheets MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Google Sheets MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Google Sheets MCP with Claude Agent SDK

Google ADK

Google ADK

Use Google Sheets MCP with Google ADK

LangChain

LangChain

Use Google Sheets MCP with LangChain

Mastra AI

Mastra AI

Use Google Sheets MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Google Sheets MCP with LlamaIndex

CrewAI

CrewAI

Use Google Sheets MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Google Sheets MCP?

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

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

Yes, absolutely. You can configure which Google Sheets 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 Google Sheets 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