Gigasheet with Vercel AI SDK

How to integrate Gigasheet MCP with Vercel AI SDK v6

Trusted by

GET STARTED FOR FREE GET A DEMO

30 min · no commitment · see it on your stack

Introduction Also integrate Gigasheet with TL;DR What is Vercel AI SDK What is the Gigasheet MCP server Supported Tools & Triggers Creating MCP Server - Stand-alone vs Composio SDK Step-by-step Guide Complete Code Conclusion How to build Gigasheet MCP Agent with another framework Explore Other Toolkits FAQ

Connect Gigasheet without Auth hassles

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

Try for Free

Introduction

This guide walks you through connecting Gigasheet to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Gigasheet agent that can list all columns in your sales dataset, download export url for last week's data, apply saved filter to monthly report sheet through natural language commands.

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

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

Also integrate Gigasheet with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex 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 Gigasheet integration
Using Composio's Tool Router to dynamically load and access Gigasheet 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 Gigasheet MCP server, and what's possible with it?

The Gigasheet MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Gigasheet account. It provides structured and secure access to your big data spreadsheets, so your agent can perform actions like retrieving datasets, applying filters, exporting data, managing sheets, and integrating with connector sources on your behalf.

Dataset retrieval and inspection: Instantly fetch metadata or details for any dataset or sheet, such as column names, types, and structure, so you can quickly understand and analyze your data.
Automated data export and download: Direct your agent to initiate data exports and retrieve download links for processed datasets, streamlining big data extraction directly to your tools or workflows.
Smart filtering and template application: Apply saved filter templates to sheets or retrieve available filter templates, enabling rapid, repeatable data curation without manual setup.
Sheet and folder management: Effortlessly delete sheets or folders—including recursive deletions—so you can keep your workspace organized and clutter-free.
Connector and integration management: List and manage connector connections to keep all your external data sources in sync with Gigasheet, making data aggregation seamless and automated.

Supported Tools & Triggers

Tools

Append Rows to DatasetAppends rows to an existing Gigasheet dataset using column letters as keys.

Append Sheet from Another SheetTool to append data from a source sheet to a target sheet by matching column names.

Apply HTTP EnrichmentTool to apply generic HTTP enrichment to a Gigasheet dataset.

Calculate Enrich Expected CreditsCalculate expected credits for a user-defined HTTP enrichment operation.

Cancel HTTP Enrichment TaskTool to cancel a running enrichment task.

Check Connector Source AvailabilityTool to check if a source of the given type is available.

Combine FilesTool to combine multiple files into a new file.

Copy FileTool to copy a file in Gigasheet.

Count Dataset Deduplication ResultsTool to count how many duplicates will be removed and how many rows remain when deduplicating.

Count Dataset GroupsTool to count the number of groups matching certain criteria in a Gigasheet dataset.

Count Dataset RowsCounts rows in a Gigasheet dataset matching specified filter criteria.

Count Dataset ActivitiesTool to get total activity count on a given Gigasheet dataset.

Create AI Chat QueryAI analysis assistant for Gigasheet datasets.

Create Dataset Column CommentTool to add a comment to a column in a Gigasheet dataset.

Add Comment to CellTool to add a comment to a specific cell in a Gigasheet dataset.

Create Conditional Label ColumnTool to add a label column to a Gigasheet dataset with values based on conditional filters.

Create Formula ColumnTool to create a new column based on a formula input in a Gigasheet dataset.

Edit Formula ColumnTool to edit a formula column in a Gigasheet dataset.

Create Formula PreviewTool to calculate a formula preview on a Gigasheet dataset and return sample results with involved column values.

Create Iterator ColumnTool to add an iterator column to a Gigasheet dataset based on current filters and order.

Create Dataset LiveshareTool to create a new liveshare for a Gigasheet dataset.

Create Dataset ViewTool to create a new view for a Gigasheet dataset with a specified name and client state version.

Explode JSON ColumnTool to explode JSON data in a column into separate columns.

Create File AggregationTool to retrieve ungrouped aggregated values for a Gigasheet file.

Create Blank FileTool to create an empty file in your Gigasheet Library.

Create Files DirectoryTool to create a new folder in your Gigasheet Library.

Create Cross-File LookupCreates a cross-file lookup to enrich data by matching values between two sheets.

Send MCP Request to Sheet AssistantTool to interact with Gigasheet Sheet Assistant via the Model Context Protocol (MCP) over HTTP.

Split ColumnTool to split a column into multiple columns based on a separator.

Delete Sheet Assistant LogsTool to delete Sheet Assistant chat history for a specific sheet.

Delete columns by nameTool to delete multiple columns from a Gigasheet dataset by their column names.

Delete Connector SourceTool to delete a connector source for the authenticated user.

Delete Dataset CommentTool to delete a comment from a cell in a Gigasheet dataset.

Delete Rows Not Matching FilterDeletes rows in a Gigasheet dataset that do NOT match the specified filter criteria.

Delete Duplicated Rows from DatasetTool to delete duplicated rows from a Gigasheet dataset based on specified columns and sort model.

Delete Rows from DatasetTool to delete selected rows from a Gigasheet dataset.

Delete Rows Matching FilterTool to delete rows in a Gigasheet dataset that match a specified filter.

Delete dataset viewTool to delete a specific view from a Gigasheet dataset.

Delete dataset live shareTool to delete a live share of a Gigasheet dataset.

Delete sheet or folder by handleDeletes a Gigasheet sheet or folder by its unique handle identifier.

Delete column from sheetTool to delete a single column from a Gigasheet sheet by its column identifier.

Delete Filter TemplateTool to delete a saved filter template by its unique handle.

Delete multiple columns from fileTool to delete multiple columns from a Gigasheet file.

Filter File RowsTool to retrieve rows from a Gigasheet file matching specified filter criteria.

Generate Dataset DescriptionGenerates an AI-powered description for a Gigasheet dataset.

Get Sheet AI Chat HistoryTool to retrieve AI chat history for a sheet.

Get Cell CommentsTool to get comments for a specific cell in a Gigasheet dataset.

Get Client State Current VersionRetrieves the current client-state version and timestamp for a specified sheet.

Get Connector Connection ParametersTool to get connection parameters for a specific connector.

Get Connector Connection ParametersTool to retrieve connection parameters for a specific connector type.

Get Connector ConnectionsTool to list connector connections.

Get Connector SourcesTool to retrieve information about connected data sources for the user.

Get Connector Source ParametersTool to get parameters required for a specific connector source type.

Get Dataset Column CommentsTool to get comments for a specific column in a dataset sheet.

Get Dataset by HandleRetrieves comprehensive metadata for a specific dataset in Gigasheet.

Get Dataset ColumnsTool to list all column metadata (IDs, names, types) for a dataset.

Get Dataset Export Download URLTool to retrieve the download URL for an exported dataset.

Get Dataset Liveshare CSVTool to retrieve CSV data from a Gigasheet liveshare.

Get Dataset NoteTool to retrieve a dataset's note by handle.

Get Dataset Organization PermissionsTool to retrieve organization file permissions for a dataset.

Get Dataset Version MetadataRetrieves metadata about a dataset at a specific version.

Get Dataset ViewsTool to list all views associated with a specific dataset.

Get Dataset Operation StatusTool to get information about the last operation on a dataset.

Get Dataset ActivityTool to get the list of write actions on a given dataset sheet.

Get Dataset View MetadataTool to retrieve view metadata for a specific view within a dataset.

Get Docs Formulas FunctionsTool to retrieve all supported formula functions.

Get Enrich Task StatusTool to get status for a user-defined HTTP enrichment task.

Apply Filter Template On SheetTool to fetch a saved filter template's model for a given sheet.

Get Filter TemplatesRetrieves all saved filter templates from GigaSheet.

Get Filter Template by HandleRetrieves details of a specific saved filter template by its unique handle.

Generate New HandleTool to generate a new unique dataset handle.

Get Library FilesTool to retrieve all datasets and files in the user's Gigasheet library.

Get Library Files in DirectoryRetrieves all library files with file permissions in a given directory.

Get Library Home Page FilesTool to retrieve suggested recent files for the home page.

Get Library PathTool to retrieve the chain of parent directories for a file or folder in Gigasheet.

Get TICIntel NPI Public ProfileTool to retrieve public NPI (National Provider Identifier) profile from TICIntel database.

Get TIC Intel StatesTool to list available TIC Intel states from Gigasheet.

List Cities by StateTool to retrieve a list of cities for a given US state code from the TICIntel dataset.

List Providers by CityTool to retrieve a list of healthcare providers in a specific city and state from the TicIntel dataset.

Get User DetailsRetrieves detailed information about the authenticated user in Gigasheet.

Get User Enrichment CreditsTool to get the current user's enrichment credit information.

Get User MetadataTool to retrieve metadata for the authenticated user.

Get User Autofill SuggestionsRetrieves autofill suggestions for the authenticated user, including team members and previously used share recipients.

Get User Space UsedTool to get the amount of space used by the current user in bytes.

Get Authenticated User InfoTool to fetch the authenticated user's details.

List Billing PlansTool to list available Gigasheet billing plans.

List Dataset CommentsTool to get all comments in a dataset sheet.

List Dataset LivesharesTool to list all liveshares for a specific Gigasheet dataset.

List All DatasetsTool to retrieve all datasets owned by the user at any folder depth.

List Datasets by HandleTool to list files and datasets in a given Gigasheet location.

List Library ExportsTool to list exports owned by the current user, regardless of location.

List Shared Files by HandleTool to retrieve all files with permissions shared with the user in a specific directory location.

Move file or folder to directoryTool to move a file or folder into a folder or to the root of your Library.

Update User MetadataTool to update user metadata in Gigasheet.

Generate AI FormulaTool to generate Excel-style formulas using AI based on natural language queries.

Cast Column Data TypeTool to change a column's data type in a Gigasheet dataset.

Change Column CaseTool to change the case of a column to Uppercase, Lowercase, Capitalized, or Proper.

Clean Company NameTool to clean company names by stripping common business suffixes (Inc.

Combine ColumnsTool to combine multiple columns into a single new column with a separator.

Append Rows to Sheet by NameAppends one or more rows to a Gigasheet dataset using column names as keys.

Generate Dataset Assistant TipsTool to generate AI-powered tips for analyzing a dataset.

Initiate Dataset ExportInitiates an asynchronous export job for a Gigasheet dataset.

Find and Replace in DatasetTool to find and replace values in specified columns of a Gigasheet dataset.

Insert Blank Row in DatasetTool to insert a blank row with null values into a dataset.

Rename Columns to UniqueTool to rename all columns in a dataset to unique names.

Save Current ViewSaves the current view state of a Gigasheet dataset and returns a view handle.

Select columns by nameTool to select specific columns from a Gigasheet dataset by name, keeping only those columns in the specified order.

Extract Domain from URL ColumnTool to extract domain from a URL column in a Gigasheet dataset.

Filter File Rows by Column NameFilter rows in a Gigasheet file by column names and return matching results.

Get Filtered Row IndexMaps an unfiltered row number to its position in the filtered result set.

Filter File with Stream ProgressFilter data from a Gigasheet file with real-time streaming progress updates.

Save Exported FileSaves a file state with applied filters and grouping to create an exported version.

Combine Files by NameTool to combine multiple files by a shared column name.

Export Gigasheet to S3Tool to export Gigasheet data to AWS S3.

Import from S3Tool to import data from AWS S3 into your Gigasheet Library.

Request Access to FileTool to request access to a Gigasheet file.

Request API AccessRequest API access by sending a notification to Gigasheet support team.

Trim Column WhitespaceTool to trim leading and trailing whitespace from all values in a column.

Unroll Delimited ColumnTool to explode a column containing delimited data into multiple rows.

Upload Raw Data DirectTool to upload raw data directly to Gigasheet using byte array contents.

Upload from URLTool to upload data to Gigasheet from a specified URL.

Preview HTTP EnrichmentTool to preview a generic HTTP enrichment on a Gigasheet dataset before executing it on all rows.

Set Dataset Client State VersionApplies or restores a specific client state version to a dataset.

Update cell by column name and rowTool to update a cell in a dataset by specifying column name and row number.

Share fileTool to share a Gigasheet file with specified recipients.

Opt out of shared fileTool to remove your access from a file that has been shared with you.

Create/Update Filter TemplateTool to create or update a saved filter template.

Rename Columns by NameTool to rename columns in a Gigasheet dataset using their current names.

Rename FileTool to rename a file in Gigasheet.

Reset Client State to DefaultResets the client state of a sheet to the default state.

Reset User PasswordTool to trigger password reset for the authenticated user.

Search Dataset ActivityTool to search the history of write actions performed on a Gigasheet dataset.

Search LibraryTool to search through the Gigasheet file library by file metadata.

Send Invite EmailsTool to send email invitations to join Gigasheet.

Set Aggregate Filter ModelTool to set the aggregate filter model in the client state of a sheet.

Set Client State AggregationsSets aggregations in the client state of a sheet.

Set Client State Column StateTool to set column state in the client state of a sheet.

Set Client State Filter ModelTool to set the filter model in the client state of a sheet.

Set Client State Group ColumnsTool to set group columns in the client state of a sheet.

Set Client State Sort ModelSets the sort model for a sheet's client state.

Set Client State Visible ColumnsTool to set visible columns in the client state of a sheet.

Set Dataset Client StateSets the client state of a dataset using a state object.

Set Dataset Column CurrencyTool to set currency format for a dataset column.

Set Dataset NoteTool to set or update a note on a dataset in Gigasheet.

Update Dataset CellTool to update a single cell value in a Gigasheet dataset by column letter and row number.

Update Dataset ViewTool to update the client state of a specified view.

Upsert Rows in DatasetTool to upsert rows in an existing Gigasheet dataset.

Validate Dataset FormulaTool to validate a formula expression against a dataset.

Validate Files CombineTool to validate a combine files request and return all errors that might appear.

Validate Files Combine by NameTool to validate a combine by name request before executing it.

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

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: ["gigasheet"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

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

  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 gigasheet, 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 Gigasheet 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 Gigasheet MCP Agent with another framework

OpenAI Agents SDK

Use Gigasheet MCP with OpenAI Agents SDK

Claude Agent SDK

Use Gigasheet MCP with Claude Agent SDK

Claude Code

Use Gigasheet MCP with Claude Code

Claude Cowork

Use Gigasheet MCP with Claude Cowork

Codex

Use Gigasheet MCP with Codex

OpenClaw

Use Gigasheet MCP with OpenClaw

Hermes

Use Gigasheet MCP with Hermes

CLI

Use Gigasheet MCP with CLI

Google ADK

Use Gigasheet MCP with Google ADK

LangChain

Use Gigasheet MCP with LangChain

Mastra AI

Use Gigasheet MCP with Mastra AI

LlamaIndex

Use Gigasheet MCP with LlamaIndex

CrewAI

Use Gigasheet MCP with CrewAI

Explore Other Toolkits

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.

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.

TOOLKIT MARKETPLACE

FAQ

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

With a standalone Gigasheet MCP server, the agents and LLMs can only access a fixed set of Gigasheet tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Gigasheet 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 v6?

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 Gigasheet tools.

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

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

Used by agents from

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for free Get a demo↗

Harsha GaddipatiCo-founder, Slashy

Karan skipped his own birthday party to fix our critical issue. It was 10 pm and he diverted his Waymo to help us instead. This really sets the bar, shows you the commitment you need to have when users rely on your software.

Abhi AryaCo-founder, Opennote

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 has immensely helped in keeping new users on the platform.

Nirman DaveCEO, Zams

We chose Composio over Pipedream because it delivered depth where it mattered. It supported niche tools and tricky edge cases that other platforms simply ignored. Giving us confidence to scale without compromising.

Ryan YuFounder, Extra Thursday

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down in the complexities of managing agent auth would have been a death sentence for Extra Thursday.

Tomisin JenrolaFounder & CEO, SwarmZero

Before partnering with Composio, adding tool integrations was a slow, resource-intensive process. Each integration could take weeks or months of engineering time, and maintaining them meant constantly keeping up with API changes.

Jerome LeclancheCo-Founder, Ingram Technologies

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.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

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.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

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.

How to integrate Gigasheet MCP with Vercel AI SDK v6

Table of Contents

Connect Gigasheet without Auth hassles

Introduction

Also integrate Gigasheet with

TL;DR

What is Vercel AI SDK?

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

Supported Tools & Triggers

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

How to build Gigasheet MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Excel

21risk

Abstract

FAQ

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

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

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

How safe is my data with Composio Tool Router?

Used by agents from

Never worry about agent reliability