Spark
Sign In
MCP Connector

Manage Google Sheets with AI

TypeScript MCP server that lets AI agents create, read, update, share and copy Google Sheets with OAuth2 or a service account.

Get from source
Works with google sheetsgoogle drive
VibeBaza
Own this? Claim it
88
Spark score
out of 100
Updated Jun 2025
Fresher alternatives ↓
Source checked Oct 10, 2026
Version 1.0.0
Models
universal
Add to Favorites

Why it matters

Enable AI agents to securely interact with Google Sheets, offering robust capabilities for creating, reading, updating, and managing spreadsheets and their data.

Outcomes

What it gets done

01

Create, list, and rename spreadsheets and sheets.

02

Read and write cell data, including batch updates.

03

Share spreadsheets with granular permissions.

04

Automate Google Sheets operations via API.

Source

Get it from source

Spark does not host a copy of it.

Open source

Reports

Agent outcome reports

No reports yet

Capabilities

Tools your agent gets

create

Creates a new spreadsheet and optionally moves it to configured Drive folder

listSheets

Lists all sheet tabs in the given spreadsheet

renameSheet

Renames an existing sheet tab

createSheet

Adds a new sheet tab to the spreadsheet

spreadsheetInfo

Gets metadata including title, sheet IDs, and grid properties for a spreadsheet

listSpreadsheets

Lists all spreadsheets in the configured Drive folder or My Drive

shareSpreadsheet

Shares spreadsheet with users at specified permission levels and sends notifications

sheetData

Reads cell values from a sheet range or entire sheet

+5 tools

Overview

A Bun-based TypeScript MCP server with tools for creating, reading, editing, sharing and copying Google Sheets. It supports service account and OAuth2 authentication. Use when an assistant must work on Google spreadsheets. Requires a Google Cloud project with Sheets and Drive APIs enabled.

What it does

MCP-Google-Sheets is a TypeScript Model Context Protocol server that lets AI agents securely interact with Google Sheets through well-typed tools. It is built on Bun and the @modelcontextprotocol/sdk, and it supports two authentication flows: a service account, supplied as a base64-encoded CREDENTIALS_CONFIG value, and OAuth2, which uses credentials.json plus a generated token.json for user-scoped access.

When to use - and when NOT to

Use it when an assistant needs to create, read, edit, organize or share Google spreadsheets on your behalf, for example building a budget sheet, reading a range of cells, appending rows, or copying a tab between spreadsheets.

It needs a real Google Cloud setup, so do not choose it if you cannot enable the Sheets API and the Drive API or obtain either an OAuth2 client ID or a service account key. It also requires Bun 1.0 or newer on your PATH.

Capabilities

The server registers these tools:

  • create makes a new spreadsheet and moves it into your Drive folder if one is configured.
  • listSheets lists all sheet tabs in a spreadsheet.
  • renameSheet renames an existing tab, and createSheet adds a new tab.
  • spreadsheetInfo fetches metadata such as title, sheet IDs and grid properties.
  • listSpreadsheets lists spreadsheets in your configured Drive folder, or in My Drive.
  • shareSpreadsheet shares a spreadsheet with users as reader, commenter or writer and sends notifications.
  • sheetData reads cell values from a sheet and range, or the whole sheet.
  • updateCells writes a two-dimensional array of values into an A1-style range.
  • batchUpdate applies multiple range updates in a single request.
  • addRows and addColumns insert rows or columns at a given index.
  • copySheet copies a tab between spreadsheets, optionally renaming it.

How to install

Prerequisites are Bun, a Google Cloud project with the Sheets API and Drive API enabled, and either an OAuth2 client ID (download credentials.json) or a service account key (download service_account.json). A Drive folder ID is optional and is used if you want new sheets moved out of My Drive.

Clone the repository, install dependencies with bun install, then configure the environment. The settings are CREDENTIALS_CONFIG for a base64-encoded service account key, EMAIL_ID for the Google email address you will use to access the spreadsheet, and the optional DRIVE_FOLDER_ID. If you use OAuth2 instead, place credentials.json next to index.ts, and token.json is generated after the first OAuth run. On Linux or macOS you can produce the base64 value by encoding the service account file and stripping newlines. Then start the server:

bun index.ts

On the first OAuth2 run you will see a URL. Visit it, grant access, and paste the code back into the terminal, after which token.json is created automatically.

How it works internally: initContext() chooses the auth method in order of service account, then OAuth2, then an error, and builds shared Google Sheets and Drive clients. Each tool is registered with server.tool(...), and the server uses StdioServerTransport so Claude can invoke tools over stdin and stdout. An agent sends a JSON request naming the tool and its arguments, such as the create tool with a title, and the server calls the Google APIs and returns JSON-wrapped results.

Who it's for

Developers and analysts who want an assistant to work with Google Sheets, and contributors who want to extend it: the project welcomes issues and pull requests for new tools, bug fixes and enhancements.

Source README

MCP-Google-Sheets

A TypeScript Model Context Protocol (MCP) server that lets AI agents securely interact with Google Sheets via well-typed “tools.” Built on Bun and the @modelcontextprotocol/sdk, it supports both OAuth2 and Service-Account flows.

🚀 Features

  • Authentication
    • Service-Account via base64-encoded CREDENTIALS_CONFIG
    • OAuth2 using credentials.json + token.json for user-scoped access
  • Tools
    • create
      Creates a new spreadsheet (and moves it into your Drive folder if configured).
    • listSheets
      Lists all sheet tabs in a given spreadsheet.
    • renameSheet
      Renames an existing sheet tab.
    • createSheet
      Adds a new sheet tab to a spreadsheet.
    • spreadsheetInfo
      Fetches metadata (title, sheet IDs, grid properties) for a spreadsheet.
    • listSpreadsheets
      Lists all spreadsheets in your configured Drive folder (or My Drive).
    • shareSpreadsheet
      Shares a spreadsheet with users (reader/commenter/writer) and sends notifications.
    • sheetData
      Reads cell values from a sheet and range (or whole sheet).
    • updateCells
      Writes a 2D array of values into an A1-style range.
    • batchUpdate
      Applies multiple range updates in a single request.
    • addRows / addColumns
      Inserts rows or columns at a specified index.
    • copySheet
      Copies a sheet tab between spreadsheets (optionally renaming it).

📋 Prerequisites

  • Bun (v1.0+) installed and on your PATH
  • A Google Cloud project with:
    • Sheets API & Drive API enabled
    • An OAuth2 Client ID (download credentials.json) or a Service Account key (download service_account.json)
  • (Optional) A Drive folder ID if you want new sheets moved out of My Drive

⚙️ Setup

  1. Clone the repo 
    git clone https://github.com/yourusername/mcp-google-sheets.git
cd mcp-google-sheets
  2. Install dependencies
bun install
  1. Configure environment

Create a .env (or export) with:

# Base64-encoded service-account key JSON (optional)
CREDENTIALS_CONFIG=BASE-64 ENCODED SERVICE_ACCOUNT.JSON


# Or put your OAuth2 JSON files next to index.ts:
#   credentials.json  (OAuth client secret)
#   token.json        (generated after first OAuth run)

# The google email address that you'll use to access the spreadsheet
EMAIL_ID="Enter the email address you’ll use to access the spreadsheet"
# (Optional) ID of the Drive folder to store new sheets
DRIVE_FOLDER_ID=1a2B3c4D5e6F...

Tip: On Linux/macOS you can do

export CREDENTIALS_CONFIG=$(base64 service_account.json | tr -d '\n')

▶️ Running the Server

bun index.ts

On first OAuth2 run (if using credentials.json), you’ll see a URL. Visit it, grant access, then paste the code back into your terminal. A token.json will be generated automatically.

🔧 How It Works

Initialization

  • initContext() picks your auth method (Service-Account → OAuth2 → error).

  • Builds google.sheets & google.drive clients and stores them in a shared context.

MCP Tool Registration

  • Each “tool” (e.g. create, listSheets, sheetData) is registered via server.tool(...).

Transport

  • Uses StdioServerTransport so Claude can invoke tools over stdin/stdout.

Invocation

The agent sends a JSON request:

{ "tool": "create", "args": { "title": "Budget Q2" } }

The server runs your handler, calls Google APIs, and returns JSON-wrapped results.

🛠️ Try It Out

Clone & configure as above.

Start the server:

bun index.ts
Invoke a tool via Claude

Demo

mcp-google-sheetsmcp-google-sheets

❤️ Contributing

Feel free to open issues or PRs for new tools, bug fixes, and enhancements.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.