google-sheets-mcp
Enables Claude to read, write, append, create, and clear Google Sheets data using natural language.
README
google-sheets-mcp
A Model Context Protocol (MCP) server that lets Claude interact with Google Sheets — read, write, append, create, and clear spreadsheet data using natural language.
Features
| Tool | Description |
|---|---|
read_cells |
Read cell values from a spreadsheet (single cell, range, or entire sheet) |
write_cells |
Write values to a cell range |
append_rows |
Append rows to the end of a sheet |
create_spreadsheet |
Create a new spreadsheet with custom sheet tabs |
list_sheets |
List all sheet tabs in a spreadsheet |
clear_cells |
Clear cell values while preserving formatting |
Prerequisites
1. Google Cloud Setup
- Go to Google Cloud Console
- Create a project (or select an existing one)
- Enable the Google Sheets API: APIs & Services → Library → search "Google Sheets API" → Enable
- Create OAuth 2.0 credentials:
- APIs & Services → Credentials → + Create Credentials → OAuth client ID
- Application type: Desktop app
- Name:
google-sheets-mcp(or any name) - Click Create → Download JSON
- Save the downloaded file as
credentials/client_secret.json
Important: Make sure to select Desktop app as the application type. Web application credentials will cause a
redirect_uri_mismatcherror.
2. Requirements
- Python 3.11+
- uv (recommended) or pip
Installation
Using uv (recommended)
git clone https://github.com/takehirokawaguchi/google-sheets-mcp.git
cd google-sheets-mcp
uv sync
Using pip
git clone https://github.com/takehirokawaguchi/google-sheets-mcp.git
cd google-sheets-mcp
pip install -e .
Configuration
Create a .env file in the project root:
# Path to your OAuth2 client secret JSON (required)
GOOGLE_OAUTH_CLIENT_SECRET_FILE=/path/to/google-sheets-mcp/credentials/client_secret.json
# Path to token cache file (optional, defaults to ~/.config/google-sheets-mcp/token.json)
# GOOGLE_OAUTH_TOKEN_FILE=/path/to/token.json
First-time authentication
Run the server once to complete the OAuth2 flow in your browser:
uv run google-sheets-mcp
A browser window will open asking you to sign in to your Google account and grant access to Google Sheets. After authorization, the token is cached at ~/.config/google-sheets-mcp/token.json and subsequent runs will not require browser interaction.
Usage with Claude Desktop
Add the following to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"google-sheets": {
"command": "uv",
"args": [
"run",
"--project",
"/path/to/google-sheets-mcp",
"google-sheets-mcp"
],
"env": {
"GOOGLE_OAUTH_CLIENT_SECRET_FILE": "/path/to/google-sheets-mcp/credentials/client_secret.json"
}
}
}
}
Restart Claude Desktop after saving the configuration. The Google Sheets tools will then be available in your conversations.
Example prompts
Read the data from Sheet1 of my spreadsheet (ID: 1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgVE2upms)
Append a new row with ["Alice", 30, "Tokyo"] to the "Users" sheet
Create a new spreadsheet called "Q1 Budget" with sheets: Overview, Jan, Feb, Mar
MCP Tools Reference
read_cells
Read cell values from a Google Spreadsheet.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
spreadsheet_id |
string | yes | — | Spreadsheet ID from the URL |
range |
string | yes | — | A1 notation range, e.g. Sheet1!A1:D5 |
value_render |
string | no | FORMATTED_VALUE |
FORMATTED_VALUE / UNFORMATTED_VALUE / FORMULA |
write_cells
Write values to a cell range.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
spreadsheet_id |
string | yes | — | Spreadsheet ID |
range |
string | yes | — | A1 notation range, e.g. Sheet1!A1:C2 |
values |
array | yes | — | 2D array of values, e.g. [["Name", "Age"], ["Alice", 30]] |
value_input |
string | no | USER_ENTERED |
USER_ENTERED (parse formulas) / RAW (literal strings) |
append_rows
Append rows to the end of data in a sheet.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
spreadsheet_id |
string | yes | — | Spreadsheet ID |
sheet_name |
string | yes | — | Sheet tab name, e.g. Sheet1 |
values |
array | yes | — | 2D array of rows to append |
value_input |
string | no | USER_ENTERED |
USER_ENTERED / RAW |
insert_data_option |
string | no | INSERT_ROWS |
INSERT_ROWS / OVERWRITE |
create_spreadsheet
Create a new Google Spreadsheet.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
title |
string | yes | — | Title of the new spreadsheet |
sheet_names |
array | no | ["Sheet1"] |
List of sheet tab names to create |
list_sheets
List all sheet tabs in a spreadsheet.
| Parameter | Type | Required | Description |
|---|---|---|---|
spreadsheet_id |
string | yes | Spreadsheet ID |
clear_cells
Clear cell values (formatting is preserved).
| Parameter | Type | Required | Description |
|---|---|---|---|
spreadsheet_id |
string | yes | Spreadsheet ID |
range |
string | yes | A1 notation range to clear, e.g. Sheet1!A1:Z100 |
Development
Run tests
uv run pytest -v
Project structure
google-sheets-mcp/
├── src/
│ └── google_sheets_mcp/
│ ├── auth.py # OAuth2 authentication
│ ├── sheets_client.py # Google Sheets API wrapper
│ ├── server.py # MCP tool definitions (FastMCP)
│ └── __main__.py # Entry point
├── tests/
│ ├── conftest.py
│ ├── test_auth.py
│ ├── test_sheets_client.py
│ └── test_server.py
├── credentials/ # Place client_secret.json here (git-ignored)
└── pyproject.toml
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.