Google Sheets API MCP Server
LocalAbout Google Sheets API MCP Server
Google Sheets API MCP Server lets MCP clients manage spreadsheets, sheets, cell values, and developer metadata through Google Sheets. It combines spreadsheet operations with MCP resources for reading spreadsheet data.
Key features
- 01Create, retrieve, update, and delete spreadsheets
- 02Manage sheets and sheet properties
- 03Read, write, append, and clear cell values
- 04Handle developer metadata
- 05Expose spreadsheet data as MCP resources
Use cases
- 01Create or maintain spreadsheets through an MCP client
- 02Read or update values across one or more ranges
- 03Organize sheets and manage spreadsheet metadata
MCP support
Exposes spreadsheet-management tools and spreadsheet, sheet, value-range, and metadata resources to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGoogle Sheets API MCP Server
A comprehensive Model Context Protocol (MCP) server for interacting with the Google Sheets API. This server provides tools and resources for managing spreadsheets, sheets, values, and developer metadata.
## Features
- Create, read, update, and delete spreadsheets
- Manage sheets within spreadsheets
- Read, write, append, and clear values
- Work with developer metadata
- Access spreadsheet data through MCP resources
## Prerequisites
- Node.js 16 or higher
- Google Cloud Platform project with the Google Sheets API enabled
- OAuth 2.0 credentials (client ID, client secret, refresh token)
## Setup
1. Clone this repository
2. Install dependencies:
```
npm install
```
3. Create a `.env` file based on `.env.example` with your Google API credentials:
```
CLIENT_ID=your_client_id
CLIENT_SECRET=your_client_secret
REDIRECT_URI=your_redirect_uri
REFRESH_TOKEN=your_refresh_token
```
## Usage
### Running the server
```
npm start
```
### Development mode
```
npm run dev
```
### Testing with MCP Inspector
```
npm run inspect
```
## Available Tools
### Spreadsheet Management
- `createSpreadsheet`: Create a new spreadsheet
- `getSpreadsheet`: Get spreadsheet details
- `batchUpdate`: Apply multiple updates to a spreadsheet
### Sheet Management
- `copySheet`: Copy a sheet to another spreadsheet
- `addSheet`: Add a new sheet to a spreadsheet
- `deleteSheet`: Delete a sheet from a spreadsheet
- `updateSheetProperties`: Update sheet properties
### Values Management
- `getValues`: Get values from a range
- `updateValues`: Update values in a range
- `appendValues`: Append values to a range
- `clearValues`: Clear values from a range
- `batchGetValues`: Get values from multiple ranges
- `batchUpdateValues`: Update values in multiple ranges
### Developer Metadata
- `getDeveloperMetadata`: Get all developer metadata
- `createDeveloperMetadata`: Create new developer metadata
- `updateDeveloperMetadata`: Update existing developer metadata
- `deleteDeveloperMetadata`: Delete developer metadata
## Available Resources
- `sheets://spreadsheet/{spreadsheetId}`: Get spreadsheet details
- `sheets://spreadsheet/{spreadsheetId}/sheet/{sheetName}`: Get sheet details
- `sheets://spreadsheet/{spreadsheetId}/values/{range}`: Get values from a range
- `sheets://spreadsheet/{spreadsheetId}/metadata`: Get all developer metadata
## Authentication
This server uses OAuth 2.0 for authentication with the Google Sheets API. You need to provide the following credentials in the `.env` file:
- `CLIENT_ID`: Your Google API client ID
- `CLIENT_SECRET`: Your Google API client secret
- `REDIRECT_URI`: The redirect URI configured in your Google API project
- `REFRESH_TOKEN`: A refresh token obtained through the OAuth 2.0 flow
## License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.