mcp-google-sheets

MCP server for Google Sheets and Google Drive: an agent reads, edits and creates spreadsheets, tabs and charts

  • 1,019 ★ on the repository
  • Last commit
  • MIT
MCP server

Broad access

Why this level

  • Writes and changes data in your Google Sheets and Google Drive
  • Can grant spreadsheet access to other users by email
  • Handles service account keys or OAuth credentials
All reasons and checks

xing5/mcp-google-sheets

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add mcp/mcp-google-sheets

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • Writes and changes data in your Google Sheets and Google Drive
  • Can grant spreadsheet access to other users by email
  • Handles service account keys or OAuth credentials

This is third-party code. Review the repository files before installing.

What it does

The server links an MCP client to the Google Sheets and Google Drive APIs. The agent finds spreadsheets in a Drive folder, reads ranges in A1 notation, writes and batch-updates cells, inserts rows and columns, and creates tabs and whole spreadsheets. It also reads formulas, copies and renames sheets, builds charts and shares files by email. To save context you can expose only the tools you need via ENABLED_TOOLS or the include-tools flag.

Who it is for. For analysts, marketers and business owners who keep records and reports in Google Sheets.

Good fit when

  • You want an agent to read and update Google Sheets data
  • You need a report or summary across several spreadsheets
  • You want to create a spreadsheet, tab or chart without manual work

Not a fit when

  • You have no Google Cloud project with a service account or OAuth
  • You need local Excel files rather than Google cloud

Example request

Build a per-manager summary from the quarterly sales sheet and write it to a new tab

MCP

Transport
stdio, sse
Authentication
OAuth

Environment variables

SERVICE_ACCOUNT_PATH secret
Path to the Google Cloud service account JSON key
DRIVE_FOLDER_ID
Id of the Google Drive folder shared with the service account
CREDENTIALS_PATH secret
Path to the OAuth client file for browser login
CREDENTIALS_CONFIG secret
Base64 credentials content instead of a file on disk

Limitations

It needs a Google Cloud project with the Google Sheets API and Google Drive API enabled and one auth method: service account, OAuth or a base64 key. For a service account you must share the Drive folder with its email. The server works with Google cloud spreadsheets and does not open local Excel files.

How to disable. Remove the mcp-google-sheets block from your MCP client config and restart it. No separate uninstall is needed because uvx runs the package on demand.

FAQ

Which auth method should I pick?

For server automation a service account is recommended because it works without a browser. For personal use OAuth with a browser login on first run is fine.

How do I reduce context usage?

All tools are enabled by default. Use the ENABLED_TOOLS variable or the include-tools flag to keep only what you need, for example reading and writing data.

Discussion

No questions or reviews yet.

MCP server and CLI to drive real Microsoft Excel: Power Query, DAX, VBA, PivotTables and charts

MCP serverBroad access887Repository stars

MCP server that gives an agent access to MySQL: schema inspection and queries, read-only by default, writes behind flags

MCP serverExtended access2.2KRepository stars

A Python MCP server for MySQL: listing tables, reading data, running SQL and inspecting schema through a controlled interface

MCP serverBroad access1.4KRepository stars

One MCP server for SQLite, SQL Server, PostgreSQL and MySQL: read and change data, edit schemas and export to CSV and JSON

MCP serverBroad access391Repository stars

An MCP server for Airtable: the agent inspects base schemas, searches, creates, updates and deletes records, and handles fields and comments

MCP serverBroad access456Repository stars
Official

Google's open-source MCP server for databases: ready tools for Postgres, MySQL, BigQuery, Spanner and more, plus custom tools in tools.yaml

MCP serverBroad access16.8KRepository stars

README in short

The README covers a one-line uvx launch, four Google Cloud auth methods and detailed service account and OAuth setup. It lists every tool for reading, writing, batch updates, sheet operations, charts and sharing. It shows Claude Desktop configs and a Docker run with SSE transport. Tool filtering for context savings is documented separately. MIT licensed.

README badge

Report a problem