Google Sheets

io.github.domdomeggPublished by GitHub account domdomeggv1.2.1Updated Oct 24, 2026

Allow AI systems to read, write, and query spreadsheet data via Google Sheets.

Overview

AI-generated overview

MCP server that lets an assistant read, write, and query Google Sheets spreadsheets through the Google Sheets API.

What you can do
  • Inspect and create spreadsheets, including metadata and sheet lists
  • Read cell values from one range or several ranges at once
  • Write, batch-write, append, or clear cell values
  • Add and delete sheets (tabs) within a spreadsheet
  • Run advanced batch operations such as formatting, merging, and filters
When to use it
Useful when an assistant should answer questions from spreadsheet data, log entries such as expenses into a tracker, or keep a sheet in sync with other tools. It fits workflows that need direct read and write access to Google Sheets.
Requirements
Runs locally as an npm package (google-sheets-mcp) over stdio, or as an HTTP server on localhost. Needs Google OAuth credentials: GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and an access token in GOOGLE_ACCESS_TOKEN with Sheets scopes, plus MCP_TRANSPORT. Requires a Google Cloud project with the Sheets API enabled and a configured OAuth consent screen and redirect URI.
Before you install
The server requests full read/write spreadsheet scope, so the assistant can overwrite, append to, clear, or delete sheet data. It handles OAuth secrets (GOOGLE_CLIENT_SECRET, GOOGLE_ACCESS_TOKEN) and acts as an OAuth proxy that forwards credentials to Google; keep those values private. Spreadsheet contents are sent to the Google Sheets API.

Installation

In SourceWeft

  1. Open Google Sheets in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

google-sheets-mcp

MCP server for Google Sheets - read, write, and query spreadsheet data.

Use Cases

Data questions: "How many open deals are in the pipeline?" or "What's our total Q3 revenue?" → reads the spreadsheet and answers directly.

Quick expense entry: Snap a photo of a receipt → extracts the details and appends a row to your expense tracker.

Cross-tool status sync: "Check all our vendor Slack channels and update the tracking spreadsheet with their latest updates" → reads Slack, updates the sheet.

Data analysis: "Break down the Salesforce figures by region and compare against our events calendar" → pulls data from multiple sources into a spreadsheet for analysis.

(These are just examples - any workflow that needs spreadsheet data can use this. Use in combination with google-drive-mcp for finding files, deleting, comments, and sharing permissions.)

Setup

1. Create Google OAuth credentials

  1. Go to Google Cloud Console
  2. Create a new project (or use existing)
  3. Enable the Google Sheets API
  4. Go to APIs & Services → OAuth consent screen, set up consent screen
  5. Go to APIs & Services → Credentials → Create Credentials → OAuth client ID
  6. Choose Web application
  7. Add http://localhost:3000/callback to Authorized redirect URIs
  8. Note your Client ID and Client Secret

2. Run the server

bash
GOOGLE_CLIENT_ID='your-client-id' \GOOGLE_CLIENT_SECRET='your-client-secret' \MCP_TRANSPORT=http \npm start

The server runs on http://localhost:3000 by default. Change with PORT=3001.

3. Add to your MCP client

With the server running, follow the instructions on install-mcp, which generates the right config for your MCP client (Claude Code, Claude Desktop, Cursor, Cline, VS Code, and more).

Architecture

This server acts as an OAuth proxy to Google:

mermaid
graph LR    A[MCP client] <--> B[google-sheets-mcp] <--> C[Google OAuth/API]
  1. Server advertises itself as an OAuth authorization server via /.well-known/oauth-authorization-server
  2. /register returns the Google OAuth client credentials
  3. /authorize redirects to Google, encoding the client's callback URL in state
  4. /callback receives the code from Google and forwards to the client's callback
  5. /token proxies token requests to Google, injecting client credentials
  6. /mcp handles MCP requests, using the bearer token to call Google Sheets API

The server holds no tokens or state - it just proxies OAuth to Google.

Tools

ToolDescription
Spreadsheet
sheets_spreadsheet_getGet spreadsheet metadata (title, sheets list, optionally cell data)
sheets_spreadsheet_createCreate a new spreadsheet
Values
sheets_values_getRead cell values from a range
sheets_values_batch_getRead cell values from multiple ranges
sheets_values_updateWrite cell values to a range (overwrites)
sheets_values_batch_updateWrite cell values to multiple ranges
sheets_values_appendAppend rows after existing data
sheets_values_clearClear cell values from a range
Sheets (tabs)
sheets_sheets_listList all sheets in a spreadsheet
sheets_sheet_addAdd a new sheet (tab)
sheets_sheet_deleteDelete a sheet (tab)
Advanced
sheets_batch_updateExecute batch operations (formatting, merging, filters, etc.)

Google Sheets API Scope

  • spreadsheets - Full read/write access to spreadsheets

Contributing

Pull requests are welcomed on GitHub! To get started:

  1. Install Git and Node.js
  2. Clone the repository
  3. Install dependencies with npm install
  4. Run npm run test to run tests
  5. Build with npm run build

Releases

Versions follow the semantic versioning spec.

To release:

  1. Use npm version <major | minor | patch> to bump the version
  2. Run git push --follow-tags to push with tags
  3. Wait for GitHub Actions to publish to the NPM registry.

Source: README.md at commit e604ee6

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.2.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.