Google Sheets MCP

English | Русский

A1 Google Sheets MCP lets an AI app work with Google Sheets in plain language. Find a spreadsheet, read its data, write and append rows, shape sheets and formatting, build charts and share the result.

It uses the Google Sheets API with your Google account. It separates reading from writing, keeps destructive operations explicit and makes the limits of the Sheets API clear instead of implying that every spreadsheet task is possible.

• 20 tools. Search and create spreadsheets, read and write ranges, manage sheets, formatting, data validation, protected ranges, conditional formats, structured tables, charts and access.
• Writes are deliberate. A write is never replayed after an ambiguous failure — a replayed append would duplicate rows — and destructive tools are marked so your AI client can ask first.
• Sheets only. Drive is an internal dependency for spreadsheet search and sharing alone; there is no generic Drive tool, and raw_request cannot reach Drive.
• Minimal Google scopes. spreadsheets covers every Sheets tool; a Drive scope is needed only for spreadsheet search and sharing.

Start with a read-only question:

Find the quarterly budget spreadsheet and summarize what each of its sheets contains.

Connect the server · Explore use cases · Open technical documentation

See it work in a minute

You: Show me the structure of the sales report spreadsheet — its sheets, their sizes and frozen rows.

Assistant: Shows the sheets with their sizes, frozen headers and the objects on them. Nothing changes.

You: Prepare a “March” sheet as a copy of “February” and clear the numbers, keeping the layout.

Assistant: Shows the plan — duplicate the sheet, rename it and clear the data ranges — then asks for confirmation before changing anything.

You: Confirm.

Assistant: Duplicates the sheet and clears the values. Formatting, data validation and frozen rows stay.

Contents

• Quick start
• What you can ask it to do
• How a spreadsheet changes
• What can change
• Getting access
• Configuration
• Data, limits and background work
• Technical documentation
• Support

Quick start

You need Node.js 20+, a Google account and OAuth credentials from a Google Cloud project with the Google Sheets API enabled.

1. Prepare Google OAuth access.
2. Add the server to your AI app.
3. Ask the read-only question above.

codex mcp add google-sheets \
  --env GOOGLE_SHEETS_CLIENT_ID=your_client_id \
  --env GOOGLE_SHEETS_CLIENT_SECRET=your_client_secret \
  --env GOOGLE_SHEETS_REFRESH_TOKEN=your_refresh_token \
  -- npx -y @a1-x-tech/mcp-google-sheets@latest

codex mcp list

claude mcp add \
  --env GOOGLE_SHEETS_CLIENT_ID=your_client_id \
  --env GOOGLE_SHEETS_CLIENT_SECRET=your_client_secret \
  --env GOOGLE_SHEETS_REFRESH_TOKEN=your_refresh_token \
  --transport stdio --scope user google-sheets \
  -- npx -y @a1-x-tech/mcp-google-sheets@latest

claude mcp list

{
  "mcpServers": {
    "google-sheets": {
      "command": "npx",
      "args": ["-y", "@a1-x-tech/mcp-google-sheets@latest"],
      "env": {
        "GOOGLE_SHEETS_CLIENT_ID": "your_client_id",
        "GOOGLE_SHEETS_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_SHEETS_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

{
  "mcpServers": {
    "google-sheets": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@a1-x-tech/mcp-google-sheets@latest"],
      "env": {
        "GOOGLE_SHEETS_CLIENT_ID": "your_client_id",
        "GOOGLE_SHEETS_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_SHEETS_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

{
  "servers": {
    "google-sheets": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@a1-x-tech/mcp-google-sheets@latest"],
      "env": {
        "GOOGLE_SHEETS_CLIENT_ID": "${input:sheets_client_id}",
        "GOOGLE_SHEETS_CLIENT_SECRET": "${input:sheets_client_secret}",
        "GOOGLE_SHEETS_REFRESH_TOKEN": "${input:sheets_refresh_token}"
      }
    }
  },
  "inputs": [
    { "type": "promptString", "id": "sheets_client_id", "description": "Google OAuth client ID" },
    { "type": "promptString", "id": "sheets_client_secret", "description": "Google OAuth client secret", "password": true },
    { "type": "promptString", "id": "sheets_refresh_token", "description": "Google OAuth refresh token", "password": true }
  ]
}

What you can ask it to do

Find and read data

• Find the newest spreadsheet with “budget” in the name and show its structure.
• Read 'Q3'!A1:F50 and summarize the totals.
• Show the formulas behind the Summary sheet.

Update the numbers

• Write this table into Sheet1!A1, formulas included.
• Append today’s figures as a new row of the log.
• Update several ranges in one batch, or clear a draft range while keeping its formatting.

Shape and present

• Add a “March” sheet, freeze the header row and make it bold.
• Highlight negative amounts in red with a conditional format and add borders.
• Build a column chart of revenue by month on its own sheet.
• Turn the data into a structured table and add a dropdown with data validation.

Protect and share

• Protect the totals row so only I can edit it.
• Give a colleague edit access and everyone else read-only.
• Show who currently has access to the file.

How a spreadsheet changes

1. Values tools address cells in A1 notation ('Sheet name'!A1:C10); structural tools (sheets, formatting, rules, tables, charts) address a numeric sheetId with 0-based indexes. get_spreadsheet supplies the ids — sheet titles are not addresses.
2. A write overwrites its range; append_values adds rows after the last data row; a null cell is skipped, not cleared.
3. clear_values empties values and formulas but keeps formatting, data validation, notes and merges. There is no undo through the API — deleting a sheet, rows or columns destroys their data.
4. Batch tools carry several ranges or requests in one call and count once against the quota; a batchUpdate is atomic — all of its requests apply or none do.

Some spreadsheet features have no dedicated tool: merged cells, named ranges, banding, filters, slicers, find-and-replace and gradient conditional-format rules go through raw_request, which is limited to the Sheets API origin. A new spreadsheet lands in the My Drive root — moving it into a folder is not covered, and manage_permissions cannot transfer ownership.

What can change

The AI client controls confirmation prompts. The server marks reads, writes and destructive tools so the client can distinguish an inspection from a live change.

Getting access

Google Sheets requires OAuth 2.0 to edit spreadsheets; an API key is not enough.

1. Create or select a Google Cloud project and enable the Google Sheets API. Also enable the Google Drive API if you want spreadsheet search and sharing.

2. Configure the OAuth consent screen and create a Desktop app OAuth client.

3. Authorize the Google account that owns or can edit the spreadsheets. The OAuth 2.0 Playground can obtain the refresh token when Use your own OAuth credentials is enabled.

4. Request the minimal scope:

   text

   Copy

   https://www.googleapis.com/auth/spreadsheets
   

   It covers every Sheets tool. Only search_spreadsheets and manage_permissions need a Drive scope on top: https://www.googleapis.com/auth/drive, or drive.readonly for search alone, or drive.file for files created through this app.

Testing-mode OAuth refresh tokens can expire after seven days. Publish the OAuth app, or use an Internal app in a Workspace domain, when you need long-lived access. Treat the client secret and refresh token as passwords.

Configuration

* Provide either the OAuth trio or an access token. Without credentials the server still starts and lists its tools; the first call names the variables to set.

Data, limits and background work

• Requests go to Google. The local server refreshes Google OAuth tokens and calls the Sheets API — and, for spreadsheet search and sharing only, the Drive API. Its anonymous telemetry contains an installation ID, package version, AI client and platform versions, and tool names — never OAuth tokens, spreadsheet data, tool arguments or prompts. Set ASKADS_TELEMETRY=0 to opt out.
• Google applies per-minute quotas. The documented limits are 300 reads and 300 writes per minute per project, and 60 of each per user; a batch call counts once however many ranges or requests it carries. A spreadsheet holds at most 10,000,000 cells. On 429, the server uses backoff; reads also retry after network and 5xx errors, while writes are not replayed after an uncertain failure.
• There is no background polling. The server runs only when called. If your AI app supports scheduled tasks, it can check a spreadsheet periodically.

Technical documentation

• MCP capability catalog — task-oriented pages for every tool.
• All tools and inputs
• Development documentation
• Publishing documentation
• Google Sheets API reference

Support

Found a bug or need a scenario? Create an issue or write in Telegram.

You made it to the end!