A1 Google Sheets MCP
A1 Google Sheets MCP is a 20-tool MCP server that lets an AI app find, read, write, format, chart, protect and share Google Sheets through the Google Sheets (and Drive, for search/sharing) APIs using plain-language requests.
Search & create: find spreadsheets by name, list files, and create new spreadsheets with custom tabs, locale and time zone.
Read data: get spreadsheet structure/metadata or cell values/formulas, read multiple ranges in one call, and inspect sheets, tables, charts, protections and conditional formats.
Write data: overwrite ranges, batch-write many ranges, append rows, and clear values while preserving formatting.
Manage sheets/tabs: add, duplicate, rename, delete, or copy sheets between spreadsheets.
Format and shape: style cells (colors, bold, alignment, number formats), freeze rows/columns, set borders, and resize/insert/delete/hide/group rows or columns.
Validation & rules: add dropdowns/data validation, protect ranges from editors, and manage conditional formatting rules.
Tables & charts: create structured tables with typed columns, and build column/bar/line/area/stepped-area/scatter/pie charts, with raw ChartSpec support.
Share & access: list, grant, update and revoke permissions (reader/commenter/writer) for users, groups, domains, or public links.
Escape hatch:
raw_requestcalls any Google Sheets API path directly for features without dedicated tools, limited to Sheets only.Safety conscious: marks destructive actions, does not replay uncertain writes/append, and uses batch/atomic updates to respect quotas.
Provides tools for interacting with Google Sheets, including searching and creating spreadsheets, reading and writing cell ranges, appending rows, managing sheets, formatting, data validation, protected ranges, conditional formats, structured tables, charts, and sharing access.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@A1 Google Sheets MCPFind the quarterly budget spreadsheet and summarize each sheet."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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_requestcannot reach Drive.Minimal Google scopes.
spreadsheetscovers 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.
Related MCP server: Google Sheets MCP Server
Contents
Quick start
You need Node.js 20+, a Google account and OAuth credentials from a Google Cloud project with the Google Sheets API enabled.
Add the server to your AI app.
Ask the read-only question above.
In the app: open Settings → MCP servers, select Add server, choose STDIO, enter the command npx -y @a1-x-tech/mcp-google-sheets@latest and environment variables GOOGLE_SHEETS_CLIENT_ID, GOOGLE_SHEETS_CLIENT_SECRET, GOOGLE_SHEETS_REFRESH_TOKEN, then select Save and Restart.
From the command line:
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@latestcodex mcp listclaude 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@latestclaude mcp listThe current official path is Settings → Extensions. For a custom desktop extension, open Advanced settings → Extension Developer → Install Extension…, select a .mcpb file and follow the prompts.
This repository currently publishes an npm stdio package and does not contain a .mcpb bundle. For Claude Desktop builds that still support local configuration, use the following JSON stdio configuration as a fallback:
{
"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"
}
}
}
}In those builds, save it to ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows.
Claude Desktop MCP documentation
Add this to ~/.cursor/mcp.json on macOS/Linux or %USERPROFILE%\.cursor\mcp.json on Windows:
{
"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"
}
}
}
}Run MCP: Open User Configuration and add:
{
"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 }
]
}Check it with MCP: List Servers.
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:F50and 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
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_spreadsheetsupplies the ids — sheet titles are not addresses.A write overwrites its range;
append_valuesadds rows after the last data row; anullcell is skipped, not cleared.clear_valuesempties 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.Batch tools carry several ranges or requests in one call and count once against the quota; a
batchUpdateis 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
Operation | What happens | Confirmation boundary |
Read metadata or values | Reads structure and cells | No change |
Create a spreadsheet | Adds a file to My Drive | Changes Google Sheets |
Write, batch-write or append values | Overwrites cells or adds rows | Changes a spreadsheet |
Format, freeze, borders, dimensions, validation, rules, tables, charts | Changes presentation, structure and rules | Changes a spreadsheet |
Clear values or delete a sheet, rows or columns | Removes data with no undo through the API | Destructive |
Manage protected ranges and permissions | Changes who can open or edit the file | Changes access |
Raw API request | Can call API methods without a dedicated tool | Potentially destructive |
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.
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.
Configure the OAuth consent screen and create a Desktop app OAuth client.
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.
Request the minimal scope:
https://www.googleapis.com/auth/spreadsheetsIt covers every Sheets tool. Only
search_spreadsheetsandmanage_permissionsneed a Drive scope on top:https://www.googleapis.com/auth/drive, ordrive.readonlyfor search alone, ordrive.filefor 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
Variable | Required | Description |
| Yes* | OAuth client ID. |
| Yes* | OAuth client secret. |
| Yes* | OAuth refresh token. |
| Yes* | Short-lived (~1 h) alternative to the OAuth trio. |
| No | Google Sheets API base URL override. |
| No | Per-request timeout; default |
| No | Temporary-error retries; default |
* 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=0to 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 and5xxerrors, 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.
Support
Found a bug or need a scenario? Create an issue or write in Telegram.
Maintenance
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to interact with Google Sheets for reading, writing, and managing spreadsheets through a set of MCP tools.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Google Sheets, performing operations like creating, reading, updating, and clearing spreadsheet data.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Google Sheets via natural language, supporting CRUD operations, listing, sharing, and batch updates.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to read, write, and manage Google Sheets using the Google Sheets API v4.MIT
Related MCP Connectors
Query your Google Sheets as structured JSON: list sheets and tabs, read schemas, filter rows.
Search and discover Google Apps Script libraries with AI-generated summaries
Google NotebookLM via natural language: create notebooks, add sources (PDF, URL, YouTube) and ask gr
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/A1-x-Tech/mcp-google-sheets'
If you have feedback or need assistance with the MCP directory API, please join our Discord server