Google Sheets MCP

Google Sheets MCP

Enables agents to create, read, and modify Google Sheets using a service account, without OAuth. Provides tools for sheet creation, appending rows, updating ranges, and reading data.

Category
Visit Server

README

Google Sheets MCP

An MCP server for MCP Studio (or any MCP-compatible host) that lets an agent create, read, and modify Google Sheets. Auth is a Google service account — no OAuth dance, no client secret, no app-verification process.

Typical use:

"Look at Hacker News, then create a Google Sheet called Top Stories with the top 10 stories. Send me the link."

The agent uses a browser MCP (like Chrome) to scrape, then this MCP's create_sheet + append_rows, and replies with the spreadsheet URL.


Tools

Tool What it does
create_sheet(title, headers?, share_with_email?) Creates a new spreadsheet; optionally writes a header row and shares it with an email as writer. Returns spreadsheet_id + url.
append_rows(spreadsheet_id, values, sheet_name?) Appends rows to the bottom of a tab. values is a 2D array of cell values.
update_range(spreadsheet_id, range, values) Overwrites an A1-notation range like Sheet1!A1:C3.
read_range(spreadsheet_id, range) Reads an A1 range and returns the values as JSON.

Quick commands

Trigger Action
/sheet_create <title> Create a new sheet with the given title.
/sheet_read Read A1:Z100 from the most recently created sheet.

Setup — one-time, ~5 minutes

You need a Google service account so this MCP can talk to the Sheets API on your behalf.

  1. Create a Google Cloud project (skip if you already have one): https://console.cloud.google.com/projectcreate

  2. Enable two APIs in that project:

  3. Create a service account:

    • Go to https://console.cloud.google.com/iam-admin/serviceaccounts
    • Click Create service account.
    • Give it any name (e.g. mcp-sheets), skip the optional role/access steps, click Done.
  4. Generate a JSON key:

    • Open the service account you just made → Keys tab → Add key → Create new key → JSON.
    • A .json file downloads. Keep it handy; you'll paste its full contents into MCP Studio in the next step.

Install in MCP Studio

From the MCP Studio prompt panel:

/install https://github.com/RPieterse/mcp-studio-google-sheets-mcp

…or install from a local clone:

/install /path/to/mcp-studio-google-sheets-mcp

Studio will then prompt for two fields:

Field What to paste
Service account JSON The entire contents of the JSON key file from step 4.
Your Google email The Google account address that newly-created sheets will be shared with as a writer (so they show up in your Drive).

That's it. Test it from the panel:

/sheet_create my first MCP-created sheet

…or just say "create a new Google Sheet called inbox" to your agent.


How ownership works

Service accounts are separate Google identities, so:

  • Sheets are owned by the service account, not by you.
  • They are automatically shared with you (using the email from install) as a writer. You'll see them under "Shared with me" in Drive — drag to My Drive if you want them mixed with your own files.
  • If you need this MCP to write to a sheet you already own, share that sheet with the service account's client_email (visible in the JSON key file).
  • Quota counts against the service account's project, not your personal Google account.

If you want sheets owned by your account directly, that requires OAuth instead of a service account — see Future work below.


Local development

git clone https://github.com/RPieterse/mcp-studio-google-sheets-mcp.git
cd mcp-studio-google-sheets-mcp
npm install
npm run build
npm test

To iterate against Studio without reinstalling, run a watcher in one terminal:

npx tsc --watch

Studio re-reads the manifest and respawns the server on each tool call, so saved code is picked up live. Manifest edits are picked up on the next /mcp-servers call.

Project layout

src/
  index.ts        Stdio entrypoint. Reads env, builds the API client, wires the server.
  server.ts       MCP tool schema + dispatch.
  tools.ts        Pure handler functions (no Google deps — testable with a mock SheetsApi).
  sheets.ts       Real googleapis-backed SheetsApi implementation.
  credentials.ts  Parses + validates the service account JSON.
  types.ts        Shared types + the SheetsApi interface.
test/             vitest unit tests against the mock API.
widget.manifest.json    MCP Studio manifest.

Tests

npm test runs the vitest suite. Tools and credential parsing are covered against an in-memory mock SheetsApi; no Google account or network is touched.


Permissions declared

network: sheets.googleapis.com, www.googleapis.com, oauth2.googleapis.com
secrets: gsheets_credentials

No filesystem access. The service account JSON never leaves the OS keychain; this MCP only sees it via process.env at spawn time.


Future work

  • OAuth flow for user-owned sheets (requires Studio's OAuth implementation to support client_secret, which Google's Desktop OAuth requires even with PKCE — pending an upstream change to MCP Studio).
  • Batch update tool (batch_update_range) for multi-range writes in one API call.
  • Sheet/tab management — add new tabs, rename, delete.
  • Formatting — bold headers, freeze first row, etc.

PRs welcome.


License

MIT.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured