
Connect Google Sheets Oauth to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage and manipulate your spreadsheets through any AI client.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 7 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 7 available through Google Sheets.
- 01
Sheets.info
This capability retrieves metadata for a specific Google Sheet. It provides the title, timezone, locale, and a list of all available sheet tabs with their dimensions.
- 02
Sheets.read
This capability reads cell values from a specified range using A1 notation. It returns the data as a Markdown table for easy reading.
- 03
Sheets.append
This capability adds new rows to the end of an existing table. It places the data after the last populated row without overwriting what is already there.
- 04
Sheets.batch read
This capability pulls data from multiple different ranges in a single request. It is much faster than reading ranges one by one.
05-07
3 capabilities in this set.
Part of 7 available through Google Sheets.
- 05
Sheets.clear
This capability removes all values from a specified range. It wipes the content but leaves your colors, borders, and fonts intact.
- 06
Sheets.create
This capability generates a brand new, blank Google Spreadsheet. It returns the new spreadsheet ID and a direct link to open it.
- 07
Sheets.write
This capability overwrites specific cells or ranges with new data. It evaluates formulas starting with an equals sign just like a human user would.
Real work
What teams actually run
Automated Reporting
An agent appends new daily sales figures to a master sheet automatically.
Data Cleaning
You tell your agent to clear out old data in a specific range before starting a new project.
Project Tracking
A PM asks the agent to check the metadata and sheet names of a project tracker to verify its structure.
Rapid Data Entry
A developer uses the agent to write structured JSON arrays directly into specific spreadsheet cells.
Automate a task
Put Google Sheets to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Google Sheets works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Google Sheets to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
1162ms average. Fast in production.
Google Sheets is checked daily against the live service.
- Fastest day
- 859ms
- Slowest day
- 1443ms
- 14-day trend
- Improving-9%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Google Sheets, so you can see the experience inside your AI.
It does not authenticate your account with Google Sheets. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Google Sheets Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_WRZzfv7tD5Iq0uGPYkA47NxkBfDiDeHJTMYzqLBk/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Google Sheets capabilities are ready to use.
{
"mcpServers": {
"google-sheets-oauth-mcp": {
"url": "https://edge.vinkius.com/vk_preview_WRZzfv7tD5Iq0uGPYkA47NxkBfDiDeHJTMYzqLBk/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Google Sheets in Claude and other AIs
Who it's for
Built for the work Google Sheets owners hand off.
This MCP is built for anyone who manages data in Google Sheets but wants to use an AI agent to do the heavy lifting.
- 01
Data Analysts
They use the agent to populate and query spreadsheets for analysis without manual entry.
- 02
Operations Teams
They automate real-time reporting and log data across multiple sheet ranges.
- 03
Product Managers
They audit project trackers and verify sheet metadata through chat.
FAQ
Questions Google Sheets owners ask.
- 01
How do I connect my Google account?
You need to provide a Google OAuth2 Access Token. You can get this via the Google OAuth Playground or by using the gcloud auth command.
- 02
Will this overwrite my existing data?
It depends on the capability you use. The sheets.write capability will overwrite existing values in a range, while sheets.append only adds new rows to the end of your data.
- 03
Does it support formulas?
Yes, when using sheets.write, the agent uses USER_ENTERED input, meaning any formulas starting with an equals sign will be evaluated by Google Sheets.
- 04
Can I clear data without losing my colors and borders?
Yes, the sheets.clear capability removes cell values but preserves all existing formatting like colors, fonts, and borders.
- 05
Which AI clients can use this MCP?
This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
- 06
How do I get a Google OAuth2 access token for this server?
You can use the Google OAuth Playground (select Sheets API v4 and authorize) or run 'gcloud auth print-access-token' in your terminal. Note that these tokens are typically valid for 1 hour.
- 07
Can my agent create a new spreadsheet and add data to it in one go?
Yes. The agent can orchestrate multiple operations. First, use 'create_spreadsheet' to get the new ID, and then use 'write_data' or 'append_data' to populate it with your JSON arrays natively.
- 08
What is the benefit of batch reading through the agent?
Batch reading allowing your agent to retrieve data from multiple non-contiguous ranges (e.g., 'Sheet1!A1:B10' and 'Sheet2!C5:D15') in a single request, improving context efficiency and reasoning accuracy flawlessly.
Explore
More in Industry Titans
PubNub (Real-time Messaging) AI Connector
Enable real-time messaging, presence tracking, and message history for your AI agent using PubNub's global dat
ViewElectricSQL (Sync Engine) AI Connector
Sync Postgres data to your AI agent in real-time using ElectricSQL's HTTP Sync API — fetch shapes, stream upda
ViewGoogle Sheets AI Connector
Interact with Google Sheets to read, write, and manipulate data via AI.
ViewData Pipeline Prover AI Connector
A data team asked an AI to build an ETL pipeline. No schema contract. No idempotency. No freshness SLA. The pi
View
Suggestions
AI Batch vs Real-time Economics Engine AI Connector
Evaluate cost-efficiency and profitability of Batch vs. Real-time AI processing architectures.
ViewQuestDB (Time-Series) AI Connector
High-performance time-series database for fast SQL queries, data ingestion, and real-time analytics directly f
Viewimgix (Real-time Image Processing) AI Connector
Optimize and transform images via imgix — manage CDN sources, purge assets, and monitor origin connections.
ViewReal-Time Currency Exchange AI Connector
Give your AI access to the global forex market. Convert real-time and historical currencies instantly using of
View
Connect Google Sheets to Claude, Cursor, ChatGPT & more
