Skip to content

MCP server

Google Sheets MCP server

Google's own Sheets MCP server lets AI read and update cell values and formulas, change spreadsheet structure and insert rows or columns.

At a glance

Maintained by
Google
Tools exposed
6 listed below
Reviewed
September 24, 2026

Why it matters

What it does and why it matters

Spreadsheets are where many businesses really run: price lists, trackers, budgets and reports. Google's own Sheets MCP server lets an assistant read values, read spreadsheet details, update values and formulas, change spreadsheet settings and insert rows or columns.

That supports questions such as "what are total sales by region in this sheet" and tasks such as "add this week's numbers to the tracker".

At review time, it is part of Google's Workspace developer preview program, which requires membership. It can overwrite values and formulas, so we work on copies or specific ranges while testing, and keep version history on so changes can be rolled back.

For sheets that feed reports or other systems, we protect key ranges and give the assistant a separate input tab to write to. That keeps formulas and totals safe while still letting the assistant do the typing.

Use cases

Best business use cases

Sheet questions

Ask questions about data in a sheet. See automated reporting.

Update trackers

Add rows to trackers from emails or forms. See data entry automation.

Formulas

Write and fix formulas.

Restructure

Insert columns and tidy layouts.

Report prep

Prepare data for weekly reports.

Tools

Available tools

Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.

Read and write: Read and write for spreadsheet values, formulas and structure.

  • get_values

    Reads cell values and grid data.

  • get_spreadsheet

    Gets sheet names and spreadsheet metadata.

  • update_values

    Writes cell values.

  • update_formulas

    Sets or updates formulas.

  • update_spreadsheet

    Runs structural batch updates.

  • insert_dimension

    Inserts rows or columns.

Workflows

Example workflows

Weekly numbers update

  1. 1

    Share this week's figures.

  2. 2

    The assistant finds the tracker sheet.

  3. 3

    It adds a row with the figures.

  4. 4

    It checks totals update correctly.

  5. 5

    It reports the change.

Fix a broken formula

  1. 1

    Point to the cell with an error.

  2. 2

    The assistant reads the formula and data.

  3. 3

    It explains the problem.

  4. 4

    It proposes a fix.

  5. 5

    It updates the formula after approval.

Prompts

Example prompts

  • “What were total sales by region in the Q3 sheet?”

  • “Add this week's figures as a new row in the Sales Tracker.”

  • “Why does cell F12 show an error, and how do I fix it?”

Setup

Installation and configuration

Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.

Claude Code: terminal

claude mcp add --transport http --client-id YOUR_CLIENT_ID --client-secret --callback-port 8080 google-sheets https://sheetsmcp.googleapis.com/mcp/v1
  • Hosted server: https://sheetsmcp.googleapis.com/mcp/v1.
  • Needs: OAuth 2.0 client ID and secret from your own Google Cloud project..

Security

Security considerations

  • Limit workspaces

    Connect with an account that sees only the workspaces or projects a task needs.

  • Mark AI-created items

    Use a label or naming rule so items created by the assistant are easy to spot and review.

  • Guard deletes

    Keep version history on so overwritten values can be restored.

  • Untrusted text

    Task descriptions and comments can contain misleading text. Treat them as data.

Related servers

Servers that pair well with it

Google Drive

Google's own Drive MCP server lets AI search, read and create files in Google Drive, with your Google Workspace sign-in.

Airtable

Airtable's official hosted MCP server lets AI list workspaces, create bases and read records, with wider read and write access to tables and automations.

BigQuery

Google's remote BigQuery MCP server lets AI list datasets and tables and run SQL, with a read-only query tool and IAM controls.

Keep exploring

FAQ

Questions people ask us

Have a question that is not here? Ask us directly.

Start a project

Want this connected to your own systems? We build AI workflows with MCP.

Send a short brief. We reply with questions, a suggested plan and an estimate you can compare with other offers.

Your privacy choices

We use necessary storage to run this site. With your permission we also use Google Analytics to see which pages help people, and load maps from Google. You can change this at any time. Read the cookie policy.