Gsheets MCP Server

Google Sheets document management via read, write, and batch operation support.

Data last scanned yesterday · Reviewed last month

10 6 dangerous tools42 tools★ 87TypeScriptMIT

Overview

This server allows AI assistants to interact with Google Sheets, supporting tasks ranging from basic reading and writing to advanced operations like formatting, chart management, and conditional formatting. It integrates directly with MCP clients like Claude Desktop or Cursor to bridge the gap between AI agents and spreadsheet data. Configuration involves setting up a Google Cloud Project with the Sheets API enabled and using a service account for authentication. The server supports credentials provided via file paths or JSON strings, offering flexibility in how the connection is established during runtime.

Our verdict

With a security score of 40/100, this server is currently classified as high-risk. This assessment is driven by the fact that it is a community-maintained project rather than an official vendor release, and critical aspects such as OAuth support and read-only mode safety have not been editorially reviewed. Because it grants write access to your spreadsheets, users should proceed with caution and verify the codebase before deployment in sensitive environments.

Supports batch operations and complex spreadsheet formatting
Small footprint with only three direct dependencies
Actively maintained with a commit in the last day

High-risk score due to lack of editorial security review
Authentication and read-only modes remain unverified
Community-maintained without official vendor oversight

Setup

Claude Desktop

{
  "mcpServers": {
    "mcp-gsheets": {
      "args": [
        "-y",
        "mcp-gsheets"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

Tool	Description	Risk
sheets_get_values	Read cell values from a single range	low
sheets_batch_get_values	Read cell values from multiple ranges in one request	low
sheets_get_metadata	Get spreadsheet metadata: title, locale, sheets list with IDs, row/column counts	low
sheets_check_access	Verify that the service account can access a spreadsheet	low
sheets_update_values	Write values to a single range (overwrites existing content)	medium
sheets_batch_update_values	Write values to multiple ranges in one request	medium
sheets_append_values	Append rows after the last row of an existing table.	medium
sheets_clear_values	Clear all values in a range (preserves formatting)	medium
sheets_insert_rows	Insert blank or pre-filled rows at a specific position	medium
sheets_delete_columns	Delete one or more columns using a full-column A1 range	high

Compatibility

Client	Local	Docker	Remote	Read-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

›What are the technical requirements to run the Gsheets MCP server?

You need Node.js version 20 or higher, npm, and a Google Cloud project with the Google Sheets API enabled.

›How do I grant the server access to my Google Sheets?

You must create a service account in your Google Cloud project and share the specific spreadsheets you want to access with the service account email, granting it 'Editor' permissions.

›Can I authenticate without using a physical credential file?

Yes, you can provide the service account credentials directly as a JSON string using the GOOGLE_SERVICE_ACCOUNT_KEY environment variable instead of a file path.

›What specific operations does this server support?

The server supports reading, writing, and managing spreadsheets, including advanced operations like batch processing, formatting, charts, and conditional formatting.