xlsx-drive-mcp

xlsx-drive-mcp

An MCP server that lets AI agents read and write .xlsx files stored on Google Drive.

Category
Visit Server

README

xlsx-drive-mcp

An MCP server that lets AI agents (Claude and others) read and write .xlsx files stored on Google Drive. Fills the gap between Excel MCP servers (local files only) and Google Drive MCP servers (native Google Sheets only).

Features

  • Read/write cell values, formulas, formatting, charts
  • Full sheet management (create, delete, rename, copy)
  • Google Drive authentication with zero extra setup for existing workspace-mcp users
  • Conflict detection on concurrent edits

Installation

pip install xlsx-drive-mcp

Requires Python 3.10+.

Authentication

Option A: Existing workspace-mcp users (zero extra setup)

If you already use workspace-mcp, credentials are reused automatically. Skip to Claude Config below.

Option B: Standalone setup

  1. Go to Google Cloud Console
  2. Create a project (or use an existing one)
  3. Enable the Google Drive API
  4. Create credentials: OAuth client ID → Desktop app
  5. Download the client ID and secret, then:
export GOOGLE_CLIENT_ID=your_client_id
export GOOGLE_CLIENT_SECRET=your_client_secret
xlsx-drive-mcp auth --user you@example.com

This opens a browser, completes the OAuth flow, and stores credentials at ~/.xlsx-drive-mcp/credentials/you@example.com.json.

Add to your global .gitignore:

~/.xlsx-drive-mcp/

Claude Config

{
  "mcpServers": {
    "xlsx-drive": {
      "command": "xlsx-drive-mcp",
      "args": ["--user", "your-actual-email@example.com"]
    }
  }
}

Replace your-actual-email@example.com with the email you authenticated with. If you have only one credential file, --user can be omitted.

Scope note

  • workspace-mcp users inherit workspace-mcp's scope, which is typically full Drive access.
  • Standalone users get drive.file scope -- access only to files this app created or opened. With drive.file scope, list_xlsx_files only returns files you've previously opened with this tool. To search all Drive files, use full drive scope or the workspace-mcp path.

Finding a folder_id

Open any Drive folder in your browser. The URL looks like: https://drive.google.com/drive/folders/1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74 The folder_id is the last segment: 1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74.

Important warnings

  • write_range over formula cells replaces formulas with static values.
  • read_range with data_only=true (default) returns cached values, not live formula results. Use data_only=false to get formula strings instead.
  • copy_sheet silently drops charts and images from the copied sheet (openpyxl limitation).
  • delete_xlsx moves the file to trash. The user has 30 days to recover it from Drive UI.

Tool reference

Tool Description
list_xlsx_files Search Drive for xlsx files
get_xlsx_info Sheet names, data dimensions, named ranges
create_xlsx Create a new blank xlsx on Drive
delete_xlsx Move an xlsx to trash
list_sheets List all sheets
create_sheet Add a new sheet
delete_sheet Remove a sheet
rename_sheet Rename a sheet
copy_sheet Duplicate a sheet (drops charts/images)
read_range Read cell values
write_range Write cell values
append_rows Append rows below last data
clear_range Clear values, preserve formatting
read_format Read cell formatting (colors, bold, borders)
format_range Apply formatting to a range
set_column_width Set column widths
set_row_height Set row heights
merge_cells Merge a cell range
unmerge_cells Unmerge a cell range
create_chart Create a bar, line, pie, or scatter chart
write_formula Write a formula to a single cell

Troubleshooting

MCP server won't start / tool not found: Claude Desktop launches MCP servers as background processes with no visible output. To see server logs, run the server manually:

xlsx-drive-mcp --user your@email.com

Any errors will appear in the terminal.

list_xlsx_files returns no results: With drive.file scope, only files this app created or previously opened are visible. Use get_xlsx_info(file_id) directly with a known file_id from the Drive URL instead.

Shared Drive / Team Drive: Not officially tested in v1. May work; not supported. Open an issue if you test it.

Service accounts: Not supported in v1. Tracked as a roadmap item.

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