Skip to main content

MCP server for Excel automation via xlwings COM. Supports DRM-protected files.

Project description

mcp-server-xlwings

MCP server for Excel automation via xlwings COM. Works with DRM-protected files.

License: MIT Python 3.10+

Why xlwings?

Libraries like openpyxl or pandas read .xlsx files directly from disk. This fails when:

  • DRM / file-level encryption is applied (common in enterprise environments)
  • You need to interact with a live Excel session (formulas, macros, add-ins)
  • Files are locked by another process

mcp-server-xlwings uses COM automation to talk to the running Excel process, so it can read and write any file that Excel itself can open -- including DRM-protected documents.

xlwings-exclusive capabilities

These features are impossible with file-based libraries like openpyxl:

  • Read the user's current selection -- see exactly what the user is looking at
  • Get the active workbook -- no need to specify a file path
  • Run VBA macros -- execute existing macros and get their return values
  • Live formula results -- set_formula returns the calculated value immediately
  • Force recalculation -- trigger Excel to recalculate all formulas

Installation

With uvx (recommended)

uvx mcp-server-xlwings

With pip

pip install mcp-server-xlwings

Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "xlwings": {
      "command": "uvx",
      "args": ["mcp-server-xlwings"]
    }
  }
}

Or with a local Python installation:

{
  "mcpServers": {
    "xlwings": {
      "command": "python",
      "args": ["-m", "mcp_server_xlwings"]
    }
  }
}

Claude Code

claude mcp add xlwings -- uvx mcp-server-xlwings

Available Tools (17)

Active Excel (xlwings-exclusive)

Tool Description
get_active_workbook Get info about the currently active workbook, sheet, and selection
read_selection Read data from the cells the user currently has selected
activate_sheet Switch the visible sheet in Excel
run_macro Execute a VBA macro and get its return value
close_workbook Close a workbook, optionally saving first
recalculate Force recalculation of all formulas

Core Workbook

Tool Description
list_open_workbooks List all currently open workbooks
open_workbook Open a file or create a new workbook
save_workbook Save or Save As

Read / Write

Tool Description
read_range Read data from a cell range
write_range Write a 2D array to a cell range
read_cell_info Get detailed cell info (value, formula, format, type)
set_formula Set a formula and get the calculated result immediately
find_replace Search for text, optionally replace it

Sheet & Structure

Tool Description
manage_sheets List, add, delete, rename, or copy sheets
insert_delete_cells Insert or delete rows/columns

Formatting

Tool Description
format_range Apply formatting (bold, italic, underline, color, borders, alignment, wrap text, number format)

Examples

See what the user is working on

"What's in the spreadsheet I have open?"

The agent calls get_active_workbook() to discover the workbook name and sheets, then read_range() to fetch the data.

Read the user's selection

"Summarize the data I've selected"

The agent calls read_selection() to get exactly the cells the user has highlighted.

Run a macro

"Run the UpdateReport macro"

The agent calls run_macro(macro_name="UpdateReport") and returns the result.

Build a summary row

"Add a SUM formula in C10 that totals C2:C9"

The agent calls set_formula(workbook="report.xlsx", cell="C10", formula="=SUM(C2:C9)") and gets back the calculated value.

Format a header row

"Make row 1 bold and centered with a yellow background"

The agent calls format_range(workbook="report.xlsx", cell_range="A1:D1", bold=true, alignment="center", bg_color="#FFFF00").

Insert rows

"Insert 3 blank rows at row 5"

The agent calls insert_delete_cells(workbook="report.xlsx", action="insert", target="row", position=5, count=3).

Requirements

  • Windows (Excel COM automation is Windows-only)
  • Microsoft Excel installed
  • Python 3.10+

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_server_xlwings-0.2.0.tar.gz (69.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_server_xlwings-0.2.0-py3-none-any.whl (11.6 kB view details)

Uploaded Python 3

File details

Details for the file mcp_server_xlwings-0.2.0.tar.gz.

File metadata

  • Download URL: mcp_server_xlwings-0.2.0.tar.gz
  • Upload date:
  • Size: 69.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for mcp_server_xlwings-0.2.0.tar.gz
Algorithm Hash digest
SHA256 bb13b37b7cbbf224be9a2786a42148c08b4b80555d55b3ae18fb91608e987da7
MD5 06ff56b24e124ec8aa4e243fc17315b8
BLAKE2b-256 72572f31157d9c2c0c445f7b7782b0ef6294e09159f36dd86d6e3fc5e7a99cca

See more details on using hashes here.

File details

Details for the file mcp_server_xlwings-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: mcp_server_xlwings-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 11.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for mcp_server_xlwings-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5fc4a0cb77a4f2fe93926284f1d7510886083a328b8be89a3c853941c016b5a3
MD5 f2e5f1c2fb83d5a9c658e502fe082863
BLAKE2b-256 04ce2b7a111050d88a0e28ea882d79587e1b449c42b7368a9b129a48bd67ad35

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page