Skip to main content

This is a MCP server tool for ai to automate microsoft excel application

Project description

ExcelMCP

ExcelMCP server is designed for AI to Automate Microsoft Excel Application in Windows OS. Not working on Linux/MacOS.

Installation

There are two ways or two modes to install ExcelMCP (They also can be used in the same time):

1. User ExcelMCP as stdio server:

  • One ExcelMCP server for One MCP Client mode
  • Put following setting to MCP.json file for vscode or some proper place for other AI IDE:
{
    "servers": {
        "ExcelMCP": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "excelmcp"
            ]
        }
    }
}

2. User ExcelMCP as sse server:

  • One ExcelMCP server for multi MCP Client mode
  • You can change port and host as you like

step 1:

Run one command in shell or power shell:

uvx excelmcp sse

With "url": "http//127.0.0.1:8000/sse"

or

uvx excelmcp sse --port 8009

or

uvx excelmcp sse 8009

or

uvx excelmcp sse --port 8009 --host 127.0.0.1

With "url": "http//127.0.0.1:8009/sse"

setp 2:

Put following setting to MCP.json file for vscode or some proper place for other AI IDE:

{
    "servers": {
        "ExcelMCP": {
            "url": "http//127.0.0.1:8009/sse"
        }
    }
}

Usage

On AI IDE, you can ask AI modle to control Excel Application by ExcelMCP server:

  • You ask AI modle to open a new Excel Application. AI modle will send a request to ExcelMCP server, and ExcelMCP server will open a new Excel Application.

  • You ask AI modle to do whatever you want to do in the current Excel Application. AI modle will analye your request, and call ExcelMCP server's tool to accomplish your request.

Tools Reference

Tools:

  • Installed(): chedk if Excel Application is installed on your computer.

  • Launch(...): launch a new Excel Application and set it's visibility.

  • Visible(): set the current Excel Application's visibility to True or False.

  • Quit(): quit the current Excel Application.

  • WorkBook(BookPath:=None): create a new Excel WorkBook if BootPath is None or empty and open or save an Excel WorkBook as the BookPath refer to.

  • There're some other tools not mentioned here.

  • RunPython(...): run python code in the current Excel Application.

    • This is most powerful tool in ExcelMCP server. AI can use this tool to do whatever you want to do in the current Excel Application.
    • There's an Global variable named class instance "The" in the python code, "The.Excel" hold the current Excel Application,
    • The openpyxl library is imported in the python code, so you can use openpyxl to manipulate excel files.
  • More other tools will be added in the future.

Development

git clone https://github.com/officemcp/excelmcp

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

excelmcp-1.0.1.tar.gz (5.5 MB view details)

Uploaded Source

Built Distribution

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

excelmcp-1.0.1-py3-none-any.whl (5.1 kB view details)

Uploaded Python 3

File details

Details for the file excelmcp-1.0.1.tar.gz.

File metadata

  • Download URL: excelmcp-1.0.1.tar.gz
  • Upload date:
  • Size: 5.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.16

File hashes

Hashes for excelmcp-1.0.1.tar.gz
Algorithm Hash digest
SHA256 b0fb8bac3b8974a1f3fc0f2bb38f354f70cdfacb31f7c24e1ada49a4e828934c
MD5 de1a8ef1cfeefa2a85e9a285da0fa938
BLAKE2b-256 96a0e6a3ce239706fdfbf804bb8fc82b0fccad4f0740d58ab5d943d279a9ab9f

See more details on using hashes here.

File details

Details for the file excelmcp-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: excelmcp-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 5.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.16

File hashes

Hashes for excelmcp-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d105f8975d8be6e9c8c1675311208cfaf3cfd2ea1e73789159eeabc6005ee0e4
MD5 23c3389e84688cc9c40687b508a52887
BLAKE2b-256 c95a13a26985ccc37c909d62ce387ea21ad2dacc17bb7684bf7d36686afe6823

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