Excel

Automates Excel workbook creation, editing, formatting, calculations, search, and CSV export via MCP-enabled AI agents.

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "superpyonchix-excel_mcp_server": {
      "command": "node",
      "args": [
        "C:/path/to/excel_mcp_server/dist/index.js"
      ]
    }
  }
}

You can automate Excel tasks with an MCP server that lets AI agents control Excel workbooks through natural language. Create or modify sheets, apply formatting, run calculations, search data, and export results with simple commands you issue to the MCP-enabled AI agent.

How to use

Interact with the MCP server through an MCP client. Describe the Excel action you want in natural language, and the AI agent will translate it into the appropriate workbook operations. Typical tasks include creating a new workbook, adding worksheets, setting cell values, applying formatting, inserting formulas, searching data within sheets, and exporting data to CSV. You can chain these actions in a single instruction to perform end-to-end workflows such as preparing a monthly report, analyzing data, and exporting results for sharing.

How to install

Prerequisites you need before installation:

Node.js (v16 or newer)
A supported operating system: Windows, macOS, or Linux

Step-by-step setup:

# 1. Navigate to the project directory
cd excel_mcp_server

# 2. Install dependencies
npm install

# 3. Build the project
npm run build

Configure your editor to work with Copilot

If you want to connect Copilot in VS Code, add a configuration block to your MCP settings to point to the local server runtime.

{
  "servers": {
    "excel-mcp-server": {
      "type": "stdio",
      "command": "node",
      "args": ["C:/path/to/excel_mcp_server/dist/index.js"]
    }
  }
}

Start or test the local server

After configuring, restart your editor or environment to load the MCP server. You can then ask Copilot to perform actions like creating a new Excel file, adding a sheet, or filling in data. Use practical prompts to verify that the server responds with the expected workbook changes.

Additional notes

If you encounter issues, verify that the build step completed successfully and that your editor can locate the dist/index.js file. Ensure the path in the mcp.json configuration matches your local environment. This setup enables direct, local communication between the editor and the MCP server without external endpoints.

Available tools

create_workbook

Creates a new Excel workbook that you can populate with sheets and data.

get_workbook_info

Retrieves details about a workbook, including the list of sheets and basic properties.

add_worksheet

Adds a new worksheet to an existing workbook.

set_cell_value

Sets a single cell to a specified value.

get_cell_value

Retrieves the value of a single cell.

set_range_values

Writes values to a range of cells in a table-friendly format.

get_range_values

Reads values from a range of cells in a worksheet.

format_cell

Applies formatting to a cell or range, such as font style, background color, and borders.

add_formula

Inserts a formula into a cell to perform calculations.

find_data

Searches for specific data within a worksheet.

export_to_csv

Exports a worksheet or range to a CSV file.