Excel MCP server

Enables Excel file manipulation capabilities including workbook creation, data manipulation, formatting, charts, and pivot tables without requiring Microsoft Excel installation.
Back to servers
Provider
Haris Musa
Release date
Mar 17, 2025
Language
Python
Stats
4 stars

The Excel MCP Server provides Excel file manipulation capabilities without requiring Microsoft Excel installation. It allows you to create workbooks, manipulate data, apply formatting, and use advanced Excel features through a Model Context Protocol server built on OpenPyXL.

Requirements

  • Python 3.10+
  • MCP SDK 1.2.0+
  • OpenPyXL 3.1.2+

Installation and Setup

Environment Configuration

Before running the server, you can configure where Excel files will be stored using an environment variable:

  • EXCEL_FILES_PATH: Directory where Excel files will be stored (default: ./excel_files)

Set this variable according to your operating system:

Windows CMD:

set EXCEL_FILES_PATH=C:\path\to\excel\files
uv run excel-mcp-server

Windows PowerShell:

$env:EXCEL_FILES_PATH="C:\path\to\excel\files"
uv run excel-mcp-server

Linux/MacOS:

export EXCEL_FILES_PATH=/path/to/excel/files
uv run excel-mcp-server

Claude Desktop Configuration

You can also configure the server in Claude Desktop's configuration:

{
  "mcpServers": {
    "excel": {
      "command": "uv run excel-mcp-server",
      "transport": "sse",
      "env": {
        "EXCEL_FILES_PATH": "/path/to/excel/files"
      }
    }
  }
}

Usage

Starting the Server

To start the server, run:

uv run excel-mcp-server

The server will start in SSE mode and wait for connections from MCP clients.

Connecting in Cursor IDE

Once the server is running, connect to the SSE endpoint in Cursor IDE:

http://localhost:8000/sse

Available Capabilities

The Excel MCP server provides tools for:

  • Workbook and worksheet management: Create, open, and modify Excel workbooks
  • Data operations: Read, write, and transform data in worksheets
  • Formatting and styling: Apply formatting to cells and ranges
  • Visualizations: Create charts and graphs
  • Data analysis: Build and manipulate pivot tables

Working with Excel Files

The server creates and manipulates Excel workbooks through OpenPyXL, allowing you to:

  • Create new workbooks or open existing ones
  • Manage worksheets within workbooks
  • Work with ranges of cells
  • Apply formatting and styles
  • Create and customize charts and pivot tables

For detailed documentation of all available tools, their parameters, and usage examples, refer to the TOOLS.md file in the project repository.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later