Excel Data Manager MCP server

The Excel MCP Server is a powerful tool that provides comprehensive Excel file management and data analysis capabilities. It enables you to read various Excel formats, perform data analysis, create visualizations, and manage Excel files through the Claude AI interface.

Installation

Setting Up Environment

1. Create a new Python environment (recommended):

# Using uv (recommended)
uv init excel-mcp-server
cd excel-mcp-server
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Or using pip
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install dependencies:

# Using uv
uv pip install -r requirements.txt

# Or using pip
pip install -r requirements.txt

Integration with Claude Desktop

To connect the MCP server with Claude:

1. Install Claude Desktop
2. Open Settings and navigate to the Developer tab
3. Edit claude_desktop_config.json:

{
  "mcpServers": {
      "command": "uvx",
      "args": [
        "mcp-excel-server"
      ],
      "env": {
        "PYTHONPATH": "/path/to/your/python"
      }
  }
}

Features and Capabilities

File Reading Tools

• read_excel: Reads Excel files in various formats (XLSX, XLS, CSV, TSV, JSON)
• get_excel_info: Retrieves metadata and structure information about Excel files
• get_sheet_names: Lists all worksheet names in an Excel file

Data Analysis Tools

• analyze_excel: Performs statistical analysis on Excel data
• filter_excel: Filters data based on specified conditions
• pivot_table: Creates pivot tables from Excel data
• data_summary: Generates comprehensive data summaries with statistics

Visualization Tools

• export_chart: Generates various chart types from Excel data
  • Supports line charts, bar charts, scatter plots, and histograms

File Operation Tools

• write_excel: Creates new Excel files with specified data
• update_excel: Updates existing Excel files without overwriting everything

Resource Access

Access Excel files and information using these resource patterns:

• excel://{file_path}: Access file content
• excel://{file_path}/info: Get file structure information
• excel://{file_path}/preview: Generate preview image of the data

Usage Examples

Here are some example commands you can use with Claude and the Excel MCP Server:

• "Analyze my sales_data.xlsx file"
• "Create a bar chart for product_sales.csv"
• "Filter employees over 30 in employees.xlsx"
• "Generate a pivot table of department sales"

Prompt Templates

The server includes helpful prompt templates for common tasks:

• analyze_excel_data: Guides you through Excel data analysis
• create_chart: Assists with creating data visualizations
• data_cleaning: Helps with data cleaning operations

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.