mcpField
E
Excel MCP Server

Excel MCP Server

Local
github.com/yzflyData & Analytics95Updated 17w ago

About Excel MCP Server

Excel MCP Server provides MCP tools for reading, analyzing, visualizing and writing Excel data across XLSX, XLS, CSV, TSV and JSON formats. It suits users who want to work with spreadsheet data through natural language.

Key features

  1. 01Reads XLSX, XLS, CSV, TSV and JSON files
  2. 02Offers statistics, data quality checks and pivot tables
  3. 03Generates charts and exports them as images
  4. 04Writes and updates Excel files

Use cases

  1. 01Analyzing a sales data file through natural language
  2. 02Filtering spreadsheet rows by conditions
  3. 03Creating a pivot table and bar chart of department sales

MCP support

The server exposes Excel reading, analysis and writing as MCP tools, resources and prompt templates.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Excel MCP Server

An MCP server that provides comprehensive Excel file management and data analysis capabilities.

Features

  • Excel File Operations

    • Read multiple Excel formats (XLSX, XLS, CSV, TSV, JSON)
    • Write and update Excel files
    • Get file information and sheet names
  • Data Analysis

    • Summary statistics and descriptive analysis
    • Data quality assessment
    • Pivot tables
    • Filtering and querying data
  • Visualization

    • Generate charts and plots from Excel data
    • Create data previews
    • Export visualizations as images

Installation

  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
  1. Install dependencies:
# Using uv
uv pip install -e .

Integration with Claude Desktop

  1. Install Claude Desktop
  2. Open Settings and go to the Developer tab
  3. Edit claude_desktop_config.json:
{
  "mcpServers": {
      "command": "uvx",
      "args": [
        "mcp-excel-server"
      ],
      "env": {
        "PYTHONPATH": "/path/to/your/python"
      }
  }
}

Available Tools

File Reading
  • read_excel: Read Excel files
  • get_excel_info: Get file details
  • get_sheet_names: List worksheet names
Data Analysis
  • analyze_excel: Perform statistical analysis
  • filter_excel: Filter data by conditions
  • pivot_table: Create pivot tables
  • data_summary: Generate comprehensive data summary
Data Visualization
  • export_chart: Generate charts
    • Supports line charts, bar charts, scatter plots, histograms
File Operations
  • write_excel: Write new Excel files
  • update_excel: Update existing Excel files

Available Resources

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

Prompt Templates

  • analyze_excel_data: Guided template for Excel data analysis
  • create_chart: Help create data visualizations
  • data_cleaning: Assist with data cleaning

Usage Examples

  • "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"

Security Considerations

  • Read files only from specified paths
  • Limit file size
  • Prevent accidental file overwriting
  • Strictly control data transformation operations

Dependencies

  • pandas
  • numpy
  • matplotlib
  • seaborn

License

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.