Excel Reader MCP server

The Excel Reader MCP server helps you efficiently process Excel files in AI applications by automatically handling large spreadsheets through chunking and pagination. It integrates with Claude and other MCP-compatible AI systems to extract and analyze spreadsheet data.

Installation Options

Via Smithery (Recommended for Claude Desktop)

Install automatically using the Smithery CLI:

npx -y @smithery/cli install @ArchimedesCrypto/excel-reader-mcp-chunked --client claude

As a Global MCP Server

1. Install the package globally:

npm install -g @archimdescrypto/excel-reader

2. Add it to your MCP settings file (typically located at ~/.config/claude/settings.json):

{
  "mcpServers": {
    "excel-reader": {
      "command": "excel-reader",
      "env": {}
    }
  }
}

Using the Excel Reader

The Excel Reader provides a single tool called read_excel with these parameters:

• filePath: Path to the Excel file (required)
• sheetName: Name of the sheet to read (optional, defaults to first sheet)
• startRow: Starting row for pagination (optional)
• maxRows: Maximum rows to read (optional)

Basic Usage

When working with Claude or another MCP-compatible AI, you can simply ask:

Read the Excel file at path/to/file.xlsx

The AI will automatically handle file reading and chunking for large files.

Advanced Features

Automatic Chunking

The server automatically handles large files by:

• Breaking them into manageable chunks (default 100KB)
• Providing pagination metadata for navigating through the data
• Handling memory efficiently for large datasets

Sheet Selection and Pagination

You can control which data is read:

• Select specific sheets by name
• Paginate through rows with startRow and maxRows parameters
• Get information about the next available chunk

Error Handling

The server includes robust error handling:

• Validates file existence and format
• Provides clear error messages
• Gracefully handles malformed Excel files

Response Format

The Excel Reader returns data in this structure:

interface ExcelResponse {
  fileName: string;
  totalSheets: number;
  currentSheet: {
    name: string;
    totalRows: number;
    totalColumns: number;
    chunk: {
      rowStart: number;
      rowEnd: number;
      columns: string[];
      data: Record<string, any>[];
    };
    hasMore: boolean;
    nextChunk?: {
      rowStart: number;
      columns: string[];
    };
  };
}

SheetJS Extensions

Since the Excel Reader is built on SheetJS, it supports several advanced features:

Formula Handling

// Enable formula parsing
const wb = XLSX.read(data, {
  cellFormula: true,
  cellNF: true
});

Cell Formatting

// Access cell styles and formatting
const styles = Object.keys(worksheet)
  .filter(key => key[0] !== '!')
  .map(key => ({
    cell: key,
    style: worksheet[key].s
  }));

Data Validation

// Access data validation rules
const validation = worksheet['!dataValidation'];

Sheet Features

• Merged Cells: worksheet['!merges']
• Hidden Rows/Columns: worksheet['!rows'], worksheet['!cols']
• Sheet Protection: worksheet['!protect']

For more information about SheetJS capabilities, visit the SheetJS Documentation.

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.