A Model Context Protocol (MCP) server for reading Excel files with automatic chunking and pagination support. Built with SheetJS and TypeScript, this tool helps you handle large Excel files efficiently by automatically breaking them into manageable chunks.

• 📊 Read Excel files (.xlsx, .xls) with automatic size limits
• 🔄 Automatic chunking for large datasets
• 📑 Sheet selection and row pagination
• 📅 Proper date handling
• ⚡ Optimized for large files
• 🛡️ Error handling and validation

To install Excel Reader for Claude Desktop automatically via Smithery:

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

1. Install globally:

npm install -g @archimdescrypto/excel-reader

2. Add to your MCP settings file (usually at ~/.config/claude/settings.json or equivalent):

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

1. Clone the repository:

git clone https://github.com/ArchimdesCrypto/mcp-excel-reader.git
cd mcp-excel-reader

2. Install dependencies:

npm install

3. Build the project:

npm run build

The Excel Reader provides a single tool read_excel with the following parameters:

interface ReadExcelArgs {
  filePath: string;      // Path to Excel file
  sheetName?: string;    // Optional sheet name (defaults to first sheet)
  startRow?: number;     // Optional starting row for pagination
  maxRows?: number;      // Optional maximum rows to read
}

// Response format
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[];
    };
  };
}

When used with Claude or another MCP-compatible AI:

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

The AI will use the tool to read the file, automatically handling chunking for large files.

1. Automatic Chunking

   • Automatically splits large files into manageable chunks
   • Default chunk size of 100KB
   • Provides metadata for pagination

2. Sheet Selection

   • Read specific sheets by name
   • Defaults to first sheet if not specified

3. Row Pagination

   • Control which rows to read with startRow and maxRows
   • Get next chunk information for continuous reading

4. Error Handling

   • Validates file existence and format
   • Provides clear error messages
   • Handles malformed Excel files gracefully

The Excel Reader is built on SheetJS and can be extended with its powerful features:

1. Formula Handling

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

2. Cell Formatting

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

3. Data Validation

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

4. Sheet Features

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

For more features and detailed documentation, visit the SheetJS Documentation.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Built with SheetJS
• Part of the Model Context Protocol ecosystem