Skip to main content
Glama
MCP Excel Reader

MCP Excel Reader

MCP Excel Reader

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.

Features

  • 📊 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

Related MCP server: Excel MCP Server

Installation

Installing via Smithery

To install Excel Reader for Claude Desktop automatically via Smithery:

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

As an MCP Server

  1. Install globally:

npm install -g @archimdescrypto/excel-reader
  1. Add to your MCP settings file (usually at ~/.config/claude/settings.json or equivalent):

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

For Development

  1. Clone the repository:

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

npm install
  1. Build the project:

npm run build

Usage

Usage

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[];
    };
  };
}

Basic Usage

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.

Features

  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

Extending with SheetJS Features

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

Available Extensions

  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.

Contributing

  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

License

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

Acknowledgments

Available Tools

1 tool
read_excelB

Read an Excel file and return its contents as structured data

Inputs: filePath (required), sheetName, startRow, maxRows.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'read_excel' has a clear and distinct purpose that cannot be confused with any other tool in the set.

    Naming Consistency5/5

    The single tool name 'read_excel' follows a clear verb_noun pattern. Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions to evaluate.

    Tool Count2/5

    A single tool is generally too few for a server named 'MCP Excel Reader', as it suggests a limited scope that may not support typical Excel-related workflows like writing, updating, or querying data. This feels thin for the apparent domain.

    Completeness2/5

    The tool surface is severely incomplete for an Excel reader domain. While reading is covered, there are significant gaps such as writing, editing, formatting, or analyzing Excel files, which will likely cause agent failures in broader tasks.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables reading and searching Excel files through MCP-compatible clients. Provides tools to retrieve workbook metadata, read sheet contents, and search across all sheets using absolute file paths.
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server for reading and inspecting local Excel files (.xlsx, .xlsm, .xls, .xlsb, .ods) with tools for inspecting metadata, reading ranges, and profiling structure.
      3
      6 npm
      MIT