Skip to main content
Glama
ArchimedesCrypto

MCP Excel Reader

Lector de Excel MCP

insignia de herrería Un servidor de Protocolo de Contexto de Modelo (MCP) para leer archivos de Excel con fragmentación y paginación automáticas. Desarrollada con SheetJS y TypeScript, esta herramienta le ayuda a gestionar archivos grandes de Excel de forma eficiente, dividiéndolos automáticamente en fragmentos manejables.

Características

  • 📊 Leer archivos Excel (.xlsx, .xls) con límites de tamaño automáticos

  • 🔄 Fragmentación automática para grandes conjuntos de datos

  • 📑 Selección de hojas y paginación de filas

  • 📅 Manejo adecuado de fechas

  • ⚡ Optimizado para archivos grandes

  • 🛡️ Manejo de errores y validación

Related MCP server: Excel MCP Server

Instalación

Instalación mediante herrería

Para instalar Excel Reader para Claude Desktop automáticamente a través de Smithery :

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

Como servidor MCP

  1. Instalar globalmente:

npm install -g @archimdescrypto/excel-reader
  1. Agregue a su archivo de configuración de MCP (generalmente en ~/.config/claude/settings.json o equivalente):

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

Para el desarrollo

  1. Clonar el repositorio:

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

npm install
  1. Construir el proyecto:

npm run build

Uso

Uso

El lector de Excel proporciona una única herramienta read_excel con los siguientes parámetros:

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[];
    };
  };
}

Uso básico

Cuando se utiliza con Claude u otra IA compatible con MCP:

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

La IA utilizará la herramienta para leer el archivo y gestionará automáticamente la fragmentación de archivos grandes.

Características

  1. Fragmentación automática

    • Divide automáticamente archivos grandes en fragmentos manejables

    • Tamaño de fragmento predeterminado de 100 KB

    • Proporciona metadatos para la paginación.

  2. Selección de hojas

    • Leer hojas específicas por nombre

    • El valor predeterminado es la primera hoja si no se especifica

  3. Paginación por filas

    • Controle qué filas leer con startRow y maxRows

    • Obtenga información del siguiente fragmento para una lectura continua

  4. Manejo de errores

    • Valida la existencia y el formato del archivo.

    • Proporciona mensajes de error claros

    • Maneja archivos de Excel malformados con elegancia

Ampliación con funciones de SheetJS

El lector de Excel está basado en SheetJS y se puede ampliar con sus potentes funciones:

Extensiones disponibles

  1. Manejo de fórmulas

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

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

    // Access data validation rules
    const validation = worksheet['!dataValidation'];
  4. Características de la hoja

    • Celdas fusionadas: worksheet['!merges']

    • Filas/columnas ocultas: worksheet['!rows'] , worksheet['!cols']

    • Protección de hoja: worksheet['!protect']

Para conocer más funciones y documentación detallada, visita la Documentación de SheetJS .

Contribuyendo

  1. Bifurcar el repositorio

  2. Crea tu rama de funciones ( git checkout -b feature/amazing-feature )

  3. Confirme sus cambios ( git commit -m 'Add some amazing feature' )

  4. Empujar a la rama ( git push origin feature/amazing-feature )

  5. Abrir una solicitud de extracción

Licencia

Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.

Expresiones de gratitud

Available Tools

1 tool
read_excelB

Read an Excel file and return its contents as structured data

ParametersJSON Schema
NameRequiredDescriptionDefault
filePathYesPath to the Excel file to read
sheetNameNoName of the sheet to read (optional)
startRowNoStarting row index (optional)
maxRowsNoMaximum number of rows to read (optional)

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions reading and returning data, implying a read-only operation, but fails to address critical aspects like error handling (e.g., what happens if the file doesn't exist or is corrupted), performance considerations, or format specifics of the returned structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded with the core functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (4 parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks details on behavioral traits and output format, which are important for a data-reading tool without structured output documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the input schema already documents all parameters thoroughly. The description adds no additional meaning beyond what the schema provides, such as examples or usage tips for the parameters, meeting the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Read') and resource ('an Excel file') with the outcome ('return its contents as structured data'). It's specific about what the tool does, but since there are no sibling tools mentioned, it cannot demonstrate differentiation from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or exclusions. It simply states what the tool does without context for usage decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 1 tool update
    • First observedread_excel

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
ResponsivenessUnresponsive

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
    Not graded
    quality
    D
    maintenance
    MCP server for reading and writing .xls (Excel 97-2003) files, enabling data manipulation, sheet listing, and metadata retrieval.
    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
    5 npm
    MIT