Skip to main content
Glama
Sign In
deenesjakoruzh
Excel MCP Server

Excel MCP Server

by yzfly
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Excel MCP 服务器

提供全面的 Excel 文件管理和数据分析功能的 MCP 服务器。

特征

  • Excel文件操作

    • 读取多种 Excel 格式（XLSX、XLS、CSV、TSV、JSON）

    • 编写和更新 Excel 文件

    • 获取文件信息和工作表名称

  • 数据分析

    • 汇总统计和描述分析

    • 数据质量评估

    • 数据透视表

    • 过滤和查询数据

  • 可视化

    • 从 Excel 数据生成图表和绘图

    • 创建数据预览

    • 将可视化结果导出为图像

Related MCP server: Excel MCP Server

安装

  1. 创建新的 Python 环境（推荐）：

# 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. 安装依赖项：

# Using uv
uv pip install -r requirements.txt

# Or using pip
pip install -r requirements.txt

与 Claude Desktop 集成

  1. 安装Claude Desktop

  2. 打开“设置”并转到“开发人员”选项卡

  3. 编辑claude_desktop_config.json ：

{
  "mcpServers": {
      "command": "uvx",
      "args": [
        "mcp-excel-server"
      ],
      "env": {
        "PYTHONPATH": "/path/to/your/python"
      }
  }
}

可用工具

文件读取

  • read_excel ：读取 Excel 文件

  • get_excel_info ：获取文件详细信息

  • get_sheet_names ：列出工作表名称

数据分析

  • analyze_excel ：执行统计分析

  • filter_excel ：按条件过滤数据

  • pivot_table ：创建枢轴表

  • data_summary ：生成全面的数据摘要

数据可视化

  • export_chart ：生成图表

    • 支持折线图、条形图、散点图、直方图

文件操作

  • write_excel ：写入新的 Excel 文件

  • update_excel ：更新现有的 Excel 文件

可用资源

  • excel://{file_path} ：获取文件内容

  • excel://{file_path}/info ：获取文件结构信息

  • excel://{file_path}/preview ：生成数据预览图

提示模板

  • analyze_excel_data ：Excel 数据分析的指导模板

  • create_chart ：帮助创建数据可视化

  • data_cleaning ：协助数据清理

使用示例

  • “分析我的sales_data.xlsx文件”

  • “为 product_sales.csv 创建条形图”

  • “在employees.xlsx中筛选出30岁以上的员工”

  • “生成部门销售额数据透视表”

安全注意事项

  • 仅从指定路径读取文件

  • 限制文件大小

  • 防止意外文件覆盖

  • 严格控制数据转换操作

依赖项

  • 熊猫

  • numpy

  • matplotlib

  • 西伯恩

执照

MIT 许可证

Available Tools

8 tools
analyze_excelC
Perform statistical analysis on Excel data.

Args:
    file_path: Path to the Excel file
    columns: Comma-separated list of columns to analyze (analyzes all numeric columns if None)
    sheet_name: Name of the sheet to analyze (for Excel files)
    
Returns:
    JSON string with statistical analysis

Inputs: file_path (required), columns, sheet_name.

data_summaryC
Generate a comprehensive summary of the data in an Excel file.

Args:
    file_path: Path to the Excel file
    sheet_name: Name of the sheet to summarize (for Excel files)
    
Returns:
    Comprehensive data summary as string

Inputs: file_path (required), sheet_name.

export_chartB
Create a chart from Excel data and return as an image.

Args:
    file_path: Path to the Excel file
    x_column: Column to use for x-axis
    y_column: Column to use for y-axis
    chart_type: Type of chart ('line', 'bar', 'scatter', 'hist')
    sheet_name: Name of the sheet to chart (for Excel files)
    
Returns:
    Chart as image

Inputs: file_path (required), x_column (required), y_column (required), chart_type, +1 more.

filter_excelB
Filter Excel data using a pandas query string.

Args:
    file_path: Path to the Excel file
    query: Pandas query string (e.g., "Age > 30 and Department == 'Sales'")
    sheet_name: Name of the sheet to filter (for Excel files)
    
Returns:
    Filtered data as string

Inputs: file_path (required), query (required), sheet_name.

pivot_tableB
Create a pivot table from Excel data.

Args:
    file_path: Path to the Excel file
    index: Column to use as the pivot table index
    columns: Optional column to use as the pivot table columns
    values: Column to use as the pivot table values
    aggfunc: Aggregation function ('mean', 'sum', 'count', etc.)
    sheet_name: Name of the sheet to pivot (for Excel files)
    
Returns:
    Pivot table as string

Inputs: file_path (required), index (required), columns, values, +2 more.

read_excelA
Read an Excel file and return its contents as a string.

Args:
    file_path: Path to the Excel file
    sheet_name: Name of the sheet to read (only for .xlsx, .xls)
    nrows: Maximum number of rows to read
    header: Row to use as header (0-indexed)
    
Returns:
    String representation of the Excel data

Inputs: file_path (required), sheet_name, nrows, header.

update_excelC
Update an existing Excel file with new data.

Args:
    file_path: Path to the Excel file to update
    data: New data in CSV or JSON format
    sheet_name: Name of the sheet to update (for Excel files)
    format: Format of the input data ('csv' or 'json')
    
Returns:
    Confirmation message

Inputs: file_path (required), data (required), sheet_name, format.

write_excelB
Write data to an Excel file.

Args:
    file_path: Path to save the Excel file
    data: Data in CSV or JSON format
    sheet_name: Name of the sheet (for Excel files)
    format: Format of the input data ('csv' or 'json')
    
Returns:
    Confirmation message

Inputs: file_path (required), data (required), sheet_name, format.

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    B3.4/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools have distinct purposes like reading, writing, filtering, and analyzing Excel data, but analyze_excel and data_summary overlap significantly as both perform data analysis/summarization. The descriptions help differentiate them slightly, but an agent might struggle to choose between them for basic statistical tasks.

    Naming Consistency5/5

    All tools follow a consistent verb_noun or verb_excel pattern (e.g., read_excel, update_excel, filter_excel, pivot_table). The naming is predictable and readable throughout, with no mixing of conventions like camelCase or snake_case deviations.

    Tool Count5/5

    With 8 tools, this server is well-scoped for Excel operations, covering core tasks like reading, writing, updating, filtering, analyzing, summarizing, charting, and pivoting. Each tool earns its place without feeling excessive or insufficient for the domain.

    Completeness4/5

    The toolset provides strong coverage for Excel data manipulation and analysis, including CRUD-like operations (read, write, update) and advanced features (pivot tables, charts). A minor gap exists in lacking tools for specific Excel formatting or cell-level edits, but agents can work around this with the available tools.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Excel MCP Server

      jauinones
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for manipulating Excel files that features a headless engine for real-time formula calculation and data validation. It enables users to create, read, and manage workbooks, sheets, and charts without requiring Microsoft Excel installed.
      26 npm
      MIT

    • Excel Tools MCP

      Glosc
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for reading, writing, and analyzing Excel files using Python, pandas, and openpyxl. It enables tasks such as managing multiple worksheets, performing structural data analysis, and creating new files from JSON data.
      MIT

    • xls-mcp-servers

      Lincyghb
      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

    Appeared in Searches