excel-mcp-server

excel-mcp-server

Enables AI assistants to automate Microsoft Excel tasks such as reading/writing cells, formatting, creating charts, and managing sheets through natural language using the Model Context Protocol.

Category
访问服务器

README

Excel MCP Server

License Python Platform

🇨🇳 中文文档 | 🇺🇸 English

A Model Context Protocol (MCP) server for Microsoft Excel automation. Control Excel directly through AI assistants using natural language — read cells, write formulas, apply formatting, create charts, manage sheets, and 90+ more operations.

Features

Read & Write

  • Read cell values, formulas, styles, merged cells
  • Set values and formulas with auto type detection
  • Copy, paste, find & replace

Formatting & Styles

  • Font, color, alignment, borders, number formats
  • Conditional formatting (cell value, formula, databar, color scale, icon set, top/bottom, duplicates, etc.)
  • Cell styles (gradient fill, pattern fill, tint/shade, diagonal borders, built-in styles)
  • Row height, column width, format copying

Data Operations

  • Sort (single & multi-column), auto filter
  • Remove duplicates, text-to-columns, fill series
  • Subtotals, grouping/ungrouping, outline levels
  • Data validation (list, number, date, time, text length, custom formula)

Charts

  • Create, edit, delete charts (column, bar, line, pie, scatter, area, doughnut, radar)
  • Deep editing: trendlines, single-point coloring, data labels, axis config, gridlines
  • Export chart as image

Tables (ListObject)

  • Create, style, resize Excel tables
  • Total row with custom aggregation functions
  • Convert tables to/from ranges

Shapes & Textboxes

  • Insert, edit, move, delete shapes (rectangle, oval, triangle, star, arrow, etc.)
  • Insert and edit textboxes with full formatting

Page Layout & Print

  • Page setup (orientation, paper size, margins, zoom, fit-to-pages)
  • Print area, print titles, page breaks
  • Headers & footers with dynamic fields (date, page number, sheet name)

Sheet Management

  • Add, delete, rename, copy, hide, show, activate worksheets
  • Tab color, zoom, gridlines, headings visibility
  • Split windows, freeze panes, calculation mode

Workbook Properties

  • Set document properties (title, author, keywords, etc.)
  • Formula auditing (trace precedents, trace dependents)
  • Named ranges, comments, hyperlinks, protection

Quick Start

Prerequisites

  • Windows with Microsoft Excel installed and running
  • Python 3.10+
  • An MCP-compatible AI client (Claude Desktop, Cursor, etc.)

Install

git clone https://github.com/yaoyuansh/excel-mcp-server.git
cd excel-mcp-server
pip install -e .

Configure MCP Client

Claude Code:

claude mcp add excel-mcp-server -s user -- uv run --directory C:/path/to/excel-mcp-server excel-mcp-server

Or use the equivalent JSON configuration:

{
  "mcpServers": {
    "excel-mcp-server": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "C:/path/to/excel-mcp-server",
        "excel-mcp-server"
      ]
    }
  }
}

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "excel-mcp-server": {
      "command": "python",
      "args": ["-m", "excel_mcp.server"],
      "cwd": "C:/path/to/excel-mcp-server/src"
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "excel-mcp-server": {
      "command": "python",
      "args": ["-m", "excel_mcp.server"],
      "cwd": "C:/path/to/excel-mcp-server/src"
    }
  }
}

Tools

Tool Description
list_workbooks List all open Excel workbooks
list_sheets List worksheets with used ranges
read_sheet Read data, styles, charts, tables, shapes, validations, filters, print settings
edit_sheet Edit with 90+ actions (values, formulas, formatting, charts, tables, shapes, page layout, etc.)
manage_sheets Add, delete, rename, copy, hide, show, activate worksheets

See docs/TOOLS.md for full API reference.

Architecture

┌─────────────────┐     stdio/HTTP      ┌──────────────────┐
│  AI Assistant   │ ◄──────────────────► │  MCP Server      │
│  (Claude/Cursor)│                      │  (server.py)     │
└─────────────────┘                      └────────┬─────────┘
                                                  │
                                          ┌───────▼─────────┐
                                          │  Excel Core      │
                                          │  (excel_core.py) │
                                          │  win32com COM    │
                                          └───────┬─────────┘
                                                  │ COM API
                                          ┌───────▼─────────┐
                                          │  Microsoft Excel │
                                          │  (running app)   │
                                          └─────────────────┘

Project Structure

excel-mcp-server/
├── .gitignore              # Git ignore rules
├── README.md              # English documentation
├── README_CN.md           # 中文文档
├── LICENSE                # Apache 2.0
├── pyproject.toml         # Python packaging config
├── docs/
│   └── TOOLS.md           # Full API reference (EN + CN)
├── tests/                 # Regression and metadata tests
└── src/
    └── excel_mcp/
        ├── __init__.py    # Package init
        ├── server.py      # MCP server (5 tools)
        └── excel_core.py  # Excel operations engine (90+ actions)

Development

Run the regression test suite:

pip install -e ".[dev]"
pytest

The tests cover package import, MCP tool schemas, license metadata consistency, and protection against accidental lowercase JSON literals (true / false / null) in Python code.

License

Apache 2.0 — see LICENSE

Copyright 2026 yaoyuansh

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选