macOS Office 365 MCP Server

macOS Office 365 MCP Server

Enables AI assistants to create and manipulate Microsoft Office documents (PowerPoint, Word, Excel) on macOS via AppleScript automation.

Category
访问服务器

README

macOS Office 365 MCP Server

A Model Context Protocol (MCP) server that enables AI assistants to create and manipulate Microsoft Office documents (PowerPoint, Word, and Excel) on macOS. This is a Proof of Concept and a personal project that is not an official MCP Server. Let me know if you have any issues.

LinkedIn: https://www.linkedin.com/in/bluhmadam/

Features

PowerPoint

  • Create presentations with custom titles and themes
  • Add slides with various layouts
  • Insert text, images, and speaker notes
  • Save presentations in multiple formats

Word

  • Create documents from scratch or templates
  • Add headings, paragraphs, lists, and tables
  • Apply text formatting and styles
  • Save documents in multiple formats

Excel

  • Create workbooks with multiple worksheets
  • Write data to cells and ranges
  • Add formulas and calculations
  • Create charts (bar, line, pie)
  • Apply cell formatting and styles
  • Save workbooks in multiple formats

Prerequisites

System Requirements

  • macOS 10.15 or later
  • Python 3.8 or later
  • Microsoft Office for Mac (PowerPoint, Word, and/or Excel)

Python Dependencies

pip install mcp
pip install python-pptx
pip install python-docx
pip install openpyxl
pip install aiofiles

Installation

  1. Clone the repository

    git clone https://github.com/vAirpower/macos-office365-mcp-server.git
    cd macos-office365-mcp-server
    
  2. Install dependencies

    pip install -r requirements.txt
    
  3. Set up macOS permissions

    The server uses AppleScript to control Office applications. You need to grant permissions:

    a. Open System PreferencesSecurity & PrivacyPrivacy b. Select Automation in the left sidebar c. Find your terminal application (Terminal, iTerm2, VS Code, etc.) d. Check the boxes for:

    • Microsoft PowerPoint
    • Microsoft Word
    • Microsoft Excel

    If prompted when first running the server, click "OK" to allow automation.

Configuration

MCP Client Configuration

Add the server to your MCP client configuration:

For Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "office365": {
      "command": "python",
      "args": ["/path/to/macos-office365-mcp-server/src/office365_mcp_server.py"]
    }
  }
}

For Cline (VS Code)

Edit your Cline MCP settings:

{
  "mcpServers": {
    "office365": {
      "command": "python",
      "args": ["/path/to/macos-office365-mcp-server/src/office365_mcp_server.py"]
    }
  }
}

Usage

Once configured, the AI assistant can use the following tools:

PowerPoint Tools

  • create_presentation - Create a new presentation
  • add_slide - Add a slide to a presentation
  • add_text_to_slide - Add text content to a slide
  • add_image_to_slide - Add an image to a slide
  • add_speaker_notes - Add speaker notes to a slide
  • save_presentation - Save the presentation to a file

Word Tools

  • create_document - Create a new document
  • add_heading - Add a heading to a document
  • add_paragraph - Add a paragraph with optional formatting
  • add_list - Add a bulleted or numbered list
  • add_table - Add a table with data
  • save_document - Save the document to a file

Excel Tools

  • create_workbook - Create a new workbook
  • add_worksheet - Add a worksheet to a workbook
  • write_cell - Write data to a specific cell
  • write_range - Write data to a range of cells
  • add_formula - Add a formula to a cell
  • create_chart - Create a chart from data
  • save_workbook - Save the workbook to a file
  • list_worksheets - List all worksheets in a workbook

Utility Tools

  • list_active_presentations - List all open presentations
  • list_active_documents - List all open documents
  • list_active_workbooks - List all open workbooks
  • check_office_status - Check if Office apps are available

Example Usage

Creating a PowerPoint Presentation

# AI Assistant can execute:
result = await create_presentation(
    title="Q4 Sales Report",
    theme="modern"
)

slide = await add_slide(
    presentation_id=result["presentation_id"],
    layout="Title and Content"
)

await add_text_to_slide(
    slide_id=slide["slide_id"],
    text="Revenue increased by 25%",
    placeholder="content"
)

await save_presentation(
    presentation_id=result["presentation_id"],
    file_path="~/Desktop/Q4_Sales.pptx"
)

Creating a Word Document

# AI Assistant can execute:
doc = await create_document(title="Project Proposal")

await add_heading(
    document_id=doc["document_id"],
    text="Executive Summary",
    level=1
)

await add_paragraph(
    document_id=doc["document_id"],
    text="This proposal outlines our approach...",
    formatting={"font_size": 12, "font_name": "Arial"}
)

await save_document(
    document_id=doc["document_id"],
    file_path="~/Desktop/proposal.docx"
)

Creating an Excel Workbook

# AI Assistant can execute:
workbook = await create_workbook(title="Sales Analysis")

# Add data
data = [
    ["Product", "Q1", "Q2", "Q3", "Q4"],
    ["Laptops", 100, 150, 200, 180],
    ["Tablets", 80, 90, 110, 120],
    ["Phones", 200, 250, 300, 350]
]

await write_range(
    workbook_id=workbook["workbook_id"],
    sheet_name="Sheet1",
    start_cell="A1",
    data=data,
    formatting={"bold": True}  # Bold headers
)

# Add a formula
await add_formula(
    workbook_id=workbook["workbook_id"],
    sheet_name="Sheet1",
    cell="F2",
    formula="=SUM(B2:E2)"
)

# Create a chart
await create_chart(
    workbook_id=workbook["workbook_id"],
    sheet_name="Sheet1",
    chart_type="bar",
    data_range="A1:E4",
    chart_title="Quarterly Sales",
    position="G2"
)

await save_workbook(
    workbook_id=workbook["workbook_id"],
    file_path="~/Desktop/sales_analysis.xlsx"
)

Troubleshooting

Permission Issues

If you see "Not authorized to send Apple events", ensure:

  1. Your terminal has automation permissions for Office apps
  2. Office applications are installed and have been opened at least once
  3. You may need to restart your terminal after granting permissions

Import Errors

If you see import errors:

  1. Ensure all dependencies are installed: pip install -r requirements.txt
  2. Check Python version: python --version (should be 3.8+)
  3. Verify MCP is installed: pip show mcp

Office Not Found

If Office applications aren't detected:

  1. Ensure Microsoft Office for Mac is installed
  2. Try opening PowerPoint/Word/Excel manually first
  3. Check if Office is installed in the standard Applications folder

Development

Project Structure

macos-office365-mcp-server/
├── src/
│   ├── office365_mcp_server.py    # Main MCP server
│   ├── controllers/
│   │   ├── powerpoint_controller.py
│   │   ├── word_controller.py
│   │   └── excel_controller.py
│   ├── integrations/
│   │   └── applescript_bridge.py  # AppleScript automation
│   └── utils/
│       ├── config.py
│       ├── logger.py
│       └── validators.py
├── requirements.txt
└── README.md

Adding New Features

  1. Add new methods to the appropriate controller
  2. Register new tools in office365_mcp_server.py
  3. Update this README with usage examples

License

MIT License - see LICENSE file for details

Contributing

Contributions are welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Add tests for new functionality
  4. Submit a pull request

Support

For issues and questions:

  • Open an issue on GitHub
  • Check existing issues for solutions
  • Ensure you've followed all setup steps

Acknowledgments

  • Built with the Model Context Protocol (MCP)
  • Uses python-pptx, python-docx, and openpyxl for document manipulation
  • AppleScript integration for native Office control

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