MCP Outlook Tools
A Model Context Protocol server that enables AI assistants to interact with Microsoft Outlook for calendar management, email operations, and search functionality.
README
MCP Outlook Tools
A Model Context Protocol (MCP) server implementation that enables AI assistants to interact with Microsoft Outlook for calendar management, email operations, and search functionality.
Features
-
📅 Calendar Management
- Get calendar items within a date range
- Add new appointments with full details
- Support for categories and busy status
-
📧 Email Operations
- Send emails with To/CC recipients
- Display confirmation before sending
- Full body formatting support
-
🔍 Email Search
- Search emails by date and keyword
- Extract user information from addresses
- Japanese text encoding support
Requirements
- Windows OS (required for pywin32)
- Microsoft Outlook installed and configured
- Python 3.10 or higher
- MCP-compatible AI assistant (e.g., Claude Desktop)
Installation
- Clone the repository:
git clone https://github.com/wmoto-ai/mcp-outlook-tools.git
cd mcp-outlook-tools
- Install dependencies using uv:
uv pip install -e .
Or using pip:
pip install -e .
Configuration
For Claude Desktop
Add the following to your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"outlook-tools": {
"command": "uv",
"args": [
"--directory",
"C:/path/to/mcp-outlook-tools",
"run",
"--with-editable",
".",
"-m",
"outlook_tools.server"
],
"cwd": "C:/path/to/mcp-outlook-tools",
"env": {
"PYTHONIOENCODING": "utf-8"
}
}
}
}
Usage
Once configured, the following tools are available in your AI assistant:
add_appointment
Add a new appointment to Outlook calendar
Parameters:
- subject: Appointment title
- start_time: Start datetime (YYYY-MM-DD HH:MM)
- end_time: End datetime (YYYY-MM-DD HH:MM)
- location: Meeting location (optional)
- description: Detailed description (optional)
- categories: Comma-separated categories (optional)
- busy_status: 0=Free, 1=Tentative, 2=Busy, 3=Out of Office (default: 1)
get_calendar
Get calendar items for a date range
Parameters:
- start_date: Start date (YYYY-MM-DD)
- end_date: End date (YYYY-MM-DD)
send_email
Send an email via Outlook
Parameters:
- to: Recipient email addresses (semicolon-separated)
- cc: CC recipients (semicolon-separated)
- subject: Email subject
- body: Email body text
Project Structure
mcp-outlook-tools/
├── src/
│ └── outlook_tools/
│ ├── __init__.py
│ ├── server.py # MCP server implementation
│ ├── calendar_service.py # Calendar operations
│ └── search_service.py # Email search operations
├── test/ # Test files
├── pyproject.toml # Project configuration
└── README.md # This file
Development
Running Tests
pytest test/
Type Checking
pyright src/
Linting
ruff check src/
Security Notes
- This tool requires access to your local Outlook installation
- Emails are displayed before sending for user confirmation
- No credentials are stored in the code
- All operations use Windows COM interface with existing Outlook authentication
Limitations
- Windows only (due to pywin32 dependency)
- Requires Outlook to be installed and configured
- Time zone handling assumes JST (+9 hours)
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built with FastMCP framework
- Uses pywin32 for Outlook COM interface
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。