MCP Outlook Tools
Interact with Microsoft Outlook for calendar management, email operations, and search functionality.
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
-
š Calendar Management
- Get calendar items within a date range
- Add new appointments with full details
- Support for categories and busy status
-
š§ Email Operations
- Send emails with To/CC recipients
- Display confirmation before sending
- Full body formatting support
-
š 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/
āāā src/
ā āāā outlook_tools/
ā āāā __init__.py
ā āāā server.py # MCP server implementation
ā āāā calendar_service.py # Calendar operations
ā āāā search_service.py # Email search operations
āāā test/ # Test files
āāā pyproject.toml # Project configuration
āāā 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
Related Servers
Rednote MCP
An automated tool for searching and commenting on the social media platform Xiaohongshu (Rednote) using Playwright.
Kibela
An MCP server for integrating with the Kibela API, allowing LLMs to access and manage content on the knowledge-sharing platform.
Rememberizer
Interact with Rememberizer's document and knowledge management API to search, retrieve, and manage documents.
Lazy Toggl MCP
Simple unofficial MCP server to track time via Toggl API
Doc Lib MCP
An MCP server for document ingestion, chunking, semantic search, and note management.
ffl-mcp
Give AI a "send file" capability via P2P (Local-first)
Scenext MCP Server
Integrates with the Scenext AI platform to generate educational videos on various topics.
Spotify MCP Server
Control Spotify with natural language. Enables search, playback control, queue management, and device control using conversational commands.
SpellChecker
A fast, multilingual spell-checker for Large Language Models.
Xmind Generator
A server for generating Xmind mind maps from various data sources.