Outlook MCP
Enables AI agents to manage Microsoft Outlook emails through the Microsoft Graph API, supporting operations like listing, reading, sending, and moving emails.
README
Outlook MCP
An MCP server that connects GitHub Copilot and other AI agents to Microsoft Outlook via the Microsoft Graph API.
Features
| Tool | Description |
|---|---|
list_emails |
List emails from any folder with filtering, sorting, and pagination |
read_email |
Read a full email (body + metadata) or its internet headers |
search_emails |
Search the mailbox using KQL queries |
list_folders |
List all mail folders, optionally including sub-folders |
list_attachments |
List attachments on a specific email |
send_email |
Send a new email (plain text or HTML, CC, BCC, importance) |
reply_email |
Reply or reply-all to an email |
move_email |
Move an email to a different folder |
Requirements
- Python 3.12+
- A Microsoft 365 account with Outlook
- A Microsoft Graph API bearer token with
Mail.Read,Mail.Send, andMail.ReadWritescopes
Quick Start
# 1. Clone the repository
git clone https://github.com/your-org/outlook-mcp.git
cd outlook-mcp
# 2. Create a virtual environment and install dependencies
python -m venv .venv
.venv\Scripts\Activate.ps1
pip install -r requirements.txt
# 3. Run setup to configure VS Code
.\setup.ps1
Configuration
The server reads these environment variables:
| Variable | Required | Description |
|---|---|---|
OUTLOOK_TOKEN |
Yes | Microsoft Graph API bearer token |
OUTLOOK_PROXY |
No | Corporate HTTP proxy URL |
OUTLOOK_VERIFY_SSL |
No | Set true to verify SSL certificates (default: false) |
Getting an OUTLOOK_TOKEN
For development / testing � use Graph Explorer:
- Sign in with your Microsoft 365 account.
- Click Access token in the top panel.
- Copy the token.
For production � register an Entra ID application with delegated permissions (Mail.Read, Mail.Send, Mail.ReadWrite) and implement OAuth 2.0 to obtain tokens programmatically.
Running manually
export OUTLOOK_TOKEN=your_token_here
python server.py
Docker
docker build -t outlook-mcp .
docker run -e OUTLOOK_TOKEN=your_token_here outlook-mcp
VS Code MCP configuration
.vscode/mcp.json (generated by setup.ps1):
{
"servers": {
"outlook-mcp": {
"type": "stdio",
"command": "python",
"args": ["server.py"],
"env": {
"OUTLOOK_TOKEN": "your_token_here"
}
}
}
}
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.