SOGo MCP Server
A Model Context Protocol (MCP) server that connects your AI agents (like Codex, Claude) to your SOGo groupware server. It enables your AI assistants to read your emails, check your calendar, and search your contacts.
README
SOGo MCP Server
A Model Context Protocol (MCP) server that connects your AI agents (like Codex, Claude) to your SOGo groupware server. It enables your AI assistants to read your emails, check your calendar, and search your contacts.
Features
- Email Integration: Read recent unread emails (with full body previews) using IMAP.
- Calendar Integration: Check your schedule for today/tomorrow using CalDAV.
- Contacts Integration: Search your address book for specific contacts by name or email using CardDAV.
Prerequisites
- A SOGo account
- Python 3.11+
- Docker (Optional, for containerized deployment)
Setup Options
You can run this MCP server either Locally (Stdio) or via Docker (SSE).
Option A: Running Locally (Stdio)
This is the most common way to run MCP servers directly connected to local desktop applications like Claude Desktop or Codex.
-
Clone the repository:
git clone https://github.com/yourusername/sogo-mcp.git cd sogo-mcp -
Install dependencies:
pip install -r requirements.txt -
Configure your Client: In your client application (e.g. Codex or Claude Desktop), add the server configuration using the absolute path to your
server.pyand your SOGo credentials:{ "mcpServers": { "sogo": { "command": "python", "args": ["/absolute/path/to/sogo-mcp/server.py"], "env": { "SOGO_HOST": "mail.example.com", "SOGO_USER": "your_email@example.com", "SOGO_PASS": "your_password" } } } }
Option B: Running via Docker (SSE / Networked)
If you want to run the server on a remote machine or isolated in a container, you can use Docker Compose, which runs the server over HTTP SSE on port 8000.
-
Create an environment file: Copy the example config and fill in your details:
cp .env.example .envEdit
.envwith your SOGo credentials. You can also changeMCP_PORTif port 8000 is already in use on your machine. -
Start the Docker container:
docker compose up --build -d -
Connect to the Server: Your server is now available via SSE at
http://localhost:8000/sse(or whichever port you set). Connect your client by pointing it to this URL.
Available Tools
Once connected, your AI agent will have access to the following tools:
get_unread_emails: Fetches the most recent unread emails from your SOGo INBOX, including Date, Sender, Subject, and the text body preview.get_todays_schedule: Retrieves today's calendar events (including expanding recurring events) from your SOGo CalDAV calendars.search_contacts: Searches your SOGo CardDAV personal address book for contacts matching a name or email query.
Contributing
Pull requests are welcome! If you encounter any issues with parsing specific SOGo setups, please open an issue.
License
MIT License
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.