cbcoutinho/nextcloud-mcp-server

What it solves

This project provides a bridge between AI assistants (like Claude, GPT, and Gemini) and Nextcloud instances. It allows LLMs to interact with your personal or organizational data—such as notes, calendars, contacts, and files—using natural language, effectively turning your Nextcloud instance into a structured data source for an AI agent.

How it works

It is a standalone Model Context Protocol (MCP) server. It connects to Nextcloud via a secure API using app-specific passwords or OAuth (Login Flow v2). The server exposes over 110 tools to the AI assistant, enabling it to perform CRUD operations across various Nextcloud apps (e.g., Notes, Calendar, Deck, Mail, and Talk).

Who it’s for

Users and administrators of Nextcloud who want to integrate their data with external AI assistants, IDEs, or the Nextcloud Assistant app via the Astrolabe integration.

Highlights

• Extensive App Support: Covers 10+ Nextcloud apps including Notes, Calendar, Contacts, Files, Deck, Cookbook, Tables, Sharing, News, Mail, Collectives, Talk, and Shopping List.
• Semantic Search: An experimental RAG pipeline using a vector database (Qdrant) and embedding service (Ollama) to find content by meaning rather than keywords.
• Document Processing: Built-in OCR and text extraction for PDFs, DOCX, and images.
• Flexible Deployment: Supports Docker, Kubernetes, VM, or local installation with multiple transport options (stdio and streamable-http).
• Secure Authentication: Supports Basic Auth with app passwords and a multi-user Login Flow v2 for hosted deployments.