AIquila — Nextcloud MCP Server
Nextcloud MCP server — files, calendar, contacts, mail, maps, notes, tasks & 120+ more tools
AIquila
Private AI for your Nextcloud — your data, your server, your choice of AI provider
What is AIquila?
AIquila brings AI to your self-hosted Nextcloud. Instead of keeping your files, notes, tasks and recipes locked inside Nextcloud — or copying them by hand into a chat window — AIquila lets an AI assistant read and write your Nextcloud data directly. Your data stays on your own server, and you decide which AI provider sees it: a hosted API, or a model running on your own hardware that sends nothing to anyone.
How it works
AIquila has three components that can be used independently or together:
MCP Server — A Model Context Protocol server that gives any MCP-compatible AI assistant secure access to your Nextcloud. 342 tools across 44 categories: browse and manage files, keep calendars, tasks and contacts in sync, work in Talk, Deck and Mail, organise photos, notes and bookmarks, and run Coworkers and occ administration. It has no model of its own — it exposes Nextcloud to whichever MCP client you connect.
Nextcloud App — A native Nextcloud application that brings AI directly into the Nextcloud UI. Chat about your documents, summarise and rewrite text, run Coworkers (saved, repeatable AI jobs), and scope a conversation to a Project so the assistant only sees the folders you choose. Admins pick which providers are available, and may restrict them per user or group.
Hetzner Deployment — A single-command provisioning tool (aiquila-hetzner) that stands up a production-ready AIquila server on Hetzner Cloud, complete with Traefik reverse proxy, CrowdSec intrusion prevention, TLS, and optional monitoring.
AI providers
The Nextcloud app supports five providers for chat. Each user can pick a provider and model per conversation, within what the admin allows.
| Provider | Hosting | Notes |
|---|---|---|
| Claude (Anthropic) | Anthropic API | The default, and the most deeply integrated: vision, thinking budgets, native MCP connector, and PDF handling with citations. |
| Hetzner Inference | Hetzner (German provider) | OpenAI-compatible. Currently an experimental Hetzner service, free while experimental; Hetzner states it does not store request and response content. Tokens from experiments.hetzner.com. |
| Mistral | Mistral API (French provider) | Also supports the native MCP connector. Mistral offers EU-only processing through its regional inference endpoints. |
| Local model | Your own hardware | Ollama, LM Studio or llama.cpp. Nothing leaves your infrastructure. Supports bearer/basic/header auth and mTLS. |
| DeepSeek | DeepSeek API | OpenAI-compatible. No native MCP connector. |
Provider choice applies to chat, the per-conversation model picker and the Nextcloud Assistant / TaskProcessing integrations, which all run on the provider the user has selected. Assistant actions that send images ("Analyze images", "Extract text from image") need a vision-capable provider, and report which of the available ones qualify when the selected provider is not.
Getting Started
Pick the path that fits your setup:
| Path | What you get | Guide |
|---|---|---|
npx aiquila-mcp | Local MCP client + Nextcloud | Quick start |
| Docker + OAuth | Remote MCP client + Nextcloud | Quick start |
| Nextcloud App | AI inside the Nextcloud UI | Quick start |
| Hetzner Cloud | Full production deploy | Quick start |
| Mobile + Voice | Phone + Nextcloud hands-free | Quick start |
- Getting Started Guide — all five paths with step-by-step instructions
- Full Documentation — architecture, configuration, and advanced topics
- Nextcloud compatibility — which Nextcloud versions are supported, and what "supported" means
Contributing
Contributions are welcome. Please read CONTRIBUTING.md first — most importantly, open or comment on an issue before writing code, so we can confirm the approach before you invest the effort.
The guide covers branch and commit conventions, the checks CI runs per component, and what to expect from CI on a pull request from a fork.
Support
AIquila is free software and developed in the open. If it is useful to you, funding covers the running costs behind it — test servers, CI minutes, domains and the App Store presence:
Contributing time — issues, pull requests, documentation, or simply telling other people about the project — helps just as much.
License
AGPL-3.0 (Nextcloud App) / MIT (MCP Server)
See ACKNOWLEDGMENTS.md for the open-source projects and services AIquila is built on.
Installation
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y aiquila-mcpSet up in your AI client
Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-elgorro-aiquila-mcp": {
"command": "npx",
"args": [
"-y",
"aiquila-mcp"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referencePackage
aiquila-mcpnpmCompatible MCP Clients
AIquila — Nextcloud MCP Server works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
- Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect. - Cursor
~/.cursor/mcp.jsonRestart Cursor for changes to take effect. - VS Code
.vscode/mcp.jsonReload VS Code window for changes to take effect. - Windsurf
~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect. - Claude Code
.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.