How to Use the Nextcloud MCP in Google ADK

Q: How do I configure Nextcloud MCP tools in the Google ADK?

Install google-adk and wrap your Vinkius URL in StreamableHttpServerParameters. Pass that to McpToolset and hand the toolset to your LlmAgent.

Q: Can the Google ADK filter which Nextcloud tools the agent sees?

Yes. You pass a toolnames list to the McpToolset. This lets you expose listfiles while hiding destructive tools like deletefile from the agent.

Q: Does the Nextcloud MCP Server support Gemini long-context reasoning?

It sure does. You run listfiles across a massive directory structure and feed the entire JSON response into Gemini. The Google ADK handles the context window automatically.

Q: How do I update a user status in Nextcloud via Google ADK?

Your agent calls setuserstatus and setuserstatusmessage. The model decides the appropriate status based on the prompt, and the server executes the API call.

Wire your Nextcloud MCP Server into the Google ADK. Let Gemini agents read massive file trees and manage shares directly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nextcloud MCP to Google ADK

Create your Vinkius account to connect Nextcloud to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Nextcloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed WebDAV paths to Gemini

The Nextcloud integration exposes `list_files` and `get_capabilities` to your Google ADK agents. Dump thousands of file paths into Gemini's 1M+ token context window and let the model figure out what belongs where. When the model decides to restructure a directory, it fires off `create_folder` and `delete_file` commands. You just pass the Vinkius URL to `McpToolset` and the agent handles the WebDAV requests over HTTP.

Nextcloud MCP Server sharing controls

Your agents control internal and external access using `create_share`, `list_shares`, and `update_share`. If you have a BigQuery pipeline generating reports, the agent uploads the result and immediately shares it with a specific Nextcloud group (Share Type 1). Restricting exposed tools happens using the `tool_names` filter in Google ADK. If you only want an agent to audit permissions, give it `list_shares` and block `delete_share` entirely.

Monitor user activity streams

Enterprise deployments need audit logs, and `list_activities` pulls the raw Nextcloud activity stream. Your Gemini agent reads this feed to detect anomalous file access or unauthorized sharing. For deeper user management, agents with admin tokens use `list_users` and `get_user`. They can even check who is online right now using `get_user_status`.

Setup guide

Set up Nextcloud MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Nextcloud tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Nextcloud_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Nextcloud tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Nextcloud. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Nextcloud now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Nextcloud MCP in Google ADK

Install `google-adk` and wrap your Vinkius URL in `StreamableHttpServerParameters`. Pass that to `McpToolset` and hand the toolset to your `LlmAgent`.

Yes. You pass a `tool_names` list to the `McpToolset`. This lets you expose `list_files` while hiding destructive tools like `delete_file` from the agent.

It sure does. You run `list_files` across a massive directory structure and feed the entire JSON response into Gemini. The Google ADK handles the context window automatically.

Your agent calls `set_user_status` and `set_user_status_message`. The model decides the appropriate status based on the prompt, and the server executes the API call.

The server touches active file names, folder structures, and user status messages. Vinkius processes these requests through a zero-trust architecture. No persistent storage exists — the environment spins up for the Google ADK call and vanishes immediately after.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript