How to Use the Nextcloud MCP in LangChain

Build autonomous Nextcloud workflows with LangChain agents that chain file, share, and user operations together.

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 LangChain

Create your Vinkius account to connect Nextcloud to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain File and Share Management

Stop managing Nextcloud by hand. Give your agent a sequence of tasks and let it run. It can `list_files` in a directory, find the one you need, then immediately call `create_share` to generate a public link. This isn't just about single actions. It's about building stateful workflows. For instance, an agent can create a new folder with `create_folder`, then monitor for changes using `list_activities` before deciding its next move. LangChain connects these steps into a single, observable process.

Automate User and Server Admin

Give your LangChain agent admin-level access to manage the instance. It can `list_users`, check their status with `get_user_status`, and then programmatically update it using `set_user_status` or `set_user_status_message`. This is useful for building bots that react to server events. You can even have an agent that checks server health by calling `get_capabilities` and then rotates its own credentials by using `get_app_password` followed by `delete_app_password` once the new one is stored securely.

Build Custom Nextcloud Agents with this MCP Server

The tools in this MCP Server are the building blocks for your ReAct agents. Because each tool is a discrete function, LangChain can reason about which one to use based on the goal. Need to revoke access? The agent knows to call `delete_share`. This approach lets you build complex logic. You could have an agent that audits all public shares by calling `list_shares`, checks their permissions, and then uses `update_share` to enforce a new password policy. You define the goal, the agent figures out the steps.

Setup guide

Set up Nextcloud MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Nextcloud tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "nextcloud-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Nextcloud transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

First, you get the tools from the MCP client. Then you pass that tool list directly into your agent definition. LangChain's function-calling models will automatically know how to call tools like `list_files` or `create_share` based on your prompts.

Yes, that's the whole point. You can create a chain that takes a file from an email, uses a tool to upload it to Nextcloud (not included), then calls this server's `create_share` tool to get a link, and finally sends that link to a Slack channel. It all works in one sequence.

LangChain doesn't manage permissions itself. The agent operates with the permissions of the Nextcloud user account you connect with. If your user is an admin, the agent can use `list_users`; if not, that tool call will fail.

Automating new user onboarding. A LangChain agent can be triggered when a new employee joins, then use `create_folder` to make their home directory and `update_share` to grant them access to standard company folders. This MCP connection makes it possible.

Your agent directly handles Nextcloud data like file paths, share permissions, and user details. The Vinkius MCP Server is ephemeral; your credentials and any data from tool calls like `get_user` exist only for that single operation and are not stored.

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