How to Use the Nextcloud MCP in AutoGen

Q: How do I get the Nextcloud tool schemas into AutoGen?

The autogen-extmcp package handles it. You use the mcpservertools function to connect to the MCP endpoint, and it automatically provides the tools in a format that AssistantAgent can use right away.

Deploy teams of AutoGen agents that collaborate and debate the best way to manage your Nextcloud instance.

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 AutoGen

Create your Vinkius account to connect Nextcloud to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent File and Share Management

Don't just give one agent a task. Assign a team. You can have a 'FileOrganizer' agent propose creating a new folder with `create_folder`, while a 'Compliance' agent checks if the name meets company standards before approving the action. This is about consensus. Another agent could use `list_shares` to audit existing public links, and if it finds one without a password, it can propose a fix. A 'Security' agent then debates whether to use `update_share` to add a password or just `delete_share` entirely.

Debate-Driven Server Administration

AutoGen lets your agents challenge each other. An 'Admin' agent might want to clean up old accounts by calling `list_users` and checking their last login. Before it acts, a 'Retention' agent can use `list_activities` to argue that a user is still active based on recent file changes. This conversation leads to better decisions. The agents can negotiate a plan, like setting a user's status with `set_user_status_message` to 'Account scheduled for review' instead of deleting it immediately. This MCP Server gives them the tools to argue their case with real data.

Build a Conversational Governance Team

Use AutoGen to build an automated governance committee for your Nextcloud. One agent's job is to monitor for new public shares. When it finds one, it starts a conversation with other agents to decide if the share is compliant. This isn't a simple script; it's a discussion. The agents use tools like `get_user` to identify the share owner and `list_files` to inspect the contents of a shared folder before reaching a group decision. It's a safer way to automate risky operations.

Setup guide

Set up Nextcloud MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Nextcloud tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Nextcloud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Nextcloud data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Nextcloud_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Nextcloud data")
    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 AutoGen

You pass the list of tools from the MCP Server to each agent in your group chat. When one agent wants to perform an action, like `create_share`, it proposes the tool call, and other agents can review, critique, or approve it before execution.

A great use case is automated share cleanup. You can have one agent find expired shares with `list_shares`, another agent verify they are truly inactive with `list_activities`, and a final user-proxy agent that asks you for confirmation before the 'Executor' agent calls `delete_share`.

Yes, they work within a conversational turn. One agent can call `list_files`, and in the next turn, another agent can use that file list as context to decide whether to call `delete_file`. The conversation history acts as their shared memory.

The `autogen-ext[mcp]` package handles it. You use the `mcp_server_tools` function to connect to the MCP endpoint, and it automatically provides the tools in a format that `AssistantAgent` can use right away.

The agents debate using data from your Nextcloud instance, like file lists, user statuses from `get_user_status`, and share permissions. Each agent in an AutoGen conversation can be run in its own sandboxed environment, and the MCP connection itself is stateless, processing data only when a tool is called.

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