How to Use the Nextcloud MCP in Pydantic AI

Q: How do I use the Nextcloud MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your Vinkius HTTP endpoint, then pass it to the toolsets array in your Agent definition.

Q: Why did my Pydantic AI agent fail when calling Nextcloud listusers?

The listusers tool requires admin privileges on the Nextcloud instance. If your Vinkius token lacks those rights, the server returns an error, and Pydantic AI throws a strict runtime exception.

Q: Does the Pydantic AI MCP integration support both Nextcloud user and group shares?

Yes. The createshare tool accepts specific integers for share types. Your agent passes 0 for a user share or 1 for a group share, and Pydantic AI validates the input type before sending it.

Q: Can I set a custom Nextcloud status message via Pydantic AI?

You can. The agent uses setuserstatusmessage to push text updates to the profile. Pydantic AI ensures the message payload is correctly formatted as a string.

Integrate the Nextcloud MCP Server with Pydantic AI. Execute type-safe file operations and user management without silent failures.

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 Pydantic AI

Create your Vinkius account to connect Nextcloud to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Nextcloud MCP Server strict typing

The Nextcloud MCP Server provides tools like `create_folder`, `delete_file`, and `list_files` that map directly to Pydantic models. If the Nextcloud WebDAV API returns a malformed response, your Pydantic AI agent fails loudly with a validation error. You don't have to worry about silent data corruption. The framework validates every path and filename before the agent even attempts to execute a file operation.

Manage shares with exact parameters

Agents manipulate permissions via `create_share`, `update_share`, and `delete_share`. Because Pydantic AI enforces strict types, the agent knows exactly which integer corresponds to which share type — like 0 for User, 3 for Public Link, or 10 for Talk. Auditing the current configuration requires running `list_shares`. If the returned schema does not match your expected Pydantic model, the execution halts immediately.

Administer users and app passwords

Your agent handles authentication lifecycles using `get_app_password` and `delete_app_password`. It generates new credentials for scripts and revokes them when they are no longer needed. Tracking system state works through `list_users`, `get_user`, and `list_activities`. You get a rigid, type-checked view of your Nextcloud instance status at all times.

Setup guide

Set up Nextcloud MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "nextcloud-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Nextcloud tools.",
)

result = await agent.run("List recent Nextcloud transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your Vinkius HTTP endpoint, then pass it to the `toolsets` array in your Agent definition.

The `list_users` tool requires admin privileges on the Nextcloud instance. If your Vinkius token lacks those rights, the server returns an error, and Pydantic AI throws a strict runtime exception.

Yes. The `create_share` tool accepts specific integers for share types. Your agent passes 0 for a user share or 1 for a group share, and Pydantic AI validates the input type before sending it.

You can. The agent uses `set_user_status_message` to push text updates to the profile. Pydantic AI ensures the message payload is correctly formatted as a string.

This server handles raw application passwords, user activity feeds, and file metadata. Vinkius routes these requests through a stateless proxy layer. Authentication happens via a single endpoint token, and the session memory is destroyed the second the request completes.

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