How to Use the Deta Space (Serverless Personal Cloud API) MCP in Pydantic AI

Q: How do I add the Deta Space (Serverless Personal Cloud API) tools to a Pydantic AI agent?

You'll instantiate the MCPToolset with your Vinkius endpoint URL. Then, you pass that instance into the toolsets list when you initialize your Pydantic AI Agent. It's designed to be straightforward.

Q: What happens if Deta Base returns an unexpected field when using Pydantic AI with Deta Space (Serverless Personal Cloud API)?

Your agent will immediately raise a ValidationError. This is a core feature, not a bug. It prevents your application from having to handle unpredictable data structures and stops data corruption before it starts.

Get type-safe access to your Deta Space data and files using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deta Space (Serverless Personal Cloud API) MCP to Pydantic AI

Create your Vinkius account to connect Deta Space (Serverless Personal Cloud API) 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 Deta Space (Serverless Personal Cloud API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fail-Safe Database Operations

When you use this MCP Server with Pydantic AI, you're not just storing data; you're enforcing contracts. Your agent uses `base_put_items` to add data and `base_get_item` to fetch it. The magic happens on the way back: Pydantic AI validates the response from Deta Base against your Pydantic models. If the data isn't structured exactly as you expect—maybe a field is missing or has the wrong type—your code will raise a `ValidationError` instantly. This means no silent data corruption. Your agent either gets perfect data or it fails loudly, which is exactly what you want for reliable applications.

Manage Deta Drive with Confidence

File operations become predictable and safe. When your agent calls `drive_list_files`, Pydantic AI ensures the response is actually a list of strings. If the API ever returned something malformed, your agent wouldn't just crash or misbehave—it would tell you exactly why the incoming data was invalid. This same principle applies to tools like `drive_delete_files`. You get confidence that your agent's interactions with the file system are based on verified, correctly-typed information, not just hopeful parsing of raw API responses.

Build Correct Pydantic AI Agents

Correctness is the whole point of using Pydantic AI. With tools like `base_query_items` and `base_update_item`, you get type safety in both directions. The arguments your agent sends to the tool can be validated, and the results are always checked against your models. This prevents your agent from sending malformed requests and protects it from receiving unexpected data. It's a closed loop of validation that ensures your agent's model of the world—your Deta Space data—is always accurate and up-to-date.

Setup guide

Set up Deta Space (Serverless Personal Cloud API) 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": {
        "deta-space-serverless-personal-cloud-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Deta Space (Serverless Personal Cloud API) tools.",
)

result = await agent.run("List recent Deta Space (Serverless Personal Cloud API) 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 Deta Space. 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 Deta Space (Serverless Personal Cloud API) 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 Deta Space (Serverless Personal Cloud API) MCP in Pydantic AI

It validates every tool call's response against a Pydantic model that defines the expected data structure. If the response from the Deta Space API doesn't match your model, Pydantic AI raises a `ValidationError` instead of passing bad data to your agent.

You'll instantiate the `MCPToolset` with your Vinkius endpoint URL. Then, you pass that instance into the `toolsets` list when you initialize your Pydantic AI `Agent`. It's designed to be straightforward.

Yes. Pydantic AI is model-agnostic, so you can pair it with OpenAI, Anthropic, Gemini, or a model running on your own machine. The MCPToolset handles the connection to the Deta Space server independently of the LLM you choose.

Your agent will immediately raise a `ValidationError`. This is a core feature, not a bug. It prevents your application from having to handle unpredictable data structures and stops data corruption before it starts.

The server processes your Deta Base items and Deta Drive files. Each request your agent makes runs in a zero-trust, single-use V8 Isolate sandbox on Vinkius. Your Vinkius auth token secures the connection, and the sandbox is destroyed the moment your tool call is complete.

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