How to Use the Dataiku DSS MCP in Pydantic AI

Q: How does Pydantic AI validate data returned by the Dataiku DSS MCP Server?

Pydantic AI maps the JSON responses from tools like listdatasets directly to Pydantic models. If the DSS API returns unexpected fields, the framework raises a validation error instantly.

Q: Can I use the deprecated HTTP client to connect Pydantic AI to Dataiku DSS?

No, you should use the unified MCPToolset approach. Pass the Vinkius streamable HTTP URL directly to the toolset to connect your agent.

Type-safe Dataiku DSS pipeline automation and schema validation with Pydantic AI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dataiku DSS MCP to Pydantic AI

Create your Vinkius account to connect Dataiku DSS 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 Dataiku DSS with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Schema Mapping with Pydantic AI

The `dataset_schema` tool delivers structured table schemas directly to your Pydantic AI agent. Because the framework enforces strict type-checking, any unexpected column type returned by DSS triggers an immediate validation error instead of silently corrupting your pipeline. This strict runtime validation makes it impossible for your agent to pass malformed data to downstream tasks. You write clean, typed Python code, and Pydantic AI ensures the MCP Server outputs match your exact schemas.

Validated Model Tracking via Pydantic AI

The `get_model` tool extracts performance metrics and algorithm metadata from your DSS projects. Your Pydantic AI agent parses this data against a strict model schema, verifying that keys like accuracy and drift are present and correctly typed. If a DSS update changes the JSON payload format, the agent fails loudly at the boundary. This prevents your LLM from hallucinating metrics or making decisions based on missing evaluation parameters.

Strict Pipeline Automation using this MCP Server

The `run_scenario` tool initiates Dataiku automation scenarios with runtime-checked parameters. Pydantic AI validates the status outputs from `get_job` before your script proceeds to the next execution step. Using this MCP Server ensures that your orchestration logic is completely deterministic. You get the flexibility of an agentic workflow combined with the safety of production-grade type validation.

Setup guide

Set up Dataiku DSS 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": {
        "dataiku-dss-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Dataiku DSS 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 Dataiku. 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 Dataiku DSS 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 Dataiku DSS MCP in Pydantic AI

Pydantic AI maps the JSON responses from tools like `list_datasets` directly to Pydantic models. If the DSS API returns unexpected fields, the framework raises a validation error instantly.

No, you should use the unified `MCPToolset` approach. Pass the Vinkius streamable HTTP URL directly to the toolset to connect your agent.

You define your target schema as a Pydantic model. When the agent calls `dataset_schema`, the framework validates the DSS response against your model, catching drift before it breaks your code.

Yes, Pydantic AI is model-agnostic. You can run a local model or an external API; the framework will still validate all tool outputs from the Dataiku DSS server.

The Vinkius sandbox isolates the MCP Server execution, preventing direct access to your DSS instance. Only the validated JSON payloads containing project metadata and job states are exposed to the Pydantic AI runtime.

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