How to Use the data.world MCP in Pydantic AI

Q: How do I configure the data.world MCP Server with Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with the Vinkius HTTP URL. Pass this object directly to your Agent's toolsets list.

Q: How does Pydantic AI validate data.world user profiles?

The agent calls getmyprofile and parses the profile attributes into a typed schema. This guarantees your code always has access to verified username and permission strings.

Q: Can Pydantic AI search the data.world catalog safely?

Yes, searchcatalog returns ranked resources that are validated against strict search-result models. The agent can safely navigate titles and descriptions without risking runtime type crashes.

Build type-safe data.world agents with Pydantic AI to validate dataset schemas and SQL queries via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect data.world MCP to Pydantic AI

Create your Vinkius account to connect data.world 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 data.world with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict types on data.world dataset metadata

`get_dataset_details` pulls data.world field definitions and file lists directly into Pydantic AI's validation engine. If the data.world API returns unexpected metadata formats, the runtime raises a validation error instead of passing bad data to your LLM. This prevents silent failures when your Pydantic AI agent processes complex data.world schemas. You define the exact shape of the data.world catalog data you expect, and Pydantic AI guarantees the incoming payload matches it.

Validate data.world SQL queries before running them

`list_dataset_queries` returns saved data.world SQL or SPARQL definitions that are immediately parsed into typed Python models. Your Pydantic AI agent checks the creator metadata and language type before executing the query. This strict Pydantic AI validation ensures your LLM never executes malformed data.world queries or unsupported syntax. The unified `MCPToolset` handles the MCP connection, ensuring your model receives clean, typed structures.

Monitor project workspaces using this MCP Server

`list_project_insights` and `get_project_details` fetch documented data.world findings and resource statuses with absolute type safety. The Pydantic AI framework validates every insight and project member field against your Pydantic schemas. If a data.world project status changes or a new dataset is linked, `list_recent_activity` captures the update. Your Pydantic AI agent processes these logs knowing that every event payload is fully type-checked at runtime.

Setup guide

Set up data.world 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": {
        "dataworld-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent data.world 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 data.world. 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 data.world 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 data.world MCP in Pydantic AI

Install the package using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with the Vinkius HTTP URL. Pass this object directly to your Agent's `toolsets` list.

The agent calls `get_my_profile` and parses the profile attributes into a typed schema. This guarantees your code always has access to verified username and permission strings.

Yes, `search_catalog` returns ranked resources that are validated against strict search-result models. The agent can safely navigate titles and descriptions without risking runtime type crashes.

Yes, the framework supports both Streamable HTTP and SSE transports. Since the server runs externally on Vinkius, your agent connects via HTTP to stream tool execution.

Vinkius isolates the connection inside an ephemeral V8 sandbox container. No profile details or catalog metadata are ever logged or cached on the host, keeping your enterprise data strictly private.

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