How to Use the UK ONS Discovery — Search 337+ Statistical Datasets MCP in Pydantic AI

Q: What is the most reliable way for Pydantic AI to map out available filters?

You should use getdimensions first. This tool lists all possible dimensions. If you need values for just one of those dimensions, then running getdimensionoptions gives precise filter inputs.

Q: If I need financial data from ONS, which tools help me find it?

Start with searchdatasets and use 'finance' or 'economy' as keywords. The server returns matching IDs. From there, you can get metadata using getdatasetinfo to understand the structure.

Type-safe ONS data retrieval with 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 UK ONS Discovery — Search 337+ Statistical Datasets MCP to Pydantic AI

Create your Vinkius account to connect UK ONS Discovery — Search 337+ Statistical Datasets 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 UK ONS Discovery — Search 337+ Statistical Datasets with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server for Data Querying in Pydantic AI

Your agent runs `get_observations` to query any specific ONS dataset. Since the response is validated by Pydantic, you're guaranteed that the data structure matches expectations when pulling records. It's smart to use `search_datasets` first; this finds the correct dataset ID before your agent attempts to pull observations.

Validating ONS Filters and Dimensions

Pydantic ensures data integrity when finding filters. Your agent uses `get_dimension_options` to validate available values for a dimension, like time or geography. If the API sends bad options, your pipeline fails loudly. Use `get_dimensions` to list out all possible dimensions and filter parameters that exist for any ONS dataset ID.

Searching the Full UK Statistics Catalog

The full catalog holds over 337 datasets. Your agent can browse this entire collection using `list_datasets`, keeping your data source discovery accurate. If you're looking for something specific, `search_datasets` lets you filter the massive list by keyword efficiently.

Setup guide

Set up UK ONS Discovery — Search 337+ Statistical Datasets 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": {
        "uk-ons-discovery-search-337-statistical-datasets-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to UK ONS Discovery — Search 337+ Statistical Datasets tools.",
)

result = await agent.run("List recent UK ONS Discovery — Search 337+ Statistical Datasets 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 UK ONS. 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 UK ONS Discovery — Search 337+ Statistical Datasets 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 UK ONS Discovery — Search 337+ Statistical Datasets MCP in Pydantic AI

The MCP Server provides six tools that your agent uses. Your workflow starts with `search_datasets` to find the ID, and then proceeds using `get_observations`. All results are validated against Pydantic models.

You should use `get_dimensions` first. This tool lists all possible dimensions. If you need values for just one of those dimensions, then running `get_dimension_options` gives precise filter inputs.

Yes. The server supports querying with flexible filters via `get_observations`. Since the data is validated, your agent can trust that the combination of dimension filters will yield a predictable result.

Start with `search_datasets` and use 'finance' or 'economy' as keywords. The server returns matching IDs. From there, you can get metadata using `get_dataset_info` to understand the structure.

This MCP Server accesses public statistical metadata, dimensions, and observations. The server design ensures that only requested, aggregated statistics are passed to your agent.

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