How to Use the UK ONS Discovery — Search 337+ Statistical Datasets MCP in OpenAI Agents SDK

Q: What is the best way for OpenAI Agents SDK to find all available filters?

First, use getdimensions on a specific dataset. Then, if you need options for just one filter—say, time periods—run getdimensionoptions. This ensures your agent has every valid parameter before making a query.

Q: Can UK ONS Discovery — Search 337+ Statistical Datasets handle complex queries with OpenAI Agents SDK?

Absolutely. The server supports flexible filtering via getobservations. Your agent can combine dimension filters (geography, time) to query highly specific data records from the 337+ datasets.

Q: If I want to find a dataset about trade statistics, which tool should I use with OpenAI Agents SDK?

Start with searchdatasets. This function lets you enter keywords like 'trade' and the server returns matching IDs. Once you have the ID, you can proceed with metadata retrieval using getdatasetinfo.

Find UK statistics fast with your OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect UK ONS Discovery — Search 337+ Statistical Datasets to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Querying ONS Data with the MCP Server

You can let your agent run `get_observations`, querying any specific ONS dataset. Just provide the required dataset ID and filter parameters, and it pulls the exact data points you need. It's crucial to remember that before querying, your agent must use `search_datasets` to find the correct dataset ID, followed by `get_dimensions` to map out all available filters.

Discovering Data Filters and Dimensions

Finding the right filter values can be a headache. Your agent handles this using `get_dimension_options`, which gives you every option for time periods, geography codes, or specific categories. This prevents your workflow from failing due to bad input. Additionally, running `get_dimensions` lets your system check exactly what filters are available for any given ONS dataset ID.

Browsing the Full Dataset Catalog

Need to know what data exists? Your agent can browse the entire catalog using `list_datasets`, helping you see all 337+ topics covered by the ONS. This is better than guessing which dataset holds the answer. Alternatively, if you're looking for something specific, `search_datasets` lets your team keyword search across the full range of available statistics.

Setup guide

Set up UK ONS Discovery — Search 337+ Statistical Datasets MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all UK ONS Discovery — Search 337+ Statistical Datasets tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives UK ONS Discovery — Search 337+ Statistical Datasets tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate UK ONS Discovery — Search 337+ Statistical Datasets tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="UK ONS Discovery — Search 337+ Statistical Datasets Agent",
            instructions="You have access to UK ONS Discovery — Search 337+ Statistical Datasets tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The MCP Server exposes six tools that let your agent interact directly with the ONS catalog. Your agent uses `search_datasets` to locate the required dataset ID, then proceeds to query it using `get_observations`.

First, use `get_dimensions` on a specific dataset. Then, if you need options for just one filter—say, time periods—run `get_dimension_options`. This ensures your agent has every valid parameter before making a query.

Absolutely. The server supports flexible filtering via `get_observations`. Your agent can combine dimension filters (geography, time) to query highly specific data records from the 337+ datasets.

Start with `search_datasets`. This function lets you enter keywords like 'trade' and the server returns matching IDs. Once you have the ID, you can proceed with metadata retrieval using `get_dataset_info`.

This MCP Server touches public statistical metadata, dimensions, and observations. The server design handles the API calls; your agent only receives the requested, aggregated statistics.

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