An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect London Air Air Quality Diffusion Tubes to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get real-time and historical pollution data for London boroughs.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through London Datastore.

  1. 01

    Air quality by hour

    This capability provides London air-pollutant means broken down by the hour of the day. You can filter the results by specific months or hours.

  2. 02

    Air quality monthly

    This capability retrieves monthly mean concentrations for 14 pollutants from 2008 to 2019. It covers both roadside and background networks.

  3. 03

    Air quality overview

    This capability gives you a compact summary of the London monthly air-quality series. It shows the minimum, maximum, and mean values for each pollutant.

  4. 04

    Diffusion borough lookup

    This capability looks up a specific London borough within the 2024 diffusion-tube study. It automatically handles variations in borough naming.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through London Datastore.

  1. 05

    Diffusion boroughs

    This capability provides a summary of the 2024 diffusion-tube air-monitoring data for all London boroughs. You can limit the results to the top N boroughs.

  2. 06

    Diffusion overview

    This capability returns city-wide totals from the 2024 diffusion-tube summary.

  3. 07

    Diffusion sites

    This capability lists the specific 2024 diffusion-tube monitoring sites within a chosen borough. It includes site IDs, coordinates, and monthly means.

Real work

What teams actually run

01

Regulatory Compliance Audits

Check if specific London boroughs are exceeding UK legal air quality limits using the 2024 diffusion-tube data.

02

Trend Analysis

Compare NO2 or PM2.5 levels from 2008 to the present to see how air quality has changed over time.

03

Hyper-local Exposure Studies

Use diffusion-tube site data to find specific monthly means for a single borough.

04

Diurnal Pattern Research

Analyze hourly pollutant profiles to identify peak pollution times during the day.

One connector, every AI

London Datastore works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put London Datastore to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1825ms average. Fast in production.

London Datastore is checked daily against the live service.

Daily averagePeak 3957ms
Sep 29Today
Fastest day
1635ms
Slowest day
3957ms
14-day trend
Improving-10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of London Datastore, so you can see the experience inside your AI.

It does not authenticate your account with London Datastore. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

London Datastore Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_McyHZuQELl5I81MBH76n7tpHOUmZO0RKQWT87306/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — London Datastore capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "london-air-air-quality-diffusion-tubes-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_McyHZuQELl5I81MBH76n7tpHOUmZO0RKQWT87306/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up London Datastore in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work London Datastore owners hand off.

This MCP is built for professionals who need to analyze urban environmental data without manually cleaning government spreadsheets.

  • 01

    Environmental Researchers

    They hand off the task of pulling long-term pollutant time series to the agent.

  • 02

    Urban Planners

    They use the agent to compare borough-level pollution data against health guidelines.

  • 03

    Policy Analysts

    They task the agent with identifying areas where air quality exceeds legal limits.

FAQ

Questions London Datastore owners ask.

  • 01

    How far back does the air quality data go?

    The monthly air pollutant series includes data from January 2008 through August 2019.

  • 02

    Does this include the latest 2024 data?

    Yes, the MCP includes the 2024 diffusion-tube study data for all 33 London boroughs.

  • 03

    Can I search for boroughs using partial names?

    Yes, the diffusion_borough_lookup capability is case-insensitive and handles common variations like 'LB Barnet' or 'Barnet' automatically.

  • 04

    What pollutants can I check?

    You can access data for 14 indicators, including NO, NO2, NOx, O3, PM10, PM2.5, and SO2.

  • 05

    Is the data from roadside or background stations?

    The monthly air quality capabilities provide data for both roadside and background networks.

  • 06

    Do I need an API key?

    No. data.london.gov.uk publishes every dataset as an anonymous file download (CSV or Excel). This MCP defines no credentials and needs nothing configured.

  • 07

    Which indicators are in the monthly series?

    Fourteen, in pairs: NO, NO2, NOx, O3, PM10, PM2.5 and SO2, each measured roadside and in background (units µg/m³). air_quality_overview returns the min, max and mean of every one of them across the whole series.

  • 08

    What is a diffusion tube?

    A low-cost passive sampler: air diffuses through a cap into a sorbent, and the 12-month average is reported per site. Because it integrates exposure over months rather than minutes, it is ideal for mapping long-term neighbourhood-level pollution across all 33 London boroughs.

  • 09

    Why do some borough names look misspelled in the source?

    The 2024 study stores two boroughs with typos ('LB Waltham' for Waltham Forest, 'RB Kensignton & Chelsea'). diffusion_borough_lookup accepts the plain friendly names. 'Waltham Forest', 'Kensington and Chelsea', 'City of London'. and resolves them to the stored sheet names automatically.

Explore

More in Environment

Suggestions

Connect London Datastore to Claude, Cursor, ChatGPT & more