An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Paris Lighting Street Light Inventory 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. Access real-time data on 165,000 public lighting fixtures.

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 Paris Open Data.

  1. 01

    Arrondissement lighting

    Counts the total number of light fixtures within a specific Paris arrondissement. You provide the district number from 1 to 20.

  2. 02

    Count light fixtures

    Returns a fast total count of fixtures filtered by road, category, sector, or arrondissement. Use this to quickly gauge the scale of lighting in a specific area.

  3. 03

    Lighting overview

    Provides a high-level summary of the entire lighting network. It breaks down the top maintenance sectors, lamp families, and road category splits.

  4. 04

    Fixtures by road

    Lists and counts the specific fixtures located on a given road. You must use the uppercase road label as stored in the city database.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Paris Open Data.

  1. 05

    Light fixture lookup

    Retrieves the full technical profile for a single fixture using its unique code. It returns coordinates, work type, and maintenance notes.

  2. 06

    List light fixtures

    Queries the full inventory of Paris street lights with exact-match filters. You can filter by road, sector, or arrondissement to get a paginated list of fixture details.

  3. 07

    Public private split

    Calculates the distribution of the lighting network between public and private roads. It returns three totals: the entire network, public roads, and private roads.

Real work

What teams actually run

01

Street-Level Audits

An urban planner asks for the total number of lamps on a specific road to plan upgrades.

02

District Comparisons

A researcher compares the lighting density between different arrondissements.

03

Infrastructure Mapping

A developer uses fixture coordinates to overlay lighting data onto a map.

04

Ownership Research

A policy analyst checks the proportion of lighting on private versus public roads.

One connector, every AI

Paris Open Data 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 Paris Open Data 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

958ms average. Fast in production.

Paris Open Data is checked daily against the live service.

Daily averagePeak 1313ms
Sep 28Today
Fastest day
729ms
Slowest day
1313ms
14-day trend
Improving-36%

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 Paris Open Data, so you can see the experience inside your AI.

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

Paris Open Data Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_rZXYBE4zv6L51gQ78bQCWvMQbXKKnwDmXNIkQGiZ/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 — Paris Open Data capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "paris-lighting-street-light-inventory-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_rZXYBE4zv6L51gQ78bQCWvMQbXKKnwDmXNIkQGiZ/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 Paris Open Data in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Paris Open Data owners hand off.

This MCP is designed for professionals working with urban infrastructure and city data.

  • 01

    Urban Designers

    They use the agent to pull fixture counts and locations for streetscape planning.

  • 02

    Journalists

    They query the data to report on lighting quality and infrastructure distribution.

  • 03

    Data Analysts

    They use the capability to extract specific datasets for urban studies and mapping.

FAQ

Questions Paris Open Data owners ask.

  • 01

    Is this a live feed for reporting broken street lights?

    No. This MCP accesses the city's fixed asset register, which contains technical details and locations, not live outage or dimming reports.

  • 02

    How do I search for a specific road?

    You must use the road label exactly as it is stored in the database, which is in UPPERCASE and includes a type suffix, such as "LEGENDRE (RUE)".

  • 03

    Can I find the exact location of a lamp?

    Yes. Using the light_fixture_lookup capability with a fixture code will return the WGS84 coordinates.

  • 04

    Do I need to know the official arrondissement format?

    No. You can provide a simple number from 1 to 20, and the MCP will automatically map it to the required zero-padded label.

  • 05

    What kind of data is included for each fixture?

    The data includes the fixture code, work type, lighting regime, maintenance notes, coordinates, road name, road category, maintenance sector, and arrondissement.

  • 06

    Do I need an API key?

    No. opendata.paris.fr serves all city datasets anonymously over its Opendatasoft REST API. This MCP defines no credentials and needs nothing configured.

  • 07

    How are the road names stored?

    UPPERCASE with a type suffix in parentheses, e.g. "LEGENDRE (RUE)" or "CINQ MARS (AVENUE)". The voie filter is an exact match on the stored label. fetch a page of list_light_fixtures to see the exact forms.

  • 08

    What does the public/private split mean?

    voie_categorie separates the network between streets maintained on public land (VOIES PUBLIQUES) and privately owned roads lit by the city (VOIES PRIVEES). public_private_split returns both totals plus the grand total in one call.

  • 09

    Is this a live sensor feed?

    No. The dataset is the city's fixed asset register of each fixture. its code, location, lamp/support family and lighting regime. It is not a dimming, outage or occupancy feed.

Explore

More in Government Public Data

Suggestions

Connect Paris Open Data to Claude, Cursor, ChatGPT & more