Download PDFMarkdown Version

Connect Nyc Open Data Explorer to ChatGPT, Claude and Gemini

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. Query thousands of New York City public datasets directly through your AI.

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.

How Vinkius works: one connection, every tool, in any AI
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.

Complete set · 5 capabilities

The complete NYC Open Data capability set.

These are the exact actions your AI can choose when you ask it to work with NYC Open Data.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 5 available through NYC Open Data.

  1. 01

    Browse dataset

    Query specific rows from any NYC Open Data dataset using SOQL filters. You can use double quotes for string values and ISO format for dates.

  2. 02

    Dataset row count

    Get the exact total number of rows in a dataset. You can apply filters to get a count for a specific subset of data.

  3. 03

    Dataset stats

    Retrieve row counts and grouped statistics for a dataset. This is useful for seeing the top-N values within a specific column.

Capability set02 / 02

04-05

2 capabilities in this set.

Part of 5 available through NYC Open Data.

  1. 04

    Get dataset info

    Fetch the metadata for a single dataset. Use this to find the exact column names and descriptions before running queries.

  2. 05

    Search datasets

    Search the entire NYC Open Data catalog using keywords. It returns the dataset ID, name, and description for each match.

One connector, every AI

NYC 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 NYC 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.

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 5 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 NYC Open Data, so you can see the experience inside your AI.

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

NYC Open Data Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_mAEjDrv8HxIky2zc7dK9Ip3znh6k9dtZoZIaMrSc/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 — NYC Open Data capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "nyc-open-data-explorer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_mAEjDrv8HxIky2zc7dK9Ip3znh6k9dtZoZIaMrSc/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? How to give Claude access to NYC Open Data

See all the AI clients this connector works with ↑

Who it's for

Built for the work NYC Open Data owners hand off.

Data professionals and researchers who need to pull real-time city information into their AI workflows.

  • 01

    Data Analysts

    They hand off the task of finding and filtering specific city datasets to their agent.

  • 02

    Urban Researchers

    They use the MCP to pull statistical summaries of city trends like crime or traffic.

  • 03

    Software Developers

    They integrate live NYC data into applications by letting their AI client query the SODA API.

FAQ

Questions NYC Open Data owners ask.

  • 01

    Do I need an API key to use this MCP?

    No. All access is anonymous and requires no credentials or API keys.

  • 02

    How do I know which columns to query?

    You should use the get_dataset_info capability first to see the exact column names and descriptions.

  • 03

    What happens if I want to filter by a specific borough?

    You can use the browse_dataset capability with a SOQL filter, such as borough="QUEENS".

  • 04

    Can I get a summary of the data without downloading it?

    Yes, you can use dataset_stats to get grouped counts or dataset_row_count for total totals.

  • 05

    Which AI clients can use this?

    Any MCP-compatible client like Claude, Cursor, or Windsurf can use this MCP once connected via Vinkius.

  • 06

    Do I need an API key?

    No. NYC Open Data serves all public datasets anonymously over its SODA API (data.cityofnewyork.us). This MCP defines no credentials and needs nothing configured.

  • 07

    How do I find the id of a dataset?

    Use search_datasets with a keyword. it queries the platform catalog and returns each match's 8-character id (like "erm2-nwe9"). That id feeds get_dataset_info, browse_dataset, dataset_stats and dataset_row_count.

  • 08

    Borough values differ across datasets. how do I know the format?

    Formats are dataset-specific: 311 and shootings use UPPERCASE ("QUEENS"), food and sanitation use Title Case ("Queens"), DOT potholes use single-letter codes. Capability descriptions state the expected values, and the errors from a mismatched value are reported verbatim by the platform.

  • 09

    What size is the catalog?

    The platform catalogs about 3,000 entries: roughly 2,400 standard datasets, plus filtered views, maps and external data sources. search_datasets searches all of them; the ny-* suite MCPs wrap the most-used families with dedicated capabilities.

Explore

More in Data Analytics

Suggestions

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