Download PDFMarkdown Version

Connect Nyc Cycling Bike Infrastructure 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. Plan smarter bike trips with live NYC transit data.

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 · 8 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

01-04

4 capabilities in this set.

Part of 8 available through NYC Open Data.

  1. 01

    Bike direction split

    This capability compares inbound and outbound traffic volumes for a specific travel mode. Use it to see if a bridge or corridor has a heavy commuter bias in one direction.

  2. 02

    Count bike lanes

    This capability returns a fast count of NYC bike route segments that match your specific filters. It's useful for quickly gauging the scale of a route or street before pulling more detailed data.

  3. 03

    List bike corrals

    This capability identifies the 912 secure and community bike corrals across the city. Use it when you need a more reliable parking option than a standard chainable rack.

  4. 04

    List bike lanes

    This capability provides details on approximately 29,700 bike route segments, including facility types like Protected or Shared. You can filter by borough or street to trace the network for trip planning.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through NYC Open Data.

  1. 05

    Search bike flows

    This capability pulls raw 15-minute interval counts from live traffic sensors. It provides the specific volume of bikes, pedestrians, or scooters at a given street or intersection.

  2. 06

    Search bike parking

    This capability searches through 38,000 bike racks and corrals citywide. It returns addresses and street locations to help you find a place to lock up near your destination.

  3. 07

    Top bike greenways

    This capability ranks the named greenways in NYC by their segment count. Use it to identify the primary long-distance cycling corridors in the city.

  4. 08

    Top bike sensors

    This capability identifies the busiest bike, pedestrian, or scooter sensors based on total volume. It helps you find the highest traffic areas within a specific lookback window.

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. 8 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_3P46RSzw0PDTHAxf04vdii8m7mlX1Du1VtzGnGRA/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-cycling-bike-infrastructure-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_3P46RSzw0PDTHAxf04vdii8m7mlX1Du1VtzGnGRA/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.

This MCP is built for anyone navigating the NYC cycling network who needs real-time or structural data without manual searching.

  • 01

    Urban Cyclists

    Use the agent to find protected lanes and secure parking for daily commutes.

  • 02

    City Planners

    Hand off data analysis tasks like checking sensor volumes or greenway lengths to your AI.

  • 03

    Logistics Coordinators

    Use traffic flow and direction split data to understand micro-mobility patterns.

FAQ

Questions NYC Open Data owners ask.

  • 01

    Do I need an API key to use this NYC cycling data?

    No. Vinkius hosts the MCP, so you get keyless access to the data through your AI client.

  • 02

    How recent is the traffic sensor data?

    The sensor readings are live and include 15-minute interval counts collected up to today.

  • 03

    Can I find secure parking instead of just regular bike racks?

    Yes. You can specifically search for the 912 secure and community bike corrals using the list_bike_corrals capability.

  • 04

    Which AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 05

    How do I search for a specific street?

    When asking your agent to search, ensure the street name matches the casing used in the results, as the data uses specific uppercase and mixed-case formats.

  • 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

    Do the text filters ignore case or match partial values?

    No. The NYC data platform only supports exact-match filters, and each table stores its values differently: the bike-route table stores the boro as the numeric code 1-5 and the street in UPPERCASE ("1 AV". the capability auto-uppercases the street input); the bike-parking table stores the boro in title case ("Brooklyn", "Staten Island") and mixes street casings (e.g. "BROADWAY" and "Broadway". pass the street as it appears in a result row). Facility classifications are stored as "Protected", "Conventional", "Shared", "Signed Route", "Wide Parking Lane", "Sidewalk" or "Curbside", and the greenway names are a short set ("Manhattan Waterfront", "Jamaica Bay", "Brooklyn Waterfront", ...). Use list_bike_lanes or search_bike_parking with no filters to see the exact stored values before filtering.

  • 08

    What do the direction codes on bike routes mean?

    The route segments carry a short direction code: "L" for left-side/one-way, "R" for right-side/one-way and "2" for two-way operation. Use it to read which way a one-way street's bike lane flows.

  • 09

    How do sensor ids map to streets?

    top_bike_sensors returns numeric sensor ids. Call search_bike_flows with that sensor id: the flowname field carries the street context, e.g. "87th ST. and Columbus IN" or "Manhattan Bridge Display Bike Counter Cyclist IN". Only 15-minute interval readings are returned (hourly summary rows are excluded), and the counts are live, collected up to today.

Explore

More in Government Public Data

Suggestions

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