DEV Community: Wins Parking

How we stop fake QR stickers on parking signs

Wins Parking — Thu, 05 Nov 2026 16:05:50 +0000

Fake QR stickers on parking meters are now a national problem. Police and cities in New York, Orlando, Fort Lauderdale, Raleigh, Ann Arbor and Asheville have warned drivers since mid-2025.

The attack is cheap. Print a sticker, cover the real code, collect payments. The driver pays a criminal and still gets a ticket.

Park Graph runs QR code parking payments for private lots, so this problem is ours to solve. Here is the design.

1. Every sign is one of a kind

Each lot's QR carries a code that only Park Graph issues. A copied or outside sticker doesn't carry it. A scan with no valid code never reaches a pay page for that lot.

2. Fake codes get flagged before anyone is penalized

Before any payment notice goes out, the lot's sign must match its code. If it doesn't, notices at that lot stop and the owner is alerted until the original sign is confirmed. Drivers aren't penalized for a scam they couldn't see.

3. Drivers only ever pay on parkgraph.com

The pay page always lives on parkgraph.com and shows the lot name, the sign code and a verified operator badge. Card details go straight to Stripe and never touch our servers.

4. Money only goes to verified owners

Owners pass a Stripe ID check, and each lot is verified before its first payout. A scammer can't open an account and collect.

Patent pending

We filed five U.S. patent applications on this work in October 2026. They cover counterfeit payment-code detection for parking and EV charging, payment notices verified against posted sign codes, AI-assistant reservation holds, lot onboarding from a photo message, and multi-lot fleet reservations.

For developers

The same lots are bookable from code and AI assistants through the Park Graph API and MCP server. Drivers always finish payment on parkgraph.com; no tool charges a card on its own.

Full details are on the Park Graph security page. Lot owners can start free and go live the same day.

Only 16% of U.S. fast-charging stations meet federal NEVI standards: free open data

Wins Parking — Thu, 05 Nov 2026 15:58:29 +0000

We checked every open public DC fast-charging station in the U.S. against the federal NEVI minimums. The result: 2,545 of 15,926 stations (16%) pass.

The data comes from the U.S. Department of Energy's Alternative Fuels Data Center station locator. ChargingNear.me rebuilds it every day and publishes it free under CC BY 4.0 at chargingnear.me/data.

The rule we tested

A NEVI-grade station needs:

At least four CCS ports
Each able to deliver 150 kW at the same time
Within 1 mile of a designated Alternative Fuel Corridor

The source is 23 CFR 680.106 (FHWA final rule, February 28, 2023). Each of the 13,381 failing stations is listed with the reason it fails.

Where the gaps are

We also measured every stretch of Interstate, U.S. highway and designated EV corridor where fast chargers sit more than 50 miles apart.

878 stretches run more than 50 miles between fast chargers.
307 of them are on FHWA-designated Alternative Fuel Corridors.
The longest is 376.6 miles, on US-2 from the Idaho line to Havre, Montana.
Three more gaps of 270 miles or longer run through Montana, Idaho and Kansas.

A charger counts for a highway when it sits within 1 mile of it. Any network and any plug count, including Tesla.

Get the files

File	Format
U.S. DC fast stations checked against NEVI minimums	CSV, JSON
U.S. highway charging gaps over 50 miles	CSV, JSON
All 18 open data files	CSV, JSON

Every file carries a row count, version, last-updated date, column dictionary, methodology and a "Cite as" line.

Use it from code or an AI assistant

The same data is available through the free ChargingNear.me API and MCP server. Ask Claude or another MCP client for "charging gaps on I-70" or "NEVI-grade stations in Texas" and it answers from the daily file.

Drivers can use it too: find EV charging stations near you by plug, network and speed across 273,136 ports.

Data as of November 5, 2026. Cite as: ChargingNear.me, "U.S. DC fast stations checked against NEVI minimums," US EV Charging Open Data, version 5, November 5, 2026, CC BY 4.0.

A free MCP server and API for 95,000+ US EV charging stations

Wins Parking — Sun, 25 Oct 2026 15:52:02 +0000

68% of EV drivers hit a broken charger in a single year (Plug In America survey). Most charger data an AI assistant can reach is stale, scraped or undated.

ChargingNear.me covers 95,724 US charging stations in all 50 states and DC, including 17,028 DC fast chargers from 98 networks. It syncs daily from the U.S. Department of Energy NREL database and cross-checks Open Charge Map, Google Places and TomTom. Every station page carries the date it was last verified.

We opened that data to agents and developers.

MCP server

https://chargingnear.me/api/mcp

Remote, streamable HTTP, read-only, no key. Listed in the official MCP Registry as me.chargingnear/mcp.

Tool	What it does
`search_stations`	Filter by city, state, network, connector, speed, power or live availability
`get_nearest_stations`	Nearest stations to a latitude/longitude
`get_station_details`	Full record for one station
`find_stations_on_route`	Stations along a list of waypoints, for trip planning
`get_city_charging_stats`	Station count, network mix and top stations for a city
`get_state_charging_stats`	The same for a state

Add it to Claude Desktop, Cursor or any client that supports remote MCP:

{
  "mcpServers": {
    "chargingnearme": {
      "url": "https://chargingnear.me/api/mcp"
    }
  }
}

Each result carries a citation_url, and the server tells the model to cite it. Answers point back to a dated station page instead of a guess.

REST API

No key needed for 100 requests a day:

curl "https://chargingnear.me/api/v1/stations/nearest?lat=39.7392&lng=-104.9903&radius=5&limit=10"

The OpenAPI 3.1 spec is at https://chargingnear.me/.well-known/openapi.json. GeoJSON feeds cover map use. The base directory is CC-BY-4.0.

What people build with it

A charger finder inside a fleet or rideshare app
An EV road-trip assistant that plans stops by connector and speed
Market-gap maps for site selection: which cities have Level 2 but no DC fast

Park Graph MCP: let Claude and ChatGPT find, price and book parking

Wins Parking — Sun, 25 Oct 2026 15:51:12 +0000

Most parking lots are invisible to AI assistants. Ask Claude or ChatGPT to "find me parking near Coors Field tonight" and it can only guess from web pages.

We built Park Graph to fix that. Lot owners print one QR sign. Drivers scan and pay in 30 seconds. And every lot on Park Graph is exposed to AI agents through a hosted Model Context Protocol (MCP) server.

The endpoint

https://parkgraph.com/api/mcp

Remote, streamable HTTP. The driver flow needs no API key. It is listed in the official MCP Registry as com.parkgraph/mcp and on npm as parkgraph-mcp.

Tools

Tool	What it does
`search_lots`	Lots near a latitude/longitude, nearest first, with spaces left and the current rate
`get_lot`	Address, hours, features, pricing and live spaces for one lot
`quote`	Price for N hours at the current rate, daily max applied
`reserve`	Holds a space for a few minutes while the driver confirms
`get_session`	Status, times, amount and extensions for a parking session
`extend_session`	Adds time to an active hourly session

Connect it

Claude Desktop, Cursor or any MCP client that supports remote servers:

{
  "mcpServers": {
    "parkgraph": {
      "url": "https://parkgraph.com/api/mcp"
    }
  }
}

Stdio clients can run the npm package instead:

npx -y parkgraph-mcp

An optional Park Graph API key (PARKGRAPH_API_KEY, or Authorization: Bearer on the remote endpoint) adds live availability and pricing and turns on the session tools.

A real exchange

Driver: Need parking near Eagle airport tonight 8pm to midnight, EV.

Assistant calls search_lots, then quote, then reserve, and returns a hold with a confirm link.

The server's instructions tell the model never to invent lots. An empty result means Park Graph has no lot there, and the assistant says so.

Why we built it this way

Gates and pay stations cost $15,000 to $30,000 per lot. A QR sign costs a lamination pouch. Once payments live on a QR page, the same booking flow can be handed to an agent through a few typed tools. The owner sets the rate; the agent just finds it, prices it and holds it.