Wa Dmv MCP Server

@pipeworx/wa-dmv

Washington State DMV MCP — the Department of Licensing's VIN-level electric-vehicle population and its monthly vehicle-registration transaction counts. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Washington has no agency called "the DMV": vehicle registration and driver licensing are run by the Department of Licensing (DOL). Both names appear in the tool descriptions because agents search for "WA DMV".

Tools

Auth

Keyless. Both datasets are public Socrata resources on data.wa.gov; no app token is required at the volumes this pack issues.

Per-state gotchas

• hmzg-s6q4 counts transactions, not vehicles. This is the trap in this state. King County processes roughly 160,000 registration transactions a month, so summing every month back to fiscal 2017 returns 17.6M for one county — arithmetically correct and completely misleading. wa_dmv_registration_transactions therefore pins every query to one fiscal year (the latest by default) or one calendar month, and labels the result "registration transactions during <period>". For the size of a registered fleet, use wa_dmv_ev_population.
• Washington fiscal years run July 1 – June 30. Fiscal 2026 covers July 2025 through June 2026. Data starts at fiscal 2017.
• The month column stores the last day of the month. Filter it with date_trunc_ym, which the month argument (YYYY-MM) does for you; results are reported back as YYYY-MM.
• Case differs by column. Counties and cities are plain mixed case (King, Seattle); makes and models are upper case (TESLA, MODEL 3).
• Roughly two-thirds of EV rows carry electric_range 0. 188,456 of 289,564 vehicles sit in the "Eligibility unknown as battery range has not been researched" CAFV bucket with a literal zero range, which drags any average down. The genuinely researched vehicles average ~133 miles. Treat average_electric_range_miles as a floor, not a spec.
• Socrata reports an all-zero average as the string "0E-24". The shared govNumber helper strips exponent notation into NaN, so this pack parses averages with its own avgMiles.
• ev_type has exactly two values, spelled in full: Battery Electric Vehicle (BEV) and Plug-in Hybrid Electric Vehicle (PHEV). The ev_type argument accepts BEV / PHEV / plain phrases.
• sum_of_returned_rows is not a total. Row lists are cut off by limit; total_electric_vehicles and total_transactions_in_period are separate full counts over the same filters and are the figures to quote.

Data sources

• EV population — https://data.wa.gov/resource/f6w7-q2d2.json (Electric Vehicle Population Data)
• Registration transactions — https://data.wa.gov/resource/hmzg-s6q4.json (Vehicle Registration Transactions by County)

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "wa-dmv": {
      "url": "https://gateway.pipeworx.io/wa-dmv/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/wa-dmv/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1476+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Wa Dmv data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT