mcpField
D
Dc Dmv

Dc Dmv

Remote
pipeworx.ioLegal & Government0Updated 5w ago

About Dc Dmv

Dc Dmv is an MCP server for querying District of Columbia DMV locations, vehicle inspections, and traffic convictions. It provides record-level inspection and conviction data alongside office details.

Key features

  1. 01Find nine DMV locations
  2. 02Query inspections by VIN or date
  3. 03Summarize inspection volume by month or year
  4. 04Explore convictions by offense or disposition
  5. 05Retrieve individual citation records

Use cases

  1. 01Locate a DC DMV service center
  2. 02Check inspection history for a vehicle
  3. 03Compare inspection volumes over time
  4. 04Analyze adjudicated traffic convictions

MCP support

Exposes DMV location, inspection, and conviction tools to MCP clients. Available through the Pipeworx gateway or as a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/dc-dmv/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

@pipeworx/dc-dmv

District of Columbia DMV data: service centers, the record-level vehicle inspection file, and traffic convictions. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Why DC gets its own pack

DC's grain is unlike any state's. The District publishes 766,879 individual vehicle inspections keyed by VIN and 330,728 individual traffic convictions keyed by citation, both as ArcGIS tables on the DCGIS server — not the county-level aggregates most states publish. So the tools take VINs, violation text and date ranges rather than a county argument.

Tools

ToolWhat it returns
dc_dmv_officesAll 9 DMV locations — service centers, the inspection station, two self-service emissions kiosks, the Deanwood road-test/CDL center, and Adjudication Services
dc_dmv_vehicle_inspectionsInspection records by VIN or VIN prefix, with inspection and expiration dates; or inspection volume per month/year
dc_dmv_convictionsTraffic convictions counted by violation or court disposition, or individual citation records

Auth

None. Every upstream is a public DCGIS ArcGIS MapServer layer.

The State Plane coordinate trap

The office layer's XCOORD/YCOORD columns are Maryland State Plane metres, not lat/lng. Georgetown Service Center reads 394380.55, 137456.23 — plausible-looking numbers that are wrong by the width of a hemisphere if treated as coordinates.

Every query here passes geometry: true to arcgisQuery (which sets outSR=4326) and reads latitude and longitude off the returned geometry. XCOORD/YCOORD are deliberately left out of the response so they cannot be mistaken for coordinates downstream. Georgetown's real position is 38.9050, -77.0648.

Gotchas worth knowing

These are live-verified behaviours, not guesses:

  • The inspection file's STATUS column is empty on all 766,879 rows, so a pass/fail outcome is not published. What you get is that an inspection happened, when, and when the resulting certificate expires — an expiration roughly two years out is the usual sign of a pass, a short one of a re-inspection window. The tool's note says so rather than letting a caller read a null as "unknown result". For per-test pass/fail with make and model, nj_mvc_vehicle_inspections publishes it.
  • GIS_ID, CREATOR and CREATED are also empty on the inspection table.
  • About half the conviction rows prefix the violation text with a four-digit internal code — 0201SPEED IN EXCESS OF LIMIT and SPEED IN EXCESS OF LIMIT are the same offence in two buckets. A raw group-by therefore splits and mis-ranks every violation. The tool strips the prefix and merges: "DISOBEYING OFFICIAL SIGN OR SIGNAL DEVICE" is 20,113 convictions, not the 10,369 a naive query reports.
  • DCGIS caps any single response at 2,000 rows, grouped statistics included. Month and year rollups group by day upstream (1,874 distinct days across the whole file — inside the cap) and aggregate in code; if that ever hits the cap the response flags truncated and says to narrow with inspected_since.
  • Coverage: inspections run 2020-11-01 → 2026-06-30 and are still being appended; convictions run 2002-07-01 → 2026-06-27. Both are returned in a coverage field rather than assumed.
  • Convictions are convictions. A citation that was dismissed or never adjudicated is absent, so these counts are not ticket counts.
  • The office layer carries no ZIP and no hours. MATCHADDR is the District's own geocoded street address; dmv.dc.gov posts hours per location.

Available but not wrapped

The same Transportation_DMV MapServer carries further DMV tables that are queryable but not exposed as tools:

LayerTable
142DMV Business Information
143DMV Driver License Information
144DMV ID Card Information
145DMV Reciprocity Parking Permit
146DMV Personalized Plates
147DMV Disability Placard
149DMV Vehicle Inspections FY2003-2013
150DMV Vehicle Inspections FY2014-2020
166DMV Boot and Tow

Layers 149 and 150 are the historical inspection archives and share the current table's schema, including the same empty STATUS.

Data sources

Quick Start

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

{
  "mcpServers": {
    "dc-dmv": {
      "url": "https://gateway.pipeworx.io/dc-dmv/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/dc-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 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/dc_dmv_offices \
  -H 'Content-Type: application/json' \
  -d '{"name":"Georgetown"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/dc_dmv_offices. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "dc-dmv": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-dc-dmv"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-dc-dmv

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Dc Dmv data" })

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

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.