@pipeworx/or-dmv

@pipeworx/or-dmv

Provides live wait times and office details for all 60 Oregon DMV field offices by scraping the ODOT website, with no authentication required.

Category
Visit Server

README

@pipeworx/or-dmv

Oregon DMV MCP — live wait times at all 60 Oregon DMV field offices, plus the office locator the same payload carries. Keyless.

Oregon and North Carolina are the only two US states whose DMV publishes a machine-readable live wait feed. Every other state's is captcha-gated, blocked to cloud egress, broken, or only inside a phone app.

Tools

  • or_dmv_wait_times(office?, city?, region?, open_only?, sort?, limit?) — average minutes until served and customers currently queued, per field office.
  • or_dmv_offices(office?, city?, zip?, region?, limit?) — address, city, ZIP, phone, latitude/longitude, ODOT region, appointment-only flag and the office's ODOT page.

Auth

None. Keyless and unauthenticated.

Data source

https://dmv2u2.odot.state.or.us/waittimes/home/map

Scraped from HTML — no JSON endpoint exists

This is the one thing to know before depending on this pack.

ODOT renders the wait-time map server-side. There is no API behind it: the /api paths one would guess at return nothing. The office array is assigned to aveWaitModels inside an inline <script> tag on the page. The pack finds that identifier, brace-matches the array literal that follows it, and JSON.parses the result.

That makes Oregon structurally more fragile than an API-backed pack — an ODOT template change can move or rename the identifier and break extraction until this pack is updated. Those failures are reported as exactly that (the Oregon wait-time page no longer contains the aveWaitModels office array) with a hint pointing at nc_dmv_wait_times, rather than surfacing as a parsing bug of ours.

Gotchas this pack handles for you

Closed hours produce not_reporting, never a zero wait

Outside business hours ODOT sets waitTimeEnabled: false while leaving averageMinutesUntilServed at -1 and customersWaiting at 0. Publishing that as a zero-minute wait would read as "walk right in", so those offices come back as status: "not_reporting" with wait_minutes: null.

-1 is ODOT's unavailable sentinel and it survives waitTimeEnabled being true, so it is mapped to null in that case too. Responses always carry offices_reporting, and when nothing is reporting the note says the feed is switched off rather than the lines being empty. sort: "wait" puts reporting offices first for the same reason.

Fields deliberately dropped

Each office ships an ipAddress and a set of fieldOfficeMachine* fields. Those are ODOT's internal queue-terminal plumbing and are not republished. Everything else is passed through, including open, appointmentOnly and closeDescription (as closure_note), which carry real information about an office being shut.

Phone numbers arrive as bare ten-digit strings (5419672014) and are formatted as (541) 967-2014.

Regions

region matches on the six ODOT groupings: Central Oregon, Eastern Oregon, Portland Area, Southern Oregon, The Coast, Willamette Valley.

Related

  • nc_dmv_wait_times / nc_dmv_offices — North Carolina, the other live state wait feed.
  • ca_dmv_offices — California field offices (no wait feed published).

Quick Start

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

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

Or connect to the full Pipeworx gateway for access to all 1392+ data sources:

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

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English:

ask_pipeworx({ question: "your question about Oregon DMV data" })

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

More

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured