ca-dmv
Access California DMV data on vehicle registrations, EV adoption, field offices, forms, insurer NAIC codes, and driver licenses by county.
README
@pipeworx/ca-dmv
California DMV data: registered vehicles and EV adoption by ZIP code, all 187 field offices with the services each performs, the official forms catalog, insurer NAIC codes, and licensed-driver counts by county. Keyless.
Why this is one state per pack
Part of the dmv category — one pack per state motor-vehicle agency. The states do not share a
grain: California publishes a ZIP × make × model-year × fuel snapshot, New York a record-level
file, Washington monthly transaction counts, Maryland county-months, Pennsylvania county-quarters.
A single cross-state tool meant a schema where most arguments were ignored for most states and a
"total" that was never comparable, so each agency gets its own tools with its own real arguments.
For every DMV tool in one connection, use /mcp?vertical=dmv.
Tools
| Tool | What it returns |
|---|---|
ca_dmv_vehicle_registrations |
Registered vehicle counts by ZIP, make, model year, fuel or duty class |
ca_dmv_ev_adoption |
Battery-electric and plug-in hybrid counts with share of the local fleet |
ca_dmv_offices |
All 187 field offices — address, per-day hours, coordinates, services performed |
ca_dmv_forms |
Official DMV forms by topic, with REG/DL form numbers and download pages |
ca_dmv_insurance_lookup |
Insurer NAIC codes by company name |
ca_dmv_driver_licenses |
Valid licences and ID cards held, by county, annually from 2008 |
Auth
None. Every endpoint is public California state infrastructure. The CKAN-backed tools accept an optional CKAN API key, which the public datasets do not require.
Gotchas worth knowing
Live-verified behaviours, not guesses:
- Snapshots are one CKAN resource per year, 2019–2026, and the rows carry the prior December 31 as their as-of date — the "2026" file describes the fleet on 2025-12-31.
- Grouping by ZIP surfaces a literal
OOSbucket — out-of-state registrants, ~638k vehicles — which outranks every real ZIP. Ignore it when ranking ZIPs; the tool flags it innote. OTHER/UNKis a real make value that absorbs small-count suppression and can outrank genuine makes in a by-make ranking.total_vehiclesappears only when it is honest. Grouping by fuel returns every category, so its sum is the true fleet total; any other grouping can be cut off bylimit, and those responses carrysum_of_returned_rowsplustruncatedinstead.- Fuel labels are specific strings (
Battery Electric,Plug-in Hybrid,Hybrid Gasoline,Diesel and Diesel Hybrid,Hydrogen Fuel Cell). Plain words like "electric", "phev" or "hydrogen" are mapped for you. - Form search uses the DMV site's own relevance ranking, so a broad phrase like "title transfer" can put a vessel-title form above the vehicle one.
- California publishes no wait-time feed. Only North Carolina (
nc-dmv) and Oregon (or-dmv) do;ca_dmv_officesreturns posted hours instead. - Lien lookup and appointment booking are unavailable: the lien endpoint requires a reCAPTCHA token and appointments run on a session-based kiosk system.
Data sources
- Vehicle Fuel Type Count by Zip Code — data.ca.gov CKAN,
datastore_search_sql - Driver Licenses Outstanding by County — data.ca.gov CKAN
- Field office directory — dmv.ca.gov WP REST, hours and per-office service tags
- Forms catalog — dmv.ca.gov WP REST
- Insurance carrier NAIC lookup —
https://www.dmv.ca.gov/portal/wp-json/dmv/v1/naic-lookup?s=<name>
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"ca-dmv": {
"url": "https://gateway.pipeworx.io/ca-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 California DMV data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。