io.github.pipeworx-io/ny-dmv MCP Server

The io.github.pipeworx-io/ny-dmv MCP server provides access to New York DMV information at the record level, covering vehicle and EV registrations, offices, road tests, and driving schools. It is identified by the slug io-github-pipeworx-io-ny-dmv and is tagged with MCP and Pipeworx-related topics.

🛠️ Key Features

Record-level vehicle and EV registrations
New York DMV offices
Road tests information
Driving schools information

🚀 Use Cases

Retrieve DMV registration records for vehicles and EVs
Look up DMV office locations or related details
Find information related to road tests
Access driving school information

⚡ Developer Benefits

Structured MCP server integration for New York DMV data
Discovery via topics: mcp, mcp-server, model-context-protocol, pipeworx, ny-dmv

⚠️ Limitations

No tool count or capabilities list provided in the available server data
No readme excerpt provided

@pipeworx/ny-dmv

New York State DMV MCP — registered vehicles and EV adoption, DMV offices, road test sites, licensed driving schools, and the DMV-licensed facility register. Keyless.

Tools

Tool	What it returns
`ny_dmv_vehicle_registrations(...)`	Counts of registration records by county, ZIP, city, make, model year, body type, registration class or fuel, from the 12.6M-row record-level file. Also filters on scofflaw / suspension / revocation flags.
`ny_dmv_ev_adoption(...)`	ELECTRIC-fuel registration counts plus an EV share of all registered vehicles, per county / ZIP / city / make / model year.
`ny_dmv_offices(...)`	175 NYS DMV offices with address, public phone, weekday hours and coordinates.
`ny_dmv_road_test_sites(...)`	444 active road test sites with the test types each administers and written directions to the starting point.
`ny_dmv_driving_schools(...)`	573 DMV-licensed driving schools with school number, phone and the courses each is licensed to teach.
`ny_dmv_licensed_facilities(...)`	54,563 DMV-licensed businesses — inspection stations, repair shops, dealers, dismantlers — searchable, or counted by county / city / ZIP / licence type.

Auth

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

Per-state gotchas

record_type is the first thing to get right. w4pv-hbkt mixes road vehicles (VEH, 11.4M rows) with trailers (TRL), boats (BOAT) and snowmobiles (SNOW). Every registration query defaults to VEH; an unfiltered sum is a fleet of things, not a fleet of cars.
County names are unabbreviated and upper case, and NYC boroughs use the county name. Brooklyn is KINGS, Manhattan is NEW YORK, Staten Island is RICHMOND. The Bronx and Queens keep their names.
make is truncated to five characters. Toyota is stored as TOYOT, Chevrolet as CHEVR, Volkswagen as VOLKS. Three makes collapse to a slash form instead: ME/BE (Mercedes-Benz), HA/DA (Harley-Davidson), LA/RO (Land Rover). The pack cuts and aliases the caller's make automatically, so pass the everyday name.
New York has one ELECTRIC fuel code. Battery-electric and plug-in hybrid vehicles are not separable in this source. Washington splits them — see wa_dmv_ev_population.
The facility register spells counties differently from the registration file. nhjr-rpi2 stores the first four letters of the county with spaces removed: SUFF, NASS, NEWY. The pack accepts either spelling.
The facility register keeps expired licences. Rows carry an expiration_date, and some are years past. Check it before treating a row as a currently valid licence.
A facility holds one row per licence. A repair shop that is also a public inspection station appears once under RS and once under ISP, so licence counts exceed the number of distinct businesses.
sum_of_returned_rows is not a total. Row lists are cut off by limit; total_vehicles (a separate full count over the same filters) is the figure to quote.

Data sources

Registrations — https://data.ny.gov/resource/w4pv-hbkt.json (Vehicle, Snowmobile and Boat Registrations)
Offices — https://data.ny.gov/resource/9upz-c7xg.json (DMV Office Locations)
Road test sites — https://data.ny.gov/resource/n6g4-x6f5.json (DMV Road Test Sites)
Driving schools — https://data.ny.gov/resource/3p6i-cv8y.json (DMV Driving Schools)
Licensed facilities — https://data.ny.gov/resource/nhjr-rpi2.json (Facilities Licensed by the DMV)

Quick Start

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

json

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

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

json

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

Using with ask_pipeworx

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

code

ask_pipeworx({ question: "your question about New York State DMV data" })

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

License

MIT

question	string	required	Your question or request in natural language. Accepts query, q, prompt, text, input as aliases.
query	string	optional	Alias for question.
q	string	optional	Alias for question.
prompt	string	optional	Alias for question.
text	string	optional	Alias for question.
input	string	optional	Alias for question.

question	string	required	Your question or request in natural language. Accepts query, q, prompt, text, input as aliases.
query	string	optional	Alias for question.
q	string	optional	Alias for question.
prompt	string	optional	Alias for question.
text	string	optional	Alias for question.
input	string	optional	Alias for question.

question	string	required	Your question in natural language. Accepts query, q, prompt, text, input as aliases.
query	string	optional	Alias for question.
q	string	optional	Alias for question.
prompt	string	optional	Alias for question.
text	string	optional	Alias for question.
input	string	optional	Alias for question.

question	string	required	The research question, in natural language. Broad/multi-part is fine — decomposition is the point.
depth	string	optional	How many facets to research in parallel: quick=3 (single hop), standard=5 (default; adds a gap-recovery hop that re-angles unanswered facets + a contradictions[] scan across findings), thorough=8 (paid; adds a full iterative hop that chases leads + recovers gaps, plus the contradictions[] scan).

query	string	required	Natural language description of what you want to do (e.g., "analyze housing market trends", "look up FDA drug approvals", "find trade data between countries"). Accepts task, q, description, search as aliases.
task	string	optional	Alias for query.
q	string	optional	Alias for query.
description	string	optional	Alias for query.
search	string	optional	Alias for query.
limit	number	optional	Maximum number of tools to return (default 20, max 50)

type	string	required	Entity type: "company" or "drug".
value	string	required	For company: ticker (AAPL), CIK (0000320193), or name. For drug: brand or generic name (e.g., "ozempic", "metformin").

claim	string	required	Natural-language factual claim, e.g., "Apple's FY2024 revenue was $400 billion" or "Microsoft made about $100B in profit last year".
tolerance_pct	number	optional	Max percent deviation still graded approximately_correct (0.5–50). Overrides the tolerance implied by the claim wording — set 1–2 for hallucination detection where any material error must be refuted. Default: implied by wording, capped at 5.

package	string	required	npm package name. Scoped packages (e.g. "@types/node") are accepted.
version	string	optional	Specific version to check (e.g., "18.3.1"). Defaults to the latest published version when omitted.

market	string	required	Polymarket slug ("will-bitcoin-hit-150k-by-june-30-2026"), full URL ("https://polymarket.com/event/..."), or question text ("Will Bitcoin hit $150k by June 30?")
depth	string	optional	quick = 2-3 evidence sources, thorough = full fan-out. Default thorough.
include_raw	boolean	optional	Default false. When false (recommended), FRED/FDA/GDELT/Federal-Register evidence is summarized to the few fields agents actually use — keeps responses under ~20KB. Pass true to get full upstream payloads (50KB-500KB) when you need to recompute deltas, cite specific observations, or post-process.

event	string	optional	Single-event mode (use this if you know the specific Polymarket event): event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k". Full Polymarket URLs also accepted.
topic	string	optional	Cross-event mode (use this if you want to scan related events across the platform): a topic or seed question like "Fed rate decision" or "Strait of Hormuz traffic returns to normal". Tool searches Polymarket for related events and checks monotonicity across them.

window	string	optional	Polymarket volume window to filter markets. Default 1wk.
limit	number	optional	Top N edges to return after ranking. Default 10, max 25.
min_edge_pp	number	optional	Minimum \|edge\| in percentage points to include (default 0.5). Edge is evaluated NET of slippage.
slippage_pp	number	optional	Assumed execution slippage in percentage points per leg (default 0.3). Subtracted from raw \|edge\| before ranking and Kelly sizing. Polymarket has zero trading fees as of 2024 but bid/ask + thin depth typically eats 20-50bp per trade. Bump for very thin partitions; drop to 0 if you have a smarter fill model.
category_filter	string	optional	Comma-separated list to restrict the output: "model_driven" (crypto_price + news_momentum), "structural_arbitrage" (partition_overround), "concentrated_longshot". Combine like "model_driven,structural_arbitrage". Default: all.
min_kelly	number	optional	Minimum half-Kelly fraction (as decimal, e.g. 0.005 = 0.5% of bankroll) to include single-leg opportunities. Default 0 (no filter). Skips opportunities that are too small to bet sensibly even if the edge is large.
min_partition_leg_kelly	number	optional	Minimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at the parent level by design (basket trades don't compose to single-leg Kelly), so min_kelly never filters them — this knob applies to the per-leg Kelly inside top_legs instead. Use to suppress thin partitions whose individual leg edges aren't worth the per-leg slippage cost.
min_liquidity	number	optional	Tradeable-edge filter. Minimum $ liquidity on the representative market (or for partition_overround, on at least one top_leg). Default 0 (no filter). Set to 5000 to drop thin-book opportunities where executing the edge would walk the book past breakeven.
max_spread_pp	number	optional	Tradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books — anything wider eats most plausible edges.

days	number	optional	Lookback in days (default 14, clamp 2-30).
window	string	optional	Which polymarket_edges window family to read snapshots for: 24hr \| 1wk \| 1mo (default 1wk).

url	string	required	Full URL of the site to summarize, e.g. "https://example.com" or a specific landing page.
max_links	number	optional	Maximum number of link entries to include (default 25, max 50).

entity	string	required	The thing to ask about. Brand/business name, product name, person, or topic. E.g. "Pipeworx", "OpenInvoice", "Acme Corp pricing".
context	string	optional	Optional: a phrase locating the entity (e.g. "Boston restaurant", "B2B SaaS"). Helps disambiguate common names.
models	array	optional	Which models to probe. Supported: "workers-ai" (free default), "anthropic" (requires _apiKey). Omit for just workers-ai.
_apiKey	string	optional	Optional Anthropic API key (sk-ant-...) — only needed if "anthropic" is in models. Passed straight through to api.anthropic.com.

entities	array	required	Array of 2-8 entities to compare (brand/business/product names). First entry treated as the "subject" for narrative; rest are competitors.
context	string	optional	Optional shared context applied to every probe (e.g. "B2B SaaS", "Boston restaurant"). Disambiguates common names.
models	array	optional	Which models to probe. Supported: "workers-ai" (free default), "anthropic" (requires _apiKey). Omit for just workers-ai.
_apiKey	string	optional	Optional Anthropic API key — only if "anthropic" is in models. Passed to api.anthropic.com per probe.

type	string	required	Subscription type.
params	object	required	Type-specific filter. sec_8k: {ticker:"AAPL", items?:["5.02","1.01"]}. polymarket_edge: {topic:"fed", min_spread_bps?:500}. fred_series: {series_id:"UNRATE"}. patent_grant: {applicant:"Apple Inc."}. clinical_trial: {sponsor?:"Pfizer", condition?:"lung cancer", phase?:"PHASE3"} (sponsor or condition required).
delivery	object	optional	Optional delivery channels in addition to the always-on persistent feed. {email:"you@x.com"} sends a templated alert per fired event. {sms:"+15551234567"} sends an SMS per event — must match the verified phone on the caller's account (verify at https://pipeworx.io/account first; 10/day cap). {webhook:"https://..."} POSTs each event JSON to your endpoint, HMAC-signed — the response includes delivery.webhook_secret (whsec_…) ONCE; verify X-Pipeworx-Signature = sha256 HMAC of "<X-Pipeworx-Timestamp>.<raw body>". Auto-disabled after 10 consecutive failing runs.

type	string	required	Entity type. Only "company" supported today.
value	string	required	Ticker (e.g., "AAPL") or zero-padded CIK (e.g., "0000320193").
since	string	required	Window start — ISO date ("2026-04-01") or relative ("7d", "30d", "3m", "1y"). Use "30d" or "1m" for typical monitoring.

topic	string	optional	Pre-mapped: fed \| btc \| cpi \| gdp \| sp500 \| recession \| next_pope \| next_uk_pm \| next_israel_pm \| 2028_president
kalshi_event_ticker	string	optional	Explicit Kalshi event ticker, e.g. "KXFED-26OCT". Overrides the topic-mapped Kalshi side.
polymarket_event_slug	string	optional	Explicit Polymarket event slug, e.g. "fed-decision-in-june-825". Overrides the topic-mapped Polymarket side.

market	string	optional	Single-market mode: market slug or full polymarket.com URL.
event	string	optional	Basket mode: event slug or full polymarket.com URL — checks every leg of the partition.
side	string	optional	Single-market: buy_yes \| sell_yes \| buy_no \| sell_no (default buy_yes). Basket: sell_yes \| buy_yes (default auto — sell if partition sum > 1, buy if < 1).
size_usd	number	optional	Single-market: USD to spend (buys) or target proceeds (sells). Basket: settlement notional — shares per leg, each paying $1 at resolution. Default 1000, clamp 10–1,000,000.

key	string	required	Memory key (e.g., "subject_property", "target_ticker", "user_preference")
value	string	required	Value to store (any text — findings, addresses, preferences, notes)

county	string	optional	New York county name, unabbreviated and matched case-insensitively. Brooklyn is "KINGS", Manhattan is "NEW YORK", Staten Island is "RICHMOND", Queens is "QUEENS", the Bronx is "BRONX".
city	string	optional	City or town of the registrant, e.g. "BROOKLYN", "BUFFALO", "ALBANY".
zip	string	optional	Five-digit New York ZIP code, e.g. "11201".
make	string	optional	Vehicle make; pass the everyday name, e.g. "TOYOTA", "TESLA", "FORD", "MERCEDES". New York stores makes cut to five characters (TOYOTA is filed as TOYOT), and the full name is cut to match automatically.
model_year	string	optional	Four-digit model year, e.g. "2024".
body_type	string	optional	Body-type code, e.g. "SUBN" (SUV/station wagon), "4DSD" (4-door sedan), "PICK" (pickup), "MCY" (motorcycle), "VAN".
registration_class	string	optional	Registration class code, e.g. "PAS" (passenger), "COM" (commercial), "MOT" (motorcycle), "SRF" (semi-trailer).
record_type	string	optional	Which register to read: VEH, TRL, BOAT, SNOW. Defaults to VEH (road vehicles); TRL is trailers, BOAT is vessels, SNOW is snowmobiles.
scofflaw_indicator	string	optional	Set "Y" to count only registrations flagged as scofflaw (unpaid tickets), "N" for the rest.
suspension_indicator	string	optional	Set "Y" to count only registrations under suspension, "N" for the rest.
revocation_indicator	string	optional	Set "Y" to count only revoked registrations, "N" for the rest.
fuel_type	string	optional	Fuel; plain words are mapped to New York's codes, e.g. "gas" → GAS, "diesel" → DIESEL, "electric" → ELECTRIC, "cng" → COMP N/G. The published codes are GAS, DIESEL, ELECTRIC, NONE, FLEX, COMP N/G, OTHER, PROPANE.
group_by	string	optional	Breakdown dimension: county, zip, city, fuel, make, model_year, body_type, registration_class, record_type, state. Defaults to county.
limit	number \| string	optional	Max rows to return (default 25, max 200).

io.github.pipeworx-io/ny-dmv MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

ask_pipeworx

ask_pipeworx_beta

ask_pipeworx_grounded

search_within

deep_research

discover_tools

resolve_entity

compare_entities

subscribe

unsubscribe

list_subscriptions

recent_alerts

entity_profile

recent_changes

validate_claim

scan_dependency

bet_research

polymarket_arbitrage

polymarket_edges

polymarket_kalshi_spread

polymarket_fill_risk

polymarket_edge_tracker

pipeworx_trending

suggest_questions

generate_llms_txt

ai_visibility_check

scan_competitor_ai_presence

pipeworx_feedback

remember

recall

forget

ny_dmv_vehicle_registrations

ny_dmv_ev_adoption

ny_dmv_offices

ny_dmv_road_test_sites

ny_dmv_driving_schools

ny_dmv_licensed_facilities