Model Context Protocol (MCP) Server: io.github.pipeworx-io/nj-mvc

This MCP server exposes “New Jersey MVC inspection facilities and 2.3M inspection results by make and model.” It is identified by the slug io-github-pipeworx-io-nj-mvc and is categorized under topics including mcp, mcp-server, model-context-protocol, pipeworx, and nj-mvc.

🛠️ Key Features

Provides access to New Jersey MVC inspection facilities
Provides 2.3M inspection results organized by make and model

🚀 Use Cases

Query or browse New Jersey MVC inspection data by make and model
Support data lookup workflows involving inspection facilities and results

⚡ Developer Benefits

Built for the Model Context Protocol (MCP) ecosystem (as indicated by topics)
Clear domain scope: NJ MVC inspection facilities and large-scale results dataset

⚠️ Limitations

No tool count or additional behavior details are provided in the available source data

@pipeworx/nj-mvc

New Jersey DMV data: Motor Vehicle Commission (MVC) inspection and emission-repair facilities, and the record-level vehicle-inspection results file. Keyless.

What New Jersey calls its DMV

New Jersey's agency is the Motor Vehicle Commission, universally the MVC. Residents say "MVC agency" where other states say "DMV office", so the tool descriptions name both.

Tools

Tool	What it returns
`nj_mvc_inspection_facilities`	All 1,167 licensed private/state inspection and emission-repair facilities — name, address, town, phone, licence id, what they inspect
`nj_mvc_vehicle_inspections`	Pass/fail rates aggregated from 2,314,032 individual inspection tests, by make, model, model year, fuel, body style, test type or cylinder count

Auth

None. data.nj.gov is a public Socrata portal; the public rate limit handles these queries without an app token.

The distinctive dataset

gvur-kt7q is 2,314,032 per-test records, each carrying make, model, model year, fuel, full OBD-II readiness monitors, and separate emissions and safety verdicts. No other state publishes inspection outcomes at that grain, which is what makes "which cars fail New Jersey emissions inspection most" answerable at all.

Live-verified statewide numbers: 2,080,550 passes and 233,477 failures — about a 10% overall fail rate. Split by test type, initial tests fail 8.7% of the time and re-tests 26.7%.

min_tests (default 100) exists because a fail-rate ranking without it is meaningless — a model with three tests and two failures would top every table. sort="fail_rate" ranks by failure share; the default ranks by volume.

Gotchas worth knowing

These are live-verified behaviours, not guesses:

The facility file's county column contradicts the address on some rows. A WATERFORD WORK address — Waterford Works is in Camden County — is labelled MORRIS. The county filter is kept because agents ask for counties, but prefer city when the answer has to be right, and the response says so in its note.
These are inspection and repair shops, not licensing agencies. Someone asking where to renew a New Jersey licence needs an MVC agency, which this file does not contain. The tool description is explicit so a router does not send that question here.
Town names are abbreviated and upper case (WATERFORD WORK, not "Waterford Works"), so a partial city string matches more reliably than a full one.
Coordinates are missing on some facility rows — geocoded_column is absent rather than null, so latitude/longitude come back null for those.
Inspection rows are tests, not vehicles. A car that fails and returns is counted twice; test_type="R" isolates the re-tests.
emissions_failures and safety_failures can overlap and do not have to sum to failed, which is the overall verdict column.
Makes and models are upper case and abbreviated (TOYOTA, CAMRY, F150).
Model years include junk — a handful of rows carry 2033 and 2041. min_tests filters them out of any ranking by construction.
nja_vhcl_type is empty on every row despite being documented as P/T/H, so it is not offered as a group_by. nja_body_style is the working equivalent.
as_of is fetched concurrently with the data, not after it. The 2.3M-row aggregate earns a Socrata throttle, and the metadata helper does not retry, so a sequential call intermittently returned a null refresh date.
The inspection file was last refreshed 2026-03-12; the facility file 2026-07-20. Both are reported in as_of rather than assumed current.

Data sources

data.nj.gov Socrata t6tk-mr48 — Vehicle Inspection Facility Locations
data.nj.gov Socrata gvur-kt7q — Vehicle Inspection Data

Quick Start

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

json

{
  "mcpServers": {
    "nj-mvc": {
      "url": "https://gateway.pipeworx.io/nj-mvc/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 Jersey MVC 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.

text	string	required	The document text to search inside (max ~200K chars).
query	string	required	Natural-language query — what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin".
limit	number	optional	Max passages to return (1-20, default 5).

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).

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)

city	string	optional	Town name, matched as a substring, e.g. "Edison", "Long Branch". More reliable than county.
county	string	optional	County name, e.g. "Morris", "Monmouth". Upstream mislabels some rows — prefer city.
zip	string	optional	Five-digit New Jersey ZIP code, or a prefix, e.g. "07740" or "077".
name	string	optional	Business-name substring, e.g. "MIDAS", "AUTO".
facility_type	string	optional	Facility category: "Private Inspection Facility", "Emission Repair Facility", "State Inspection Facility", "State Specialty Inspection Facility". Substrings such as "private" or "emission" also work.
inspection_type	string	optional	What the shop inspects: "Auto Only", "Emission Repair Only", "Diesel Only", "Auto and Diesel". "diesel" alone matches both diesel categories.
limit	number \| string	optional	Max facilities to return (default 50, max 200).

make	string	optional	Vehicle make, matched as a substring, e.g. "TOYOTA", "FORD", "HONDA".
model	string	optional	Vehicle model, matched as a substring, e.g. "CAMRY", "F150".
model_year	string	optional	Four-digit model year, e.g. "2015".
fuel	string	optional	Fuel; plain words map to New Jersey's codes, e.g. "gas" (GASO), "diesel" (DIES), "hybrid" (ELEG), "electric" (ELEC).
test_type	string	optional	I for an initial test, R for a re-test. Defaults to every test.
group_by	string	optional	Breakdown dimension: make, model, model_year, fuel, body_style, test_type, cylinders. Defaults to make.
min_tests	number \| string	optional	Drop groups with fewer than this many tests before ranking, so a one-car model cannot top a failure-rate table. Default 100.
sort	string	optional	tests (default) ranks by volume; fail_rate ranks by the share of tests that failed.
limit	number \| string	optional	Max groups to return (default 25, max 200).

Model Context Protocol (MCP) Server: io.github.pipeworx-io/nj-mvc

🛠️ 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

nj_mvc_inspection_facilities

nj_mvc_vehicle_inspections