Which AI clients work with the VehDB MCP server?

Any MCP-compatible client over HTTP: Claude (web and desktop), ChatGPT with developer mode, Claude Code, Cursor, VS Code and custom agents built on the Model Context Protocol. Clients that support MCP sign-in connect through OAuth with dynamic client registration; others use an API token.

REAL MCP SERVER · MODEL CONTEXT PROTOCOL OVER HTTP

The vehicle data MCP server
for AI agents.

Paste one config block and Claude, Cursor or your internal copilot can search the catalog, read specs, check live recalls and find tire fitment — as native tools, grounded in 1,342,720 real records, with the same token as the REST API.

Get an API token — free Connect in 3 steps

One-click AI connectors

Add to Claude

MCP calls share your plan's API quota — the free tier includes 100 calls/mo, no card.

claude_desktop_config.json

# The whole integration:

{

"mcpServers": {

"vehdb": {

"url": "https://mcp.vehdb.com/mcp",

"headers": { "Authorization": "Bearer TOKEN" }

}

# Your agent now has:

tools → search_vehicles · get_vehicle · decode_vin · recalls_for_vehicle · complaints_for_vehicle · model_year_scorecard · vehicle_insights · tire_sizes_for_vehicle · vehicles_for_tire_size · my_lists · api_usage · resolve_vehicle · service_bulletins_for_vehicle · decode_hin · tire_dot_check · energy_prices

What is the VehDB MCP server?

A hosted bridge between AI agents and a real, enriched vehicle database.

The Model Context Protocol (MCP) is an open standard for connecting AI agents to external tools and data. VehDB runs a hosted MCP server at https://mcp.vehdb.com/mcp that exposes our cleaned, cross-referenced vehicle database — 853,870 cars, 233,450 motorcycles, 84,300 boats and 171,100 tire fitments, enriched with EPA fuel economy and live NHTSA recalls — to any MCP-compatible client.

Instead of scraping pages, pasting spec sheets into a prompt, or hand-writing function-calling schemas, you paste one config block. The agent discovers every tool automatically and starts answering questions with structured, current data — the same data, same token and same quota as the REST API and the dashboard workspace.

Sixteen tools. Real answers.

Typed inputs, JSON output — the model calls them directly, no prompt gymnastics.

search_vehicles

Search cars, motorcycles, boats or tire sizes by make, model, year, body, fuel and drivetrain — the agent resolves any vehicle the user mentions.

"Find me 2024 hybrid SUVs from Toyota."

get_vehicle

Fetch a single record by type and UUID — full specifications plus EPA economy in one call.

"Pull the full spec sheet for that Tucson."

recalls_for_vehicle

Live NHTSA recall campaigns, open defect investigations and the NCAP crash-test rating for a car or motorcycle; for a boat, the U.S. Coast Guard recalls filed under its builder's codes.

"Are there any open recalls on a 2022 Bolt?"

service_bulletins_for_vehicle

NHTSA manufacturer communications for a model year: service bulletins, warranty extensions and special coverage, over-the-air updates, with the most named components.

"Is there a warranty extension on the 2019 Santa Fe engine?"

complaints_for_vehicle

NHTSA owner-complaint statistics by component and model year — the reliability signal that precedes recalls.

"Is the 2018 Camry a reliable year?"

model_year_scorecard

Every model year of one make/model side by side — complaints with a percentile against the same model year, recalls, investigations, NCAP stars, fatal-crash involvement and mpg — with the best and worst year called out.

"Which year of the Honda Accord should I buy?"

vehicle_insights

Aggregate reports without record sweeps: most complained-about vehicles, fatal-crash rankings by vehicle and body class, engine trends, Canadian fuel economy, recall age, rim sizes and FARS-vs-CRSS crash severity.

"Which 2019 vehicles drew the most complaints?"

tire_sizes_for_vehicle

OEM and alternate tire sizes that fit a given make/model/year, with computed geometry (±3%).

"What tires fit a 2024 Camry?"

vehicles_for_tire_size

Reverse fitment: every vehicle that runs a tire size as OEM or as an accepted alternate.

"Which cars use 225/45R17?"

decode_vin

Decode a VIN with NHTSA vPIC and get the matching VehDB cars, motorcycles and tire fitments by uuid.

"What is 1HGCM82633A004352, and what tires does it take?"

my_lists

The user's saved vehicles — the same lists curated in the dashboard, with notes and part numbers.

"Which vehicles in our lists have open quotes?"

api_usage

The plan, rate limit and how much of this month's call and record quota is left.

"How many lookups do we have left this month?"

resolve_vehicle

A vehicle as the user typed it, in the catalogue's spelling and in the spellings NHTSA files its recalls under.

"Is "2012 Ram 1500" filed as a Dodge at NHTSA?"

decode_hin

Decode a boat's Hull Identification Number: the builder from its U.S. Coast Guard code, the build month, model year and the builder's recalls; with include_history, the accidents and documentation record reported under the hull.

"Who built the boat with HIN SER12345D404, and what year is it?"

tire_dot_check

Read a tire's DOT code: the plant, the week it was made, its age and the NHTSA tire recalls covering that plant and week.

"How old is a tire marked DOT U2LL LMLR 2219?"

energy_prices

Latest EIA gasoline, diesel and electricity prices for a state, with a yearly fuel cost for any mpg.

"What would a 28 mpg car cost to fuel in California?"

Tool reference

Each tool is typed and self-describing — the agent reads the schema, you don't write one.

Tool	Inputs	Returns
`search_vehicles`	`type, make, model, year, limit, page`	Paginated matching records with core specs
`get_vehicle`	`type, uuid`	Full specifications + EPA economy fields
`decode_vin`	`vin`	Decoded VIN fields + matching car, motorcycle and tire-fitment uuids
`recalls_for_vehicle`	`car, motorcycle or boat uuid (or make, model, year, or vin)`	Live NHTSA recall campaigns, open investigations + NCAP rating; USCG recalls for a boat
`service_bulletins_for_vehicle`	`car or motorcycle uuid (or make, model, year)`	Counts by type, most named components, warranty extensions, latest communications
`complaints_for_vehicle`	`make, model, year`	Complaint totals, top components, trend by year, neighbouring model years
`model_year_scorecard`	`make, model`	Per model year: trims, mpg, complaints + percentile, top component, recalls, investigations, NCAP, FARS/CRSS crashes, best and worst year
`vehicle_insights`	`report, year / make / model, year_min, year_max`	Ranked or trended rows for the chosen report, sources labelled
`tire_sizes_for_vehicle`	`make, model, year, page`	OEM + alternate sizes, with the fitment disclaimer
`vehicles_for_tire_size`	`size, make, year, page`	Vehicles running the size as OEM or alternate
`my_lists`	`page (uses the token owner)`	The user's saved lists with notes
`api_usage`	`— (uses the token owner)`	Plan, rate limit, calls and records used this month
`resolve_vehicle`	`q, year`	Catalogue make/model spelling + the NHTSA spellings (nhtsa_match)
`decode_hin`	`hin`	Builder (USCG code), serial, build month and year, model year, catalogue makes, builder recalls
`tire_dot_check`	`tin, size, brand`	Plant, build week and year, age, matching NHTSA tire recalls, with the disclaimer
`energy_prices`	`state, mpg, fuel_type`	Weekly fuel and monthly electricity prices; annual fuel cost for the mpg

The same records are available over the REST API — see the full docs.

Ask it anything about a vehicle

Questions your AI agent can answer with VehDB

Connect VehDB to Claude, ChatGPT or Cursor and ask in plain words. The agent picks the tools; the answers below are computed from today's data.

Any recalls on a 2021 Tesla Model S?

Calls recalls_for_vehicle

23 recall campaigns, filed by NHTSA under "MODEL S" (VehDB matches every spelling). The newest, 26V283000, covers back over prevention: software. 5 NHTSA investigations are still open.

Recall campaigns: 23
Open investigations: 5
Newest: 2026-05-04