[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [NHTSA vehicle data dictionary](https://spiral.ai/integrations/gemini-cli/nhtsa-vehicle-data-dictionary)

# How to Use NHTSA vehicle data dictionary in Gemini CLI

Returns vehicle attribute definitions and data types, or the accepted values for a lookup attribute. Use it to explain decoded specifications and translate NHTSA error codes into readable messages.

|  |  |
| --- | --- |
| Model | NHTSA vehicle data dictionary |
| Available through | Alexandria |
| Category | Public Records |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with NHTSA vehicle data dictionary in Gemini CLI

- Use NHTSA vehicle data dictionary to retrieve the definitions and types of vehicle attributes. Add readable descriptions for the attributes our inventory importer currently stores.
- Use NHTSA vehicle data dictionary to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from NHTSA vehicle data dictionary and tell me what changed since last week.
- Check NHTSA vehicle data dictionary and summarize what you find in three bullet points.
- Pull the newest data from NHTSA vehicle data dictionary and give me the result as a table.

## How to set up NHTSA vehicle data dictionary in Gemini CLI

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run NHTSA vehicle data dictionary**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "vpic-nhtsa-dot-gov/vehicles/list_variables",
    "input": {
      "variable": "<variable>"
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds NHTSA vehicle data dictionary on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## NHTSA vehicle data dictionary tools and prices

- [NHTSA vPIC vehicle decoder · List variables](https://spiral.ai/tools/alexandria/vpic-nhtsa-dot-gov/vehicles/list_variables) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| variable |  | — | Variable ID (`143`) or exact name (`Error Code`). Omit for the full dictionary. |

## What can you do with NHTSA vehicle data dictionary in Gemini CLI?

Build vehicle reference tables and inventory checks from NHTSA's manufacturer records and VIN data. A coding agent can map the returned identifiers and attribute definitions into the project's existing data structures.

### Check dealer inventory descriptions

Decode inventory VINs individually or in batches, compare reported vehicle identity with listing descriptions, and explain attributes through the dictionary. Resolve unfamiliar prefixes, manufacturers, makes, and models before flagging a mismatch.

### Standardize fleet vehicle records

Enrich a business fleet's VIN records with available vehicle specifications. Reconcile manufacturer entities, prefixes, make names, and model names, then use attribute definitions to build consistent reporting categories.

### Build a vehicle research reference database

Create reference tables for manufacturers, makes, models, VIN prefixes, and attribute definitions. Use single and batch VIN decoding to attach vehicle characteristics to research records and investigate inconsistent identifiers.

### Build vehicle catalog selection lists

Start with manufacturer records, resolve their business identities and makes, and populate model selections. Add manufacturer prefix references and dictionary definitions so catalog editors can interpret vehicle categories consistently.

### Reconcile commercial trailer intake

Research trailer manufacturers and their makes, models, and WMI prefixes before matching incoming business inventory. Decode individual VIN exceptions or intake batches, using dictionary definitions to interpret trailer attributes.

### Maintain vehicle reference tables

Compare successive retrievals of manufacturer, make, model, prefix, and dictionary records. Review changed business details and reference values before updating a vehicle catalog.

### Explain vehicle identification results

Turn individual or batch decode results into readable vehicle summaries. Explain manufacturer prefixes, compare model names, and translate attribute definitions and decode errors for inventory reviewers.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## NHTSA vehicle data dictionary in other agents

- [Amp](https://spiral.ai/integrations/amp/nhtsa-vehicle-data-dictionary)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/nhtsa-vehicle-data-dictionary)
- [Claude](https://spiral.ai/integrations/claude-desktop/nhtsa-vehicle-data-dictionary)
- [Claude Code](https://spiral.ai/integrations/claude-code/nhtsa-vehicle-data-dictionary)
- [Cline](https://spiral.ai/integrations/cline/nhtsa-vehicle-data-dictionary)
- [Codex](https://spiral.ai/integrations/codex/nhtsa-vehicle-data-dictionary)
- [Cursor](https://spiral.ai/integrations/cursor/nhtsa-vehicle-data-dictionary)
- [Devin](https://spiral.ai/integrations/devin/nhtsa-vehicle-data-dictionary)
- [dots](https://spiral.ai/integrations/dots/nhtsa-vehicle-data-dictionary)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/nhtsa-vehicle-data-dictionary)
- [Gemini](https://spiral.ai/integrations/gemini/nhtsa-vehicle-data-dictionary)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/nhtsa-vehicle-data-dictionary)
- [goose](https://spiral.ai/integrations/goose/nhtsa-vehicle-data-dictionary)
- [Grok](https://spiral.ai/integrations/grok/nhtsa-vehicle-data-dictionary)
- [Grok Build](https://spiral.ai/integrations/grok-build/nhtsa-vehicle-data-dictionary)
- [Hermes](https://spiral.ai/integrations/hermes/nhtsa-vehicle-data-dictionary)
- [Instinct](https://spiral.ai/integrations/instinct/nhtsa-vehicle-data-dictionary)
- [Manus](https://spiral.ai/integrations/manus/nhtsa-vehicle-data-dictionary)
- [Muse](https://spiral.ai/integrations/muse/nhtsa-vehicle-data-dictionary)
- [Muse Code](https://spiral.ai/integrations/muse-code/nhtsa-vehicle-data-dictionary)
- [n8n](https://spiral.ai/integrations/n8n/nhtsa-vehicle-data-dictionary)
- [Notion](https://spiral.ai/integrations/notion/nhtsa-vehicle-data-dictionary)
- [OpenClaw](https://spiral.ai/integrations/openclaw/nhtsa-vehicle-data-dictionary)
- [opencode](https://spiral.ai/integrations/opencode/nhtsa-vehicle-data-dictionary)
- [Perplexity](https://spiral.ai/integrations/perplexity/nhtsa-vehicle-data-dictionary)
- [Raycast](https://spiral.ai/integrations/raycast/nhtsa-vehicle-data-dictionary)
- [VS Code](https://spiral.ai/integrations/vscode/nhtsa-vehicle-data-dictionary)
- [Windsurf](https://spiral.ai/integrations/windsurf/nhtsa-vehicle-data-dictionary)
- [Zapier](https://spiral.ai/integrations/zapier/nhtsa-vehicle-data-dictionary)

## More Gemini CLI guides

- [NHTSA vehicle complaints](https://spiral.ai/integrations/gemini-cli/nhtsa-vehicle-complaints)
- [NHTSA vehicle makes](https://spiral.ai/integrations/gemini-cli/nhtsa-vehicle-makes)
- [NHTSA vPIC vehicle decoder Decode vin](https://spiral.ai/integrations/gemini-cli/nhtsa-vpic-vehicle-decoder-decode-vin)
- [NHTSA vehicle makes and models](https://spiral.ai/integrations/gemini-cli/nhtsa-vehicle-makes-and-models)
- [NHTSA recall campaign details](https://spiral.ai/integrations/gemini-cli/nhtsa-recall-campaign-details)
- [NHTSA vehicle models](https://spiral.ai/integrations/gemini-cli/nhtsa-vehicle-models)

## Questions about NHTSA vehicle data dictionary in Gemini CLI

**Can Gemini CLI use NHTSA vehicle data dictionary?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run NHTSA vehicle data dictionary like any built-in tool.

**How much does NHTSA vehicle data dictionary cost in Gemini CLI?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need an Alexandria account to use NHTSA vehicle data dictionary in Gemini CLI?**

No. Spiral runs NHTSA vehicle data dictionary on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up NHTSA vehicle data dictionary in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while NHTSA vehicle data dictionary runs?**

NHTSA vehicle data dictionary runs in the background. Gemini CLI starts the run, checks on it and gives you the json when it's ready.

**Where does NHTSA get vPIC's information?**

NHTSA codes manufacturer submissions into vPIC after reviewing them. The vehicle descriptions reflect manufacturer-reported information.

**Does vPIC cover vehicles worldwide?**

Its scope is vehicles intended for sale or importation into the United States. Foreign manufacturers can appear, but that does not make vPIC a complete catalog of their vehicles in other markets.

**How far back does vPIC's vehicle coverage go?**

NHTSA states that vPIC is intended for model years 1981 onward. Its API FAQ reports approximately 99% decoding confidence from 1995 onward for most major brands, which is a coverage estimate rather than a guarantee for every attribute.

**How does new information reach vPIC?**

Manufacturer submissions enter the data after NHTSA review. Freshness follows that submission and review process; a newly announced vehicle is not proof that its information has already been processed.

**Does vPIC provide complete equipment information?**

NHTSA explicitly says that missing decoded values do not mean a feature or technology is unavailable on the vehicle. Its records can therefore support an equipment check without establishing a complete installed-equipment list.

