Carvector
About
Give your AI agent real vehicle data. An MCP server that lets Claude, Cursor, ChatGPT, or any MCP-capable client query the CarVector API natively — vehicle specs, representative images, federal recalls, and OBD-II diagnostic trouble codes.
Details
- Author
- carvectorio
- Downloads
- 356
- Categories
- Developer Tools, Other, AI
Jump to
- Search vehicles by year, make, model with IDs and specs
- Get full specs for one vehicle — engine, drivetrain, body, image, recall count
- Return federal recall campaigns — component, summary, consequence, remedy
- Look up OBD-II codes with title, category, severity, safety/emissions flags
- Agent chains search_vehicles → get_vehicle / get_recalls naturally
- Zero telemetry, analytics, or phone-home; writes nothing to disk
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
CarvectorCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via npx -y carvector-mcp --key cv_your_key or configure an mcpServers block with the CARVECTOR_API_KEY environment variable. For remote HTTP MCP, point to https://api.carvector.io/v1/mcp with a Bearer token. Restart your client and ask about a vehicle.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"carvector": {
"carvector": {
"command": "npx",
"args": [
"-y",
"carvector-mcp"
],
"env": {
"CARVECTOR_API_KEY": "cv_your_key"
}
}
}
}
}McpServers
{
"carvector": {
"command": "npx",
"args": [
"-y",
"carvector-mcp"
],
"env": {
"CARVECTOR_API_KEY": "cv_your_key"
}
}
}Give your AI agent real vehicle data.AnMCPserver that lets Claude, Cursor, ChatGPT, or any MCP-capable client query theCarVectorAPI natively — vehicle specs, representative images, federal recalls, owner complaints, service bulletins, defect investigations, and OBD-II diagnostic trouble codes.
Models hallucinate car data. They invent horsepower numbers, miss recalls filed last week, and guess at what a trouble code means.carvector-mcpgives your agentstructured, sourced answers it can citeinstead of a confident guess.
· MIT · Free tier, no card →carvector.io
1. Get a free API keyatcarvector.io— 500 requests a month, no credit card.
2. Add it to your MCP client.Most clients use anmcpServersblock:
{ "mcpServers": { "carvector": { "command": "npx", "args": ["-y", "carvector-mcp"], "env": { "CARVECTOR_API_KEY": "cv_your_key" } } } }
That's it. Restart your client and ask it about a vehicle.
Prefer a remote server?If your client supports HTTP MCP, skip the install and point it straight at the hosted endpoint:
{ "mcpServers": { "carvector": { "url": "https://api.carvector.io/v1/mcp", "headers": { "Authorization": "Bearer cv_your_key" } } } }
The agent chains them naturally:search_vehiclesto resolve an id, thenget_vehicle,get_recalls,get_complaints,get_tsbs, orget_investigations.
You:"Is a P0300 code serious?"
→ carvector.lookup_dtc({ code: "P0300" }) { "code": "P0300", "title": "Random/Multiple Cylinder Misfire Detected", "category": "Powertrain", "severity": "High", "safety_risk": true, "emissions_related": true }
Your agent answers:"Yes — P0300 is a high-severity, safety-related misfire code. Don't keep driving on it."Sourced, not guessed.
- A service-advisor copilotthat pulls a customer's exact trim, open recalls, the manufacturer's documented fix (TSBs), the complaint pattern behind a symptom, and a decoded check-engine code — in one turn, no tab-switching.
- A consumer car chatbotthat answers "what engine does my truck have" and "is it under recall" with real data instead of a hallucination.
- A coding/automotive agentthat needs structured vehicle knowledge as a tool, not a wall of scraped text to parse.
carvector-mcpis an open-source, thin client. It bundlesno data— every call forwards to the CarVector API, authenticated with your key. What you get back:
- Vehicles— a broad catalog (1925–2029), broken out by trim and engine variant, with representative illustrations (not photos).
- Recalls— federal recall campaigns mapped to year / make / model.
- Complaints— owner-filed complaints aggregated by component (with crash / fire / injury counts) plus the most recent filings, mapped to a vehicle.(Pro plan.)
- Service bulletins (TSBs)— the manufacturer's technical service-bulletin index — metadata, not the documents.(Business plan.)
- Investigations— federal defect investigations, a leading indicator that often precedes a recall.(Business plan.)
- DTC reference— OBD-II codes classified by category, severity, and safety/emissions flags.Reference only — repair-cost economics is on the roadmap, not in responses today.
Calls count against your plan's rate limit and show up in yourdashboard, exactly like a REST request.
This client is ~150 lines of readable JavaScript — please read them. It:
- talks toone host only—api.carvector.io(grepindex.js, it's the only URL),
- sends your keyonlyas aBearerheader to that host, nowhere else,
- haszerotelemetry, analytics, or phone-home, and writes nothing to disk,
- depends on exactly one package: the official@modelcontextprotocol/sdk.
Your key stays on your machine. Set it via theCARVECTOR_API_KEYenv var (preferred);--keyworks too but, like any CLI argument, is visible in process listings.
MIT. The client is open source; the data is served byCarVector.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Real-time Amazon data API built for AI agents. 200M+ products, 1B+ reviews, live BSR, pricing, and competitor data as clean JSON. 10 agent skills for market research, competitor monitoring, pricing, listing audits, and more. 1,000 free credits.
Predict anything with Chronulus AI forecasting and prediction agents.
Get access to Kaggle's datasets, models, competitions, notebook and benchmarks.
Access Oceanic and Atmospheric Data using AI Agents
A collection of 19 professional tools for chemical molecular processing based on the Model Context Protocol (MCP).
An MCP server for interacting with Dappier's Retrieval-Augmented Generation (RAG) models.
Performs gene set enrichment analysis using the Enrichr API, supporting all available gene set libraries.
An MCP server for the gget bioinformatics library, enabling standardized access to genomics tools and databases.
An MCP server for Hierarchical Event Descriptors (HED) that automates sidecar creation and annotation for BIDS event files using LLMs.
Provides linear programming (LP) and mixed-integer programming (MIP) optimization capabilities using the HiGHS solver.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
