RecallChecker — Vehicle Safety Recalls

Official registry AI and agents

Check U.S. NHTSA vehicle safety recall campaigns by make, model, and year. Live official data.

What can you do with RecallChecker — Vehicle Safety Recalls?

  • Web tool — search by make / model / year and get a direct answer with the recall count,
  • Reference pages — a page per common vehicle query at /recalls/[make]/[model]/[year],
  • MCP server — the same lookup as a tool any MCP-compatible AI assistant can call:

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code
claude mcp add --transport http recallchecker-vehicle-safety-recalls 'https://mcp.checkrecall.com/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "recallchecker-vehicle-safety-recalls": {
            "type": "http",
            "url": "https://mcp.checkrecall.com/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. RecallChecker
  2. Features
  3. Data source
  4. Tech
  5. Development
  6. License

RecallChecker

A free tool + MCP server that answers one question well: "Is this vehicle recalled?" Enter a car's make, model, and year and get an instant, plain-language list of open U.S. safety recalls — pulled live from official NHTSA data, with the hazard, the remedy, the date, and a link to the official notice.

Live: checkrecall.com · MCP: https://mcp.checkrecall.com/mcp

Features

  • Web tool — search by make / model / year and get a direct answer with the recall count, campaign details, dates, and official links. Results live at a shareable, crawlable URL.
  • Reference pages — a page per common vehicle query at /recalls/[make]/[model]/[year], each backed by live data.
  • MCP server — the same lookup as a tool any MCP-compatible AI assistant can call: check_vehicle_recalls(make, model, year), returning a human-readable summary plus structured data.

Data source

SourceProvidesNotes
NHTSA Recalls APIU.S. vehicle safety recall campaignsNo API key. api.nhtsa.gov/recalls/recallsByVehicle?make=&model=&modelYear=

Every answer shows the data's "as of" date and links back to the official NHTSA notice. A "no recalls found" result reports the absence of campaigns in NHTSA as of that date — it is not a guarantee of safety and is not VIN-specific. Data sourced from NHTSA (nhtsa.gov).

Tech

Next.js (App Router) + TypeScript, deployed to Cloudflare Workers via OpenNext; response caching on Workers KV. The MCP server is a second Worker that reuses the same lookup core, so the website and the assistant tool never duplicate lookup logic.

Development

npm install
npm run dev            # local dev (wrangler)
npm test               # unit tests
npm run deploy         # deploy the web app
npm run mcp:dev        # local MCP server
npm run mcp:deploy     # deploy the MCP server

Build uses next build --webpack (Turbopack output is not yet compatible with OpenNext).

License

MIT — see LICENSE.

Frequently asked questions

What is RecallChecker — Vehicle Safety Recalls?

Check U.S. NHTSA vehicle safety recall campaigns by make, model, and year. Live official data.

How do I install RecallChecker — Vehicle Safety Recalls?

It runs as a remote server. In Claude Code: claude mcp add --transport http recallchecker-vehicle-safety-recalls 'https://mcp.checkrecall.com/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does RecallChecker — Vehicle Safety Recalls need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is RecallChecker — Vehicle Safety Recalls open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains RecallChecker — Vehicle Safety Recalls?

It is published by ollo12-prog. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.