Integration

Rekor CarCheck integration

Rekor CarCheck (formerly the OpenALPR Cloud API) reads license plates and recognizes vehicles in still images. Send an image file or an image URL and get back each plate's number, region and confidence with alternative readings, and, on request, the vehicle's make, model, color, body type, year range and orientation. A configuration lookup lists the supported plate regions and every vehicle label the service can return. The raw base64 upload route is not exposed: send the file itself instead. Authentication is the account's secret key, sent as the secret_key query parameter.

Connect Rekor CarCheck How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Rekor CarCheck.Built from the 3 Rekor CarCheck tools below, on the connection you add once.

What you can do with Rekor CarCheck

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Config, 1 operation

get_configGet configGETLists the plate regions accepted by the country parameter (code, name, aliases) and every label vehicle recognition can return: body types, colors, makes, make_model pairs, orientations and year ranges.

Recognize, 1 operation

recognize_imageRecognize imagePOSTReads the license plates in an uploaded image, and with recognize_vehicle=1 also the vehicle's make, model, color, body type, year range and orientation. Each plate comes with its region, confidence and alternative readings.

Recognize url, 1 operation

recognize_image_urlRecognize image urlPOSTSame as recognize_image for an image the service downloads from a public URL. Reading a remote image needs the Plus plan or above; the Starter plan accepts uploaded images only.

Use Rekor CarCheck from Claude Code, Cursor or Codex

Connect Rekor CarCheck in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Rekor CarCheck operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Rekor CarCheck

Create your workspace
Sign up free. Nothing to install.
Connect Rekor CarCheck once
Add your Rekor CarCheck connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.