Car Image API
Documentation

MCP & agents

Remote and local MCP, Claude Code, ChatGPT actions.

Remote MCP server

The hosted server speaks MCP over Streamable HTTP. Point any MCP host at it with your key in the Authorization header — nothing to install.

POST/api/mcp
Bearer keyper tool
mcp.json
{
  "mcpServers": {
    "car-image": {
      "url": "https://car-imgs.vercel.app/api/mcp",
      "headers": {
        "Authorization": "Bearer ${CAR_IMAGE_API_KEY}"
      }
    }
  }
}

Endpoint: https://car-imgs.vercel.app/api/mcp. Most hosts expand ${CAR_IMAGE_API_KEY} from your environment; if yours does not, keep the config file out of version control.

Tools

ToolCostDescription
get_car_image1 creditReturn an image (bytes as image content, or a signed URL) plus usage metadata for a make/model/year/view/color.
create_car_image_urls1 credit per URLMint up to 50 signed URLs with a TTL and optional use cap, for embedding in a page or document.
search_vehiclesfreeSearch the catalog for makes and models; returns available years so the agent can pick a valid one.
resolve_vehiclefreeTurn a natural-language phrase ("blue 2022 bmw m3 side profile") into exact request parameters.
list_image_optionsfreeValid views (with yaw degrees), preset colors, size presets and formats.
get_accountfreeCredit balance, auto-reload state and pricing — call it before large batches.
rate_imagefreeReport a good or bad render with a reason; feeds the quality loop.
describe_apifreeA compact description of endpoints, costs and rules for agents that were not given these docs.

Tool errors carry the same status, detail and request_id as the REST API, so the agent can follow the error reference.

Claude Code

One command adds the hosted server to Claude Code — nothing to install and nothing to keep up to date:

bash
claude mcp add --transport http car-image https://car-imgs.vercel.app/api/mcp --header "Authorization: Bearer $CAR_IMAGE_API_KEY"

Export CAR_IMAGE_API_KEY in the shell you start Claude Code from (or run npx @meterapp/car-image login to get a key), then ask for "a side view of a 2024 Porsche 911 in red". Run /mcp to confirm the eight tools above are connected.

For a project-scoped setup instead, commit the .mcp.json from the Remote (HTTP) tab above — npx @meterapp/car-image agent-config --host claude-code prints both forms.

ChatGPT actions

Create a custom GPT, add an action and import the OpenAPI document from https://car-imgs.vercel.app/openapi.json. Choose Bearer authentication and paste a key with images:read. The schema declares every endpoint, parameter and problem response, so the action works without editing.

Machine-readable docs

  • /llms.txt — a compact guide to the API and its rules.
  • /agents.md — setup and safety behavior for autonomous agents.
  • /openapi.json — OpenAPI 3.1 with typed schemas.
  • /errors.md — the error reference as Markdown.

Rules for autonomous agents