CONNECT APP

Build with Plate Recognizer

Automatic License Plate Recognition - High Accuracy ALPR.

Artificial Intelligence (AI)

API key

Visit Plate Recognizer ↗ Start building

MCP

Give your agent Plate Recognizer tools

Every Plate Recognizer action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's Plate Recognizer account for each tool call — you store no tokens.

Pipedream Connect

// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": "{project_id}",
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "platerecognizer",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// e.g. run Run Recognition:
const result = await mcp.callTool({
  name: "platerecognizer-run-recognition",
  arguments: {
    imageFileOrUrl: "Image Path or URL",
    regions: ["Regions"],
  },
})

# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
    "Authorization": f"Bearer {access_token}",
    "x-pd-project-id": "{project_id}",
    "x-pd-environment": "production",
    "x-pd-external-user-id": "{external_user_id}",  # any stable ID for this user in your system
    "x-pd-app-slug": "platerecognizer",
}

async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

        # e.g. run Run Recognition:
        result = await session.call_tool("platerecognizer-run-recognition", {
            "imageFileOrUrl": "Image Path or URL",
            "regions": ["Regions"],
        })

MCP guide →

API PROXY

Call the Plate Recognizer API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Plate Recognizer API with the connected user's credentials attached. You store no tokens and write no refresh logic.

Pipedream Connect

const resp = await pd.proxy.get({
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  accountId: "apn_xxxxxxx",
  url: "https://api.platerecognizer.com/v1/plate-reader/",
})

// Any allowed Plate Recognizer endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.

# The path segment is the target URL, URL-safe base64 encoded:
# https://api.platerecognizer.com/v1/plate-reader/

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkucGxhdGVyZWNvZ25pemVyLmNvbS92MS9wbGF0ZS1yZWFkZXIv?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"

API proxy guide →

SDK

Run Plate Recognizer actions from your backend

Connect a user's Plate Recognizer account once, then run Run Recognition on their behalf from your own code — TypeScript, Python, or plain HTTP.

Pipedream Connect

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "platerecognizer-run-recognition",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    platerecognizer: { authProvisionId: "apn_xxxxxxx" },
    imageFileOrUrl: "Image Path or URL",
    regions: ["Regions"],
  },
})

from pipedream import Pipedream

pd = Pipedream(
    client_id="{oauth_client_id}",
    client_secret="{oauth_client_secret}",
    project_id="{project_id}",
    project_environment="production",
)

result = pd.actions.run(
    id="platerecognizer-run-recognition",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "platerecognizer": {"authProvisionId": "apn_xxxxxxx"},
        "imageFileOrUrl": "Image Path or URL",
        "regions": ["Regions"],
    },
)

curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "platerecognizer-run-recognition",
    "configured_props": {
      "platerecognizer": { "authProvisionId": "apn_xxxxxxx" },
      "imageFileOrUrl": "Image Path or URL",
      "regions": ["Regions"]
    }
  }'