Plate Recognizer offers Automatic License Plate Recognition (ALPR) solutions for processing images and videos to detect and decode vehicle license plates.
Plate Recognizer offers Automatic License Plate Recognition (ALPR) solutions for processing images and videos to detect and decode vehicle license plates. On Nagent, Plate Recognizer is exposed as a fully-configurable artificial intelligence integration that any agent can call — 2 actions, and API key authentication. No code is required to wire Plate Recognizer into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Plate Recognizer to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Plate Recognizer into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Plate Recognizer, with input parameters and output schema. Drop these into any step of an agent built in Helix.
PLATERECOGNIZER_READ_LICENSE_PLATETool to read license plates from images with confidence scores and optional vehicle details. Use when you need to extract license plate text, region information, or analyze vehicle attributes from images.
Input parameters
Predict vehicle make, model, orientation, color, and year. Set to true if this feature is enabled on your account. Default is false.
Additional engine configuration as JSON. Options include detection_rule, detection_mode, region strict mode, thresholds, and mode (fast/redaction). See API documentation for detailed configuration options.
File to upload for license plate recognition. Can be a Optional if upload_url is provided.
Match license plate pattern of specific states/countries. Accepts multiple country/state codes. Examples: \['us-ca', 'gb', 'de'\]. See API documentation for full list of region codes.
Unique camera identifier for tracking purposes. Useful for identifying which camera captured the image.
Predict vehicle direction of travel in degrees. Requires mmc=true. Default is false.
ISO 8601 timestamp in UTC indicating when the image was captured. Example: 2019-08-19T13:11:25
URL of the image to analyze for license plate recognition. Alternative to upload parameter. Example: https://example.com/car-image.jpg
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PLATERECOGNIZER_SNAPSHOT_GET_STATISTICSTool to retrieve usage statistics for the current month's Snapshot API recognition calls. Use after making Snapshot API calls to monitor monthly usage.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 60 agents privately built on Nagent that already use Plate Recognizer.
Build on Nagent
Connect Plate Recognizer to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Plate Recognizer, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Plate Recognizer is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Plate Recognizer is connected, you configure its 2 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Plate Recognizer steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Plate Recognizer event fires, the agent kicks off automatically.
Every Plate Recognizer action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Plate Recognizer ships with 2 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Plate Recognizer together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Plate Recognizer-based workflows tailored to your business.