NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Plate Recognizer connects to a Nagent workspace with an API key. Once it is connected, agents can call 2 Plate Recognizer actions: "Read License Plate" and "Snapshot Get Statistics". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Plate Recognizer, with input parameters and output schema.
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
Agents can call 2 Plate Recognizer actions on Nagent: "Read License Plate" and "Snapshot Get Statistics". Read License Plate: Read license plates from images with confidence scores and optional vehicle details. Each action is listed on this page with its input parameters and its output.
Plate Recognizer connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
It also takes 8 optional inputs: mmc, config, upload, regions, camera_id, direction, timestamp and upload_url. It returns data, error and successful.