@groundlight
MCP Server for Groundlight
Description
Create a detector based on the specified configuration. Supports three modes:
Input
`config` (DetectorConfig object with name, query, confidence_threshold, mode, and mode-specific configuration)
Returns
`Detector` object
Get a detector by its ID.
`detector_id` (string)
List all detectors associated with the current user.
None
List of `Detector` objects
Submit an image to be answered by the specified detector. The image can be provided as a file path, URL, or raw bytes. The detector will return a response with a label and confidence score.
`detector_id` (string), `image` (string or bytes)
`ImageQuery` object
Get an existing image query by its ID.
`image_query_id` (string)
List all image queries associated with the specified detector. Note that this may return a large number of results.
List of `ImageQuery` objects
Get the image associated with an image query by its ID. Optionally annotate with bounding boxes on the image if available.
`image_query_id` (string), `annotate` (boolean, default: false)
`Image` object
Create an alert for a detector that triggers actions when specific conditions are met.
`config` (AlertConfig object with name, detector_id, condition, and optional webhook_action, email_action, text_action, enabled, and human_review_required fields)
`Rule` object
List all alerts (rules) in the system. (Note: Not filtered by detector in the current implementation.)
`page` (integer, default: 1), `page_size` (integer, default: 100)
Update the escalation type for a detector. This determines when queries are sent for human review. Options: 'STANDARD' (escalate based on confidence threshold) or 'NO_HUMAN_LABELING' (never escalate).
punkpeye
modelcontextprotocol
amruthpillai