@groundlight
Basic information
MCP Server for Groundlight
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"groundlight": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"GROUNDLIGHT_API_TOKEN",
"groundlight/groundlight-mcp-server"
],
"env": {
"GROUNDLIGHT_API_TOKEN": ""
}
}
}
}Create a detector based on the specified configuration. Supports three modes:
`config` (DetectorConfig object with name, query, confidence_threshold, mode, and mode-specific configuration)
`Detector` object
Get a detector by its ID.
`detector_id` (string)
`Detector` object
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)
`ImageQuery` object
List all image queries associated with the specified detector. Note that this may return a large number of results.
`detector_id` (string)
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).
The groundlight-mcp-server is a Model Context Protocol server for interacting with Groundlight. It provides tools to create, list, and customize Detectors, submit and list ImageQueries, create, list, and delete Alerts, and examine detector evaluation metrics. It is designed for developers building computer vision applications that can be driven by natural-language queries.
Configure it by setting the GROUNDLIGHT_API_TOKEN environment variable and running the server via Docker. Add the supplied configuration block to your claude_desktop_config.json (for Claude Desktop) or settings.json (for Zed). Then invoke MCP tools such as create_detector, submit_image_query, list_alerts, and get_detector_evaluation_metrics.
The server offers 14 tools: create_detector, get_detector, list_detectors, submit_image_query, get_image_query, list_image_queries, get_image, create_alert, list_alerts, delete_alert, add_label, get_detector_evaluation_metrics, update_detector_confidence_threshold, and update_detector_escalation_type.
Add a `"groundlight"` entry under `mcpServers` in your `claude_desktop_config.json` using the provided Docker command and set the `GROUNDLIGHT_API_TOKEN` environment variable to your API token.
Use the `add_label` tool with an `image_query_id` and a label (integer or string). For counting detectors you can optionally specify regions of interest.
The server requires a `GROUNDLIGHT_API_TOKEN` environment variable, passed to the Docker container at runtime.
The `list_image_queries` tool may return a large number of results depending on the detector’s history.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Hindsight: Agent Memory That Learns
A curated list of references for MLOps
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Comments