groundlight-mcp-server
@groundlight
关于 groundlight-mcp-server
MCP Server for Groundlight
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"groundlight": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"GROUNDLIGHT_API_TOKEN",
"groundlight/groundlight-mcp-server"
],
"env": {
"GROUNDLIGHT_API_TOKEN": ""
}
}
}
}工具
27Create 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).
概览
What is groundlight-mcp-server?
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.
How to use groundlight-mcp-server?
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.
Key features of groundlight-mcp-server
- Create binary, multiclass, and counting detectors.
- Submit images for analysis with confidence scores.
- Manage alerts with webhook, email, or text actions.
- Label image queries to train or correct detectors.
- View detector evaluation metrics and confusion matrices.
- Update confidence thresholds and escalation types.
Use cases of groundlight-mcp-server
- Build a computer vision application to answer natural-language questions about images.
- Automate quality inspection with alerts triggered by detector conditions.
- Continuously improve detector accuracy through feedback and manual labeling.
- Monitor video streams or image feeds with human review escalation when confidence is low.
- Integrate visual understanding into AI assistants like Claude or Zed.
FAQ from groundlight-mcp-server
What tools does the groundlight-mcp-server provide?
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.
How do I configure the server with Claude Desktop?
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.
How can I provide labels for image queries?
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.
What authentication is required?
The server requires a GROUNDLIGHT_API_TOKEN environment variable, passed to the Docker container at runtime.
Are there any limitations with listing image queries?
The list_image_queries tool may return a large number of results depending on the detector’s history.
其他 分类下的更多 MCP 服务器
Core Philosophy: Connect, Unify, Respond
mindsdbDelegate anything. It comes back done.
Servers
modelcontextprotocolModel Context Protocol Servers
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
评论