mcp-server-cvdlt
If you are the rightful owner of mcp-server-cvdlt and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Python server implementing Model Context Protocol (MCP) for image object detection, segmentation, and pose estimation operations.
The MCP Server for CVDLT (Computer Vision & Deep Learning Tools) is a Python-based server that leverages the Model Context Protocol (MCP) to perform advanced image processing tasks. Built on top of the Ultralytics framework, this server is capable of detecting objects, segmenting images, and estimating human poses using state-of-the-art models like YOLOv10 and YOLOv8. It supports both local and network image inputs, making it versatile for various applications. The server can operate in different modes, including stdio and SSE transport protocols, providing flexibility in how it communicates with clients. Users need to ensure that the necessary model files are available in the specified directory to enable these functionalities. The server is designed to be integrated with other platforms, such as Claude Desktop, to enhance its utility in different environments.
Features
- Detect objects in images using YOLOv10
- Segment objects in images using YOLOv8
- Segment entire images using Ultralytics SAM
- Estimate human poses in images using YOLOv8
- Support for local and network image inputs
Tools
detect_objects
Detect objects in an image using YOLOv10. Returns JSON array of detected objects with bounding boxes, confidence scores, and class labels.
segment_objects
Segment objects in an image using YOLOv8. Returns JSON array of segmented objects with bounding boxes, confidence scores, and class labels.
segment_image
Segment entire image using Ultralytics SAM. Returns JSON array of segmented regions with bounding boxes, areas, and confidence scores.
estimate_pose
Estimate human poses in an image using YOLOv8. Returns JSON array of detected poses with keypoint coordinates and confidence scores.
