For CVDLT(Computer Vision & Deep Learning Tools) MCP Server

The repo is based on Model Context procotol of Python SDK, including DL models in CV, and provide the abilities to the LLM or vLLM model

Local serverstdioPython

What is the For CVDLT(Computer Vision & Deep Learning Tools) MCP Server?

The repo is based on Model Context procotol of Python SDK, including DL models in CV, and provide the abilities to the LLM or vLLM model

What you get

  • 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
  • MCP tool integration for client interactions

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
detect_objectsDetect objects in an image using YOLOv10
segment_objectsSegment objects in an image using YOLOv8
segment_imageSegment entire image using Ultralytics SAM
estimate_poseEstimate human poses in an image using YOLOv8

How to install the For CVDLT(Computer Vision & Deep Learning Tools) MCP Server

{
  "mcpServers": {
    "server-with-yolo": {
      "url": "http://localhost:8080/sse"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • “Use For CVDLT(Computer Vision & Deep Learning Tools) to detect objects.”
  • “Use For CVDLT(Computer Vision & Deep Learning Tools) to Input.”
  • “Use For CVDLT(Computer Vision & Deep Learning Tools) to segment objects.”

Frequently asked questions

The server requires `yolov10b.pt`, `yolov8n-seg.pt`, `yolov8n-pose.pt`, and `sam_b.pt` placed in the `./checkpoints` directory.