detect-all-objects
Analyze an image to detect all identifiable objects, returning the category, count, coordinate positions and detailed descriptions for each object.
LABSCO SUMMARY
Counting things in a photograph stops being a manual job.
A text prompt narrows detection to the object you care about, and the answer comes back with counts and 2D coordinates rather than a description of the scene. visualize-detection-result writes the boxed image to disk, which is what you hand to somebody who does not believe the number.
What it is
Object detection over an image URI in four tools: prompt-driven detection, full-scene detection, human pose keypoints, and a visualiser that draws boxes and labels onto the original image.
What you get
- Objects matching a text prompt identified and counted, with their 2D coordinates and, on request, descriptions
- Every identifiable object detected without a prompt, returning category, count, coordinates and descriptions
- 17 keypoints per person in an image, for body posture and movement analysis
- Detections drawn onto the original image with box thickness, font size and labels under your control, saved to the configured image directory
Requirements
A DINOX_API_KEY and an IMAGE_STORAGE_DIRECTORY for the annotated images to be written into, plus npx on your PATH.
Setup effort
One command plus a key — npx -y @deepdataspace/dinox-mcp, then supply credentials
USE CASES
01
Counting one kind of object across a batch of photographs
Name the object in a text prompt and read back the count and 2D coordinates, then draw the boxes onto the original image so the number can be checked by eye.
02
Cataloguing an image nobody has looked at yet
Detect everything identifiable without a prompt — category, count, position and description per object — when you do not yet know what you are looking for.
03
Analysing posture from a video frame
Get 17 keypoints per person for body posture and movement, then render them over the frame for a review that does not require reading coordinates.
4 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
detect-human-pose-keypoints
Detects 17 keypoints for each person in an image, supporting body posture and movement analysis.
detect-objects-by-text
Analyze an image based on a text prompt to identify and count specific objects, and return detailed descriptions of the objects and their 2D coordinates.
visualize-detection-result
Visualize detection results by drawing bounding boxes and labels on the original image. Images are saved to the directory specified by IMAGE_STORAGE_DIRECTORY environment variable.
BEFORE YOU INSTALL
What to know first
Tools you get
4 tools when we connected. visualize-detection-result works over STDIO only, so the official hosted endpoint can detect objects but not return the annotated image.
Requires
DINOX_API_KEY in your environment
Where it runs
Of the 5 documented clients, 1 runs the server on your machine and 4 connect to a hosted endpoint.
CONTEXT COST
Light Standing cost
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
npx
TERMINAL
npx -y @deepdataspace/dinox-mcpHosted endpoint
ENDPOINT URL
https://mcp.deepdataspace.com/mcp?key=<YOUR_API_KEY>Add this hosted endpoint to your MCP client using the credentials listed under Requirements.
MCP Clients
Cursor, Trae, Cherry Studio
JSON
{
"mcpServers": {
"dinox-mcp": {
"url": "https://mcp.deepdataspace.com/mcp?key=<YOUR_API_KEY>"
}
}
}Windsurf
WINDSURF · JSON
{
"mcpServers": {
"dinox-mcp": {
"serverUrl": "https://mcp.deepdataspace.com/mcp?key=<YOUR_API_KEY>"
}
}
}Any MCP client — npx
ANY MCP CLIENT — NPX · JSON
{
"mcpServers": {
"dinox-mcp": {
"command": "npx",
"args": [
"-y",
"@deepdataspace/dinox-mcp"
],
"env": {
"DINOX_API_KEY": "<YOUR_DINOX_API_KEY>",
"IMAGE_STORAGE_DIRECTORY": "<YOUR_IMAGE_STORAGE_DIRECTORY>"
}
}
}
}
