Official DINO-X Model Context Protocol (MCP) server that empowers LLMs with real-world visual perception through image object detection, localization, and captioning APIs.
{
"mcpServers": {
"dinox-mcp": {
"url": "https://mcp.deepdataspace.com/mcp?key=your-api-key"
}
}
}Official DINO-X Model Context Protocol (MCP) server that empowers LLMs with real-world visual perception through image object detection, localization, and captioning APIs.
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
Apache-2.0. View license →
Is it maintained?
Last commit 159 days ago. 116 stars.
Will it work with my client?
Transport: stdio, sse, http. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
Context cost
4 tools. ~400 tokens (0.2% of 200K).
This server supports HTTP transport. Be the first to test it — help the community know if it works.
detect-all-objectsFull-scene object detection - detects all objects in an image and returns their categories, bounding boxes, and optional captions
detect-objects-by-textText-prompted object detection - detects specific objects in an image based on text descriptions
detect-human-pose-keypointsHuman pose estimation - detects human poses and returns 17 keypoints, bounding boxes, and optional captions
visualize-detection-resultVisualization - creates annotated images with detection results overlaid (STDIO only)
This server is missing a description.If you've used it, help the community.
Add informationNo known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.