DINO-X-MCP

DINO-X-MCP is an MCP server. It reaches dinox. It needs AUTH_TOKEN and DINOX_API_KEY to authenticate. Its repository has 112 GitHub stars and is licensed under Apache-2.0; we last read it on 2026-10-22.

Serves image object detection, localization, and captioning APIs to empower LLMs with real-world visual perception.

MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. DINO-X-MCP’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.

4 tools documented in its README. An AI client calls these by name.

detect-all-objects

Full-scene object detection

detect-objects-by-text

Text-prompted object detection

detect-human-pose-keypoints

Human pose estimation

visualize-detection-result

Visualization

Read from the README; names are kept only if the README contains them.

What does DINO-X-MCP do?

Serves image object detection, localization, and captioning APIs to empower LLMs with real-world visual perception.

How do I install DINO-X-MCP?

Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/IDEA-Research/DINO-X-MCP

What does DINO-X-MCP connect to, and what does it need?

It reaches dinox. The credentials we found in its source are AUTH_TOKEN and DINOX_API_KEY.

Is DINO-X-MCP official and is it maintained?

We found nothing naming it as a vendor’s official server. Its repository has 112 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-06-17.

What licence does DINO-X-MCP use?

The repository declares the Apache-2.0 licence.

• Introduction to Model Context Protocol (Claude Academy)
• The Hugging Face MCP course
• Build an AI agent: a path with skills and MCP servers to practise on