# DINO-X

> Use this tool when you need to enable AI agents with real-world visual perception capabilities, such as object detection, localization, and image captioning, to solve problems in applications like accessibility tools, security monitoring, and content moderation. The DINO-X API takes in images and text prompts as inputs and outputs annotated images with bounding boxes, labels, and detailed descriptions. It is particularly useful in contexts where visual understanding is crucial, such as sports analysis, automated content moderation, and AI applications requiring comprehensive scene analysis.

Canonical page: https://skillsregistry.net/skills/idea-research-dino-x  
JSON: https://api.skillsregistry.net/v1/skills/idea-research-dino-x

## Description

This DINO-X MCP server by IDEA Research provides AI agents with real-world visual perception capabilities through the DINO-X computer vision API, enabling object detection, localization, human pose estimation, and image captioning. The implementation offers three core detection modes: text-prompted object detection for finding specific items, universal object detection for comprehensive scene analysis, and human pose keypoint detection with 17-point skeletal tracking, all with optional detailed descriptions and visualization capabilities that save annotated images with bounding boxes and labels. Built with TypeScript and the canvas library for image processing, it integrates with DeepDataSpace's hosted DINO-X API and includes robust error handling, task polling for asynchronous processing, and flexible output formatting, making it valuable for AI applications requiring visual understanding, accessibility tools, security monitoring, sports analysis, and automated content moderation workflows.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-05-18

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/idea-research-dino-x)
- **Repository:** <https://github.com/idea-research/dino-x-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "idea-research-dino-x"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/idea-research-dino-x` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/idea-research-dino-x/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt