DINO-X
** - Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
What is DINO-X?
DINO-X is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ** - advanced computer vision and object detection mcp server powered by dino-x, enabling ai agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
** - Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ** - Advanced computer vision and object detection MCP serve
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx dino-x-image-detection-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use DINO-X
DINO-X MCP Server brings advanced computer vision capabilities to AI assistants by connecting them to the DINO-X object detection platform from IDEA Research. It exposes tools for full-image object detection, text-prompted targeted detection, and human pose keypoint estimation, allowing AI agents to analyze images, identify objects with bounding boxes, describe visual content, and understand body poses. Researchers, developers, and AI applications that need vision analysis as a natural language capability will find it invaluable.
Prerequisites
- A DINO-X API key obtained by requesting access at https://cloud.deepdataspace.com/request_api
- Node.js 16 or higher and npm if running locally
- An MCP-compatible client such as Claude Desktop
- Optionally: a local directory path for saving annotated output images (stdio mode only)
Request a DINO-X API key
Visit https://cloud.deepdataspace.com/request_api and apply for API access to the DINO-X platform. The API key will be emailed to you after approval.
Option A: Use the hosted MCP endpoint (simplest)
No installation needed. Configure your MCP client to connect directly to the hosted DINO-X MCP endpoint, passing your API key as a URL parameter.
{
"mcpServers": {
"dinox-mcp": {
"url": "https://mcp.deepdataspace.com/mcp?key=YOUR-API-KEY"
}
}
}Option B: Run locally via npx
Install and run the DINO-X MCP Server locally using npx. Set your API key and an optional directory for saving annotated images.
{
"mcpServers": {
"dinox-mcp": {
"command": "npx",
"args": ["-y", "@deepdataspace/dinox-mcp"],
"env": {
"DINOX_API_KEY": "YOUR-API-KEY",
"IMAGE_STORAGE_DIRECTORY": "/path/to/save/images"
}
}
}
}Option C: Build from source
Clone the repository and build the package manually if you need to modify the server.
git clone https://github.com/IDEA-Research/DINO-X-MCP.git
cd DINO-X-MCP
npm install
npm run buildTest image detection
Provide an image URL or local file path (file:// prefix for local files in stdio mode) to the AI assistant and ask it to detect objects.
DINO-X Examples
Client configuration (local stdio)
Claude Desktop configuration running the DINO-X MCP Server locally via npx with API key and image storage directory.
{
"mcpServers": {
"dinox-mcp": {
"command": "npx",
"args": ["-y", "@deepdataspace/dinox-mcp"],
"env": {
"DINOX_API_KEY": "YOUR-API-KEY",
"IMAGE_STORAGE_DIRECTORY": "/tmp/dinox-output"
}
}
}
}Prompts to try
Example prompts that exercise the four tools: detect-all-objects, detect-objects-by-text, detect-human-pose-keypoints, and visualize-detection-result.
- "Detect all objects in this image: https://example.com/photo.jpg"
- "Find all cars and traffic signs in this image: https://example.com/street.jpg"
- "Detect the pose keypoints for all people in this image: file:///tmp/group_photo.jpg"
- "Visualize the detection results for the last analysis and save the annotated image"
- "What objects are in the foreground of this image? https://example.com/scene.png"Troubleshooting DINO-X
API returns 401 Unauthorized
Verify your DINOX_API_KEY is correct and active. For the hosted endpoint, ensure the key is appended as '?key=YOUR-API-KEY' in the URL. For local mode, confirm the DINOX_API_KEY environment variable is set in your MCP client config, not just in your shell.
Local file images fail with 'unsupported URL scheme'
Local file paths using 'file://' URLs are only supported in stdio (local) mode. The hosted HTTP endpoint only accepts 'https://' URLs. Switch to local npx mode if you need to analyze files on your filesystem.
Annotated images are not saved after detection
The visualize-detection-result tool requires IMAGE_STORAGE_DIRECTORY to be set to a writable absolute path. Ensure the directory exists ('mkdir -p /path/to/save/images') and that the process has write permission. This tool is only available in stdio mode, not the hosted HTTP mode.
Frequently Asked Questions about DINO-X
What is DINO-X?
DINO-X is a Model Context Protocol (MCP) server that ** - advanced computer vision and object detection mcp server powered by dino-x, enabling ai agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install DINO-X?
Follow the installation instructions on the DINO-X GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with DINO-X?
DINO-X works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is DINO-X free to use?
Yes, DINO-X is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
DINO-X Alternatives — Similar Data Science & ML Servers
Looking for alternatives to DINO-X? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up DINO-X in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use DINO-X?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.