Skip to content
Back to search

DINO-X-MCP

Official DINO-X Model Context Protocol (MCP) server that empowers LLMs with real-world visual perception through image object detection, localization, and captioning APIs.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/idea-research--dino-x-mcp/badge.svg)](/listings/idea-research--dino-x-mcp)

HTML

<a href="/listings/idea-research--dino-x-mcp"><img src="/api/listings/idea-research--dino-x-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

1. Prepare an MCP client

Any MCP-compatible client works, e.g.:

- [Cursor](https://www.cursor.com/) - [WindSurf](https://windsurf.com/) - [Trae](https://www.trae.ai/) - [Cherry Studio](https://www.cherry-ai.com/)

2. Get your API key

Apply on the DINO-X platform: [Request API Key](https://cloud.deepdataspace.com/request_api) (new users get free quota).

3. Configure MCP

Option A: Official Hosted Streamable HTTP (Recommended)

Add to your MCP client config and replace with your API key:

{
  "mcpServers": {
    "dinox-mcp": {
      "url": "https://mcp.deepdataspace.com/mcp?key=your-api-key"
    }
  }
}

Option B: Use the NPM package locally (STDIO)

Install Node.js first

- Download the installer from [nodejs.org](https://nodejs.org/)

- Or use command:

# macOS / Linux
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
# or
wget -qO- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash

# load nvm into current shell (choose the one you use)
source ~/.bashrc || true
source ~/.zshrc  || true

# install and use LTS Node.js
nvm install --lts
nvm use --lts

# Windows (one of the following)
winget install OpenJS.NodeJS.LTS
# or with Chocolatey (in admin PowerShell)
iwr -useb https://raw.githubusercontent.com/chocolatey/chocolatey/master/chocolateyInstall/InstallChocolatey.ps1 | iex
choco install nodejs-lts -y

Configure your MCP client:

{
  "mcpServers": {
    "dinox-mcp": {
      "command": "npx",
      "args": ["-y", "@deepdataspace/dinox-mcp"],
      "env": {
        "DINOX_API_KEY": "your-api-key-here",
        "IMAGE_STORAGE_DIRECTORY": "/path/to/your/image/directory"
      }
    }
  }
}

Note: Replace `your-api-key-here` with your real key.

Option C: Run from source locally

Make sure Node.js is installed (see Option B), then:

# clone
git clone https://github.com/IDEA-Research/DINO-X-MCP.git
cd DINO-X-MCP

# install deps
npm install

# build
npm run build

Configure your MCP client:

{
  "mcpServers": {
    "dinox-mcp": {
      "command": "node",
      "args": ["/path/to/DINO-X-MCP/build/index.js"],
      "env": {
        "DINOX_API_KEY": "your-api-key-here",
        "IMAGE_STORAGE_DIRECTORY": "/path/to/your/image/directory"
      }
    }
  }
}

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 262 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # DINO-X MCP Server
  2. [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [![npm version](https://img.shields.io/npm/v/@deepdataspace/dinox-mcp.svg)](https://www.npmjs.com/package/@deepdataspace/dinox-mcp) [![npm downloads](https://img.shields.io/npm/dm/@deepdataspace/dinox-mcp.svg)](https://www.npmjs.com/package/@deepdataspace/dinox-mcp) [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/IDEA-Research/DINO-X-MCP/pulls) [![MCP Badge](https://lobehub.com/badge/mcp/idea-research-dino-x-mcp)](https://lobehub.com/mcp/idea-research-dino-x-mcp) [![GitHub stars](https://img.shields.io/github/stars/IDEA-Research/DINO-X-MCP.svg)](https://github.com/IDEA-Research/DINO-X-MCP/stargazers)
  3. **English** | [中文](README_ZH.md)
  4. DINO-X Official MCP Server — powered by the DINO-X and Grounding DINO models — brings fine-grained object detection and image understanding to your multimodal applications.
  5. <p align="center">
  6. <video width="800" controls>
  7. <source src="https://dds-frontend.oss-cn-shenzhen.aliyuncs.com/dinox-mcp/dinox-mcp-en-overveiw.mp4" type="video/mp4">
  8. Your browser does not support the video tag.
  9. </video>
  10. </p>
  11. ## Why DINO-X MCP?
  12. With DINO-X MCP, you can:
  13. - Fine-Grained Understanding: Full image detection, object detection, and region-level descriptions.
  14. - Structured Outputs: Get object categories, counts, locations, and attributes for VQA and multi-step reasoning tasks.
  15. - Composable: Works seamlessly with other MCP servers to build end-to-end visual agents or automation pipelines.
  16. ## Transport Modes
  17. DINO-X MCP supports two transport modes:
  18. | Feature | STDIO (default) | Streamable HTTP |
  19. |:--|:--|:--|
  20. | Runtime | Local | Local or Cloud |
  21. | Transport | Standard I/O | HTTP (streaming responses) |
  22. | Input source | `file://` and `https://` | `https://` only |
  23. | Visualization | Supported (saves annotated images locally) | Not supported (for now) |
  24. ## Quick Start
  25. ### 1. Prepare an MCP client
  26. Any MCP-compatible client works, e.g.:
  27. - [Cursor](https://www.cursor.com/)
  28. - [WindSurf](https://windsurf.com/)
  29. - [Trae](https://www.trae.ai/)
  30. - [Cherry Studio](https://www.cherry-ai.com/)
  31. ### 2. Get your API key
  32. Apply on the DINO-X platform: [Request API Key](https://cloud.deepdataspace.com/request_api) (new users get free quota).
  33. ### 3. Configure MCP
  34. #### Option A: Official Hosted Streamable HTTP (Recommended)
  35. Add to your MCP client config and replace with your API key:
  36. ```json
  37. {
  38. "mcpServers": {
  39. "dinox-mcp": {
  40. "url": "https://mcp.deepdataspace.com/mcp?key=your-api-key"
  41. }
  42. }
  43. }
  44. ```
  45. #### Option B: Use the NPM package locally (STDIO)
  46. Install Node.js first
  47. - Download the installer from [nodejs.org](https://nodejs.org/)
  48. - Or use command:
  49. ```bash
  50. # macOS / Linux
  51. curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
  52. # or
  53. wget -qO- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
  54. # load nvm into current shell (choose the one you use)
  55. source ~/.bashrc || true
  56. source ~/.zshrc || true
  57. # install and use LTS Node.js
  58. nvm install --lts
  59. nvm use --lts
  60. # Windows (one of the following)
  61. winget install OpenJS.NodeJS.LTS
  62. # or with Chocolatey (in admin PowerShell)
  63. iwr -useb https://raw.githubusercontent.com/chocolatey/chocolatey/master/chocolateyInstall/InstallChocolatey.ps1 | iex
  64. choco install nodejs-lts -y
  65. ```
  66. Configure your MCP client:
  67. ```json
  68. {
  69. "mcpServers": {
  70. "dinox-mcp": {
  71. "command": "npx",
  72. "args": ["-y", "@deepdataspace/dinox-mcp"],
  73. "env": {
  74. "DINOX_API_KEY": "your-api-key-here",
  75. "IMAGE_STORAGE_DIRECTORY": "/path/to/your/image/directory"
  76. }
  77. }
  78. }
  79. }
  80. ```
  81. Note: Replace `your-api-key-here` with your real key.
  82. #### Option C: Run from source locally
  83. Make sure Node.js is installed (see Option B), then:
  84. ```bash
  85. # clone
  86. git clone https://github.com/IDEA-Research/DINO-X-MCP.git
  87. cd DINO-X-MCP
  88. # install deps
  89. npm install
  90. # build
  91. npm run build
  92. ```
  93. Configure your MCP client:
  94. ```json
  95. {
  96. "mcpServers": {
  97. "dinox-mcp": {
  98. "command": "node",
  99. "args": ["/path/to/DINO-X-MCP/build/index.js"],
  100. "env": {
  101. "DINOX_API_KEY": "your-api-key-here",
  102. "IMAGE_STORAGE_DIRECTORY": "/path/to/your/image/directory"
  103. }
  104. }
  105. }
  106. }
  107. ```
  108. ## CLI Flags & Environment Variables
  109. - Common flags
  110. - `--http`: start in Streamable HTTP mode (otherwise STDIO by default)
  111. - `--stdio`: force STDIO mode
  112. - `--dinox-api-key=...`: set API key
  113. - `--enable-client-key`: allow API key via URL `?key=` (Streamable HTTP only)
  114. - `--port=8080`: HTTP port (default 3020)
  115. - Environment variables
  116. - `DINOX_API_KEY` (required/conditionally required): DINO-X platform API key
  117. - `IMAGE_STORAGE_DIRECTORY` (optional, STDIO): directory to save annotated images
  118. - `AUTH_TOKEN` (optional, HTTP): if set, client must send `Authorization: Bearer <token>`
  119. Examples:
  120. ```bash
  121. # STDIO (local)
  122. node build/index.js --dinox-api-key=your-api-key
  123. # Streamable HTTP (server provides a shared API key)
  124. node build/index.js --http --dinox-api-key=your-api-key
  125. # Streamable HTTP (custom port)
  126. node build/index.js --http --dinox-api-key=your-api-key --port=8080
  127. # Streamable HTTP (require client-provided API key via URL)
  128. node build/index.js --http --enable-client-key
  129. ```
  130. Client config when using `?key=`:
  131. ```json
  132. {
  133. "mcpServers": {
  134. "dinox-mcp": {
  135. "url": "http://localhost:3020/mcp?key=your-api-key"
  136. }
  137. }
  138. }
  139. ```
  140. Using `AUTH_TOKEN` with a gateway that injects `Authorization: Bearer <token>`:
  141. ```bash
  142. AUTH_TOKEN=my-token node build/index.js --http --enable-client-key
  143. ```
  144. Client example with `supergateway`:
  145. ```json
  146. {
  147. "mcpServers": {
  148. "dinox-mcp": {
  149. "command": "npx",
  150. "args": [
  151. "-y",
  152. "supergateway",
  153. "--streamableHttp",
  154. "http://localhost:3020/mcp?key=your-api-key",
  155. "--oauth2Bearer",
  156. "my-token"
  157. ]
  158. }
  159. }
  160. }
  161. ```
  162. ## Tools
  163. | Capability | Tool ID | Transport | Input | Output |
  164. |:--|:--|:--|:--|:--|
  165. | Full-scene object detection | `detect-all-objects` | STDIO / HTTP | Image URL | Category + bbox + (optional) captions |
  166. | Text-prompted object detection | `detect-objects-by-text` | STDIO / HTTP | Image URL + English nouns (dot-separated for multiple, e.g., `person.car`) | Target object bbox + (optional) captions |
  167. | Human pose estimation | `detect-human-pose-keypoints` | STDIO / HTTP | Image URL | 17 keypoints + bbox + (optional) captions |
  168. | Visualization | `visualize-detection-result` | STDIO only | Image URL + detection results array | Local path to annotated image |
  169. ## 🎬 Use Cases
  170. | 🎯 Scenario | 📝 Input | ✨ Output |
  171. |---------|---------|---------|
  172. | **Detection & Localization** | **💬 Prompt:**<br>`Detect and visualize the `<br>`fire areas in the forest `<br><br>**🖼️ Input Image:**<br>![1-1](https://github.com/user-attachments/assets/b5401c20-b7f2-4a8e-bc24-4eca54c48a92)| ![1-2](https://github.com/user-attachments/assets/8bc3c9fe-5a5a-4f10-af0a-552b797a00fc)|
  173. | **Object Counting** | **💬 Prompt:**<br>`Please analyze this`<br>`warehouse image, detect`<br>`all the cardboard boxes,`<br>`count the total number`<br><br>**🖼️ Input Image:**<br>![2-1](https://github.com/user-attachments/assets/9d500523-4094-43fe-a6e5-5a714075dfd8)| <img width="1276" alt="2-2" src="https://github.com/user-attachments/assets/3f18ef8c-5e89-45fc-bd0f-f23381304272" />|
  174. | **Feature Detection** | **💬 Prompt:**<br>`Find all red cars`<br>`in the image`<br><br>**🖼️ Input Image:**<br>![4-1](https://github.com/user-attachments/assets/3a5b0776-a932-447f-bc81-42c0536381e8)|![4-2](https://github.com/user-attachments/assets/410c2120-8c86-4f90-9ce1-c34fb3b1781a)|
  175. | **Attribute Reasoning** | **💬 Prompt:**<br>`Find the tallest person`<br>`in the image, describe`<br>`their clothing`<br><br>**🖼️ Input Image:**<br>![5-1](https://github.com/user-attachments/assets/9ba4b77e-6d00-4257-9bdb-079a53ce4ca4) | ![5-2](https://github.com/user-attachments/assets/ef0ce3e1-1dd2-4bd7-a145-e1623c297911) |
  176. | **Full Scene Detection** | **💬 Prompt:**<br>`Find the fruit with`<br>`the highest vitamin C`<br>`content in the image`<br><br>**🖼️ Input Image:**<br>![6-1](https://github.com/user-attachments/assets/9cf9f475-6015-47d0-917e-5004a104d777)| ![6-3](https://github.com/user-attachments/assets/17466bc2-4b9a-4a74-9456-05c253b0b388)<br><br>*Answer: Kiwi fruit (93mg/100g)* |
  177. | **Pose Analysis** | **💬 Prompt:**<br>`Please analyze what`<br>`yoga pose this is`<br><br>**🖼️ Input Image:**<br>![3-1](https://github.com/user-attachments/assets/2b2a6b5a-939b-4c37-8f40-900ae921b07a) |![3-3](https://github.com/user-attachments/assets/41636813-aaf7-4ad0-a5c3-1a5cbe67c022)|
  178. ## FAQ
  179. - Supported image sources?
  180. - STDIO: `file://` and `https://`
  181. - Streamable HTTP: `https://` only
  182. - Supported image formats?
  183. - jpg, jpeg, webp, png
  184. ## Development & Debugging
  185. Use watch mode to auto-rebuild during development:
  186. ```bash
  187. npm run watch
  188. ```
  189. Use MCP Inspector for debugging:
  190. ```bash
  191. npm run inspector
  192. ```
  193. ## License
  194. Apache License 2.0

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.