Moondream MCP server

Provide image analysis capabilities including captioning, object detection, and visual question answering for applications like content moderation and visual search.
Back to servers
Setup instructions
Provider
NightTrek
Release date
Dec 31, 2024
Language
TypeScript
Stats
16 stars

The Moondream MCP Server provides advanced image analysis capabilities for your applications using the Moondream vision model. It integrates with Claude and Cline, creating a bridge between AI assistants and sophisticated computer vision tasks like image captioning, object detection, and visual question answering.

Installation Requirements

Before installing the Moondream MCP Server, ensure you have:

  • Node.js v18 or higher
  • Python 3.8+
  • UV package manager (will be automatically installed if not present)

Installation Steps

  1. Clone the repository and set up the server:
git clone <repository-url>
cd moondream-server
pnpm install
  1. Build the server:
pnpm run build

The server will automatically:

  • Create a Python virtual environment
  • Install UV if not present
  • Download and set up the Moondream model
  • Manage the model server process

Integration with Claude or Cline

To integrate the server with Claude or Cline, add the following to your MCP settings file (claude_desktop_config.json or cline_mcp_settings.json):

{
  "mcpServers": {
    "moondream": {
      "command": "node",
      "args": ["/path/to/moondream-server/build/index.js"]
    }
  }
}

Using the Server

Available Tool: analyze_image

The server provides a powerful image analysis tool with multiple modes:

{
  "name": "analyze_image",
  "arguments": {
    "image_path": string,  // Path to image file
    "prompt": string       // Analysis command
  }
}

Prompt Types

You can use different types of prompts depending on your needs:

  • Image Captioning: Generate natural language descriptions of images
  • Object Detection: Identify and locate specific objects within images
  • Visual Question Answering: Ask questions about image content

Usage Examples

Image Captioning

{
  "image_path": "photo.jpg",
  "prompt": "generate caption"
}

Object Detection

{
  "image_path": "scene.jpg",
  "prompt": "detect: person"
}

Visual Q&A

{
  "image_path": "painting.jpg",
  "prompt": "What colors are used in this painting?"
}

Troubleshooting

Model Download Issues

If you experience issues downloading the model automatically, you can download it manually:

wget https://huggingface.co/vikhyatk/moondream2/resolve/main/moondream-0_5b-int4.mf.gz

Server Port Conflicts

The server uses port 3475 by default. To check if this port is in use:

lsof -i :3475

Python Environment Issues

The UV package manager handles dependencies in a virtual environment located in the system temp folder. Check the logs in the temp directory if you experience Python-related issues.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "moondream" '{"command":"node","args":["/path/to/moondream-server/build/index.js"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "moondream": {
            "command": "node",
            "args": [
                "/path/to/moondream-server/build/index.js"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "moondream": {
            "command": "node",
            "args": [
                "/path/to/moondream-server/build/index.js"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later