MCP servers to handle multimodal medical data

by Ketansuhaas

279 downloads Not rated yet
GitHub

About

Process and prepare your multimodal medical data with natural language!

Explore

- Provides an MCP server for EEG data analysis.
- Uses the MNE Python library for neuroimaging data processing.
- Integrates seamlessly with Claude Desktop via claude_desktop_config.json.
- Relies on the uv package manager for environment setup.
- Supports manual or automatic server startup.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP servers to handle multimodal medical data
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

- Python environment (Anaconda recommended)
- uv package manager installed in your Python environment.

This document provides instructions for setting up and configuring the EEG server.

image
image
image

To use this EEG server with Claude Desktop, you need to add its configuration to your claude_desktop_config.json file. This file is typically located in your user's application data directory.

1. Locate or create claude_desktop_config.json.

2. Add the following JSON configuration block:

    {
      "mcpServers": {
        "eeg-server": {
          "command": "C:\\Users\\{user}\\anaconda3\\envs\\mcp\\Scripts\\uv.exe",
          "args": [
            "--directory",
            "C:\\Users\\{path to folder}\\multimodal-medical-mcp-servers\\eeg-server",
            "run",
            "server.py"
          ]
        }
      }
    }
    

Important Placeholders:
Replace {user} with your Windows username (e.g., C:\Users\YourUserName\...).
Replace {path to folder} with the full path to the directory where you cloned or placed the multimodal-medical-mcp-servers repository (e.g., C:\Users\YourUserName\Documents\Projects).

Once configured in claude_desktop_config.json, Claude Desktop should be able to start the EEG server automatically when needed.

If you need to run the server manually for testing or development, you can execute the command specified in the configuration directly in your terminal (ensure you are in an environment where uv is available):

C:\Users\{user}\anaconda3\envs\mcp\Scripts\uv.exe --directory C:\Users\{path to folder}\multimodal-medical-mcp-servers\eeg-server run server.py
Make sure to replace the placeholders as described above.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp servers to handle multimodal medical data": {
            "multimodal-medical-mcp-servers": {
                "command": "uv",
                "args": [
                    "init"
                ]
            }
        }
    }
}

McpServers

{
    "multimodal-medical-mcp-servers": {
        "command": "uv",
        "args": [
            "init"
        ]
    }
}

(Example below)

EEG Server Setup Instructions

This document provides instructions for setting up and configuring the EEG server.

image
image
image

Prerequisites

- Python environment (Anaconda recommended)
- uv package manager installed in your Python environment.

Installation

1. Navigate to the server directory:
Open your terminal and change to the eeg-server directory:

    cd path/to/your/multimodal-medical-mcp-servers/eeg-server

Replace path/to/your/ with the actual path to the multimodal-medical-mcp-servers directory on your system.

2. Initialize the environment and install dependencies:
Use uv to set up the environment and install the required Python packages:

    uv init
uv add mcp[cli] mne

Configuration for Claude Desktop

To use this EEG server with Claude Desktop, you need to add its configuration to your claude_desktop_config.json file. This file is typically located in your user's application data directory.

1. Locate or create claude_desktop_config.json.

2. Add the following JSON configuration block:

    {
      "mcpServers": {
        "eeg-server": {
          "command": "C:\\Users\\{user}\\anaconda3\\envs\\mcp\\Scripts\\uv.exe",
          "args": [
            "--directory",
            "C:\\Users\\{path to folder}\\multimodal-medical-mcp-servers\\eeg-server",
            "run",
            "server.py"
          ]
        }
      }
    }
    

Important Placeholders:
Replace {user} with your Windows username (e.g., C:\Users\YourUserName\...).
Replace {path to folder} with the full path to the directory where you cloned or placed the multimodal-medical-mcp-servers repository (e.g., C:\Users\YourUserName\Documents\Projects).

Running the Server

Once configured in claude_desktop_config.json, Claude Desktop should be able to start the EEG server automatically when needed.

If you need to run the server manually for testing or development, you can execute the command specified in the configuration directly in your terminal (ensure you are in an environment where uv is available):

C:\Users\{user}\anaconda3\envs\mcp\Scripts\uv.exe --directory C:\Users\{path to folder}\multimodal-medical-mcp-servers\eeg-server run server.py
Make sure to replace the placeholders as described above.
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.