Bio-OS MCP Server

A Model Context Protocol (MCP) based tool and prompt server for Bio-OS that provides workflow management and Docker image building capabilities.

Usage

We recommend using the CLINE extension for VSCode to interact with this MCP tool. There are two deployment options available: standalone installation on your local machine or using Code Server in a Miracle Cloud IES instance. Choose the option that best suits your needs.

Local Installation (Using MCP through local VSCode)

Prerequisites

Bio-OS MCP Server requires the following dependencies:

1. Install uv (Python package manager):

pip install uv

2. Install Cromwell (Workflow execution engine):

brew install cromwell

Installation

Clone the Bio-OS MCP Server repository:

git clone https://github.com/GBA-BI/bioos-mcp-server.git

Configuration

Configure the Bio-OS MCP Server script path in CLINE’s MCP settings. Replace the placeholders with absolute paths to your installation:

{
  "mcpServers": {
    "bioos": {
      "command": "path/to/uv",
      "args": [
        "--directory",
        "path/to/bioos-mcp-server",
        "run",
        "path/to/bioos-mcp-server/src/bioos_mcp/bioos_mcp_server.py"
      ],
      "env": {
        "PYTHONPATH": "path/to/bioos-mcp-server/src",
        "MIRACLE_ACCESS_KEY": "xxxxxxxxxxxx",
        "MIRACLE_SECRET_KEY": "xxxxxxxxxxxx"
      }
    }
  }
} 

Follow the configuration process shown below. The Bio-OS MCP Server is ready to use when the status turns green. If the connection is unstable, click “Retry Connection”:

Since CLINE does not yet support MCP Prompts, copy the contents of bioos-mcp-prompt.md into CLINE’s Custom Instructions for optimal experience:

After completing the configuration, you can begin using the Bio-OS MCP Server for development.

Cloud Installation (Using MCP through Code Server in Miracle Cloud)

For Miracle Cloud users, we provide a pre-configured Docker image with all Bio-OS MCP Server dependencies. Follow these steps:

1. Launch an IES instance using the image: registry-vpc.miracle.ac.cn/infcprelease/iespro:250217
2. Select “Open with VSCode” to access the development environment:

Configuration in Code Server

1. Click the CLINE icon in the left sidebar and configure your LLM model credentials:

2. Navigate to CLINE’s MCP configuration page and verify that Bio-OS MCP Server is properly connected. Use “Retry Connection” if needed:

Once configured, you can begin development with Bio-OS MCP Server.

Features

1. Workflow Management

• Submit and monitor workflows
• Upload WDL workflows
• Validate WDL scripts
• Generate input file templates

2. Docker Image Management

• Build Docker images
• Check build status
• Monitor build progress
• Retrieve build logs