Bioos MCP Server

🚀 Bio-OS MCP Server

A tool and prompt server based on the Model Context Protocol (MCP), specifically designed for Bio-OS, offering workflow management and Docker image building capabilities.

🚀 Quick Start

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

📦 Local Installation (Using MCP via Local VSCode)

Prerequisites

The 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 the MCP settings of CLINE. Replace the placeholders with the absolute installation paths:

{
  "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"
      }
    }
  }
} 

Follow the configuration process as shown below. When the status turns green, the Bio-OS MCP server is ready for use. If the connection is unstable, click "Retry Connection":

Since CLINE currently does not support MCP prompts, copy the contents of bioos-mcp-prompt.md to CLINE's custom instructions for the best experience:

After completing the configuration, you can start using the Bio-OS MCP server for development.

📦 Cloud Installation (Using via Miracle Cloud)

1. Log in to the Miracle Cloud platform.
2. Find the "Tool Services" section in the console.
3. Search for and select the "Bio-OS MCP Server".
4. Follow the instructions to create a new IES instance.
5. After the installation is complete, access the instance's console for further configuration.

✨ Features

• Workflow Management: Supports the definition and execution of workflows for complex bioinformatics tasks.
• Docker Image Building: Provides a convenient Docker image building tool to simplify the image creation process.
• API Support: Offers service invocation interfaces through RESTful APIs for easy integration into existing systems.

📚 Documentation

Tool List

1. wdl_development_workflow_prompt

   • Function: Generate a complete guide for WDL script development.
   • Content: Includes script development steps, task structure specifications, and runtime configuration requirements.

2. wdl_runtime_prompt

   • Function: Generate a WDL runtime configuration template.
   • Content: Covers Docker image configuration, memory settings (default 8 GB), disk space allocation (default 20 GB), and CPU settings (default 4 cores).

3. workflow_input_prompt

   • Function: Generate a guide for preparing workflow inputs.
   • Content: Includes steps for preparing input files, parameter validation specifications, and file path requirements.

4. workflow_submission_prompt

   • Function: Generate a workflow submission template.
   • Content: Involves required credentials (ak/sk), workspace configuration, and input file requirements.

5. docker_build_prompt

   • Function: Generate a guide for the Docker build process.
   • Content: Includes steps for generating a Dockerfile, build configuration requirements, image repository settings, and methods for monitoring the build status.

Prompt Content (Only Available for Direct Use via MCP Server or Claude Desktop)

Since the CLINE environment currently does not support the prompt function, the above prompts are only available when accessed directly through the MCP server.

🤝 Contributing

Issues and pull requests are welcome.

📄 License

MIT License