cubbi/README.md

MC - Monadical Container Tool

MC (Monadical Container) is a command-line tool for managing ephemeral containers that run AI tools and development environments. It works with both local Docker and a dedicated remote web service that manages containers in a Docker-in-Docker (DinD) environment. MC also supports connecting to MCP (Model Control Protocol) servers to extend AI tools with additional capabilities.

Requirements

• uv

Installation

# Clone the repository
git clone https://github.com/monadical/mcontainer.git

# Install the tool locally
# (with editable, so you can update the code and work with it)
cd mcontainer
uv tool install --with-editable . .

# Then you could use the tool as `mc`
mc --help

Basic Usage

# Create a new session with the default driver
# mc create session -- is the full command
mc

# List all active sessions
mc session list

# Connect to a specific session
mc session connect SESSION_ID

# Close a session when done
mc session close SESSION_ID

# Create a session with a specific driver
mc session create --driver goose

# Create a session with environment variables
mc session create -e VAR1=value1 -e VAR2=value2

# Mount custom volumes (similar to Docker's -v flag)
mc session create -v /local/path:/container/path
mc session create -v ~/data:/data -v ./configs:/etc/app/config

# Connect to external Docker networks
mc session create --network teamnet --network dbnet

# Connect to MCP servers for extended capabilities
mc session create --mcp github --mcp jira

# Shorthand for creating a session with a project repository
mc github.com/username/repo

# Shorthand with MCP servers
mc github.com/username/repo --mcp github

Driver Management

MC includes a driver management system that allows you to build, manage, and use Docker images for different AI tools:

# List available drivers
mc driver list

# Get detailed information about a driver
mc driver info goose

# Build a driver image
mc driver build goose

# Build and push a driver image
mc driver build goose --push

Drivers are defined in the mcontainer/drivers/ directory, with each subdirectory containing:

• Dockerfile: Docker image definition
• entrypoint.sh: Container entrypoint script
• mc-init.sh: Standardized initialization script
• mc-driver.yaml: Driver metadata and configuration
• README.md: Driver documentation

MC automatically discovers and loads driver definitions from the YAML files.

Development

# Run the tests
uv run -m pytest

# Run linting
uvx ruff check .

# Run type checking
uvx mypy .

# Format code
uvx ruff format .

Configuration

MC supports user-specific configuration via a YAML file located at ~/.config/mc/config.yaml. This allows you to set default values and configure service credentials.

Managing Configuration

# View all configuration
mc config list

# Get a specific configuration value
mc config get langfuse.url

# Set configuration values
mc config set langfuse.url "https://cloud.langfuse.com"
mc config set langfuse.public_key "pk-lf-..."
mc config set langfuse.secret_key "sk-lf-..."

# Set API keys for various services
mc config set openai.api_key "sk-..."
mc config set anthropic.api_key "sk-ant-..."

# Reset configuration to defaults
mc config reset

Default Networks Configuration

You can configure default networks that will be applied to every new session:

# List default networks
mc config network list

# Add a network to defaults
mc config network add teamnet

# Remove a network from defaults
mc config network remove teamnet

Default Volumes Configuration

You can configure default volumes that will be automatically mounted in every new session:

# List default volumes
mc config volume list

# Add a volume to defaults
mc config volume add /local/path:/container/path

# Remove a volume from defaults (will prompt if multiple matches found)
mc config volume remove /local/path

Default volumes will be combined with any volumes specified using the -v flag when creating a session.

External Network Connectivity

MC containers can connect to external Docker networks, allowing them to communicate with other services in those networks:

# Create a session connected to external networks
mc session create --network teamnet --network dbnet

Important: Networks must be "attachable" to be joined by MC containers. Here's how to create attachable networks:

# Create an attachable network with Docker
docker network create --driver bridge --attachable teamnet

# Example docker-compose.yml with attachable network
# docker-compose.yml
version: '3'
services:
  web:
    image: nginx
    networks:
      - teamnet

networks:
  teamnet:
    driver: bridge
    attachable: true  # This is required for MC containers to connect

Service Credentials

Service credentials like API keys configured in ~/.config/mc/config.yaml are automatically passed to containers as environment variables:

Config Setting	Environment Variable
langfuse.url	LANGFUSE_URL
langfuse.public_key	LANGFUSE_INIT_PROJECT_PUBLIC_KEY
langfuse.secret_key	LANGFUSE_INIT_PROJECT_SECRET_KEY
openai.api_key	OPENAI_API_KEY
anthropic.api_key	ANTHROPIC_API_KEY
openrouter.api_key	OPENROUTER_API_KEY

MCP Server Management

MCP (Model Control Protocol) servers provide tool-calling capabilities to AI models, enhancing their ability to interact with external services, databases, and systems. MC supports multiple types of MCP servers:

1. Remote HTTP SSE servers - External MCP servers accessed over HTTP
2. Docker-based MCP servers - Local MCP servers running in Docker containers
3. Proxy-based MCP servers - Local MCP servers with an SSE proxy for stdio-to-SSE conversion

Managing MCP Servers

# List all configured MCP servers and their status
mc mcp list

# View detailed status of an MCP server
mc mcp status github

# Start/stop/restart individual MCP servers
mc mcp start github
mc mcp stop github
mc mcp restart github

# Start all MCP servers at once
mc mcp start --all

# Stop and remove all MCP servers at once
mc mcp stop --all

# Run the MCP Inspector to visualize and interact with MCP servers
# It automatically joins all MCP networks for seamless DNS resolution
# Uses two ports: frontend UI (default: 5173) and backend API (default: 3000)
mc mcp inspector

# Run the MCP Inspector with custom ports
mc mcp inspector --client-port 6173 --server-port 6174

# Run the MCP Inspector in detached mode
mc mcp inspector --detach

# Stop the MCP Inspector
mc mcp inspector --stop

# View MCP server logs
mc mcp logs github

# Remove an MCP server configuration
mc mcp remove github

Adding MCP Servers

MC supports different types of MCP servers:

# Add a remote HTTP SSE MCP server
mc mcp remote add github http://my-mcp-server.example.com/sse --header "Authorization=Bearer token123"

# Add a Docker-based MCP server
mc mcp docker add github mcp/github:latest --command "github-mcp" --env GITHUB_TOKEN=ghp_123456

# Add a proxy-based MCP server (for stdio-to-SSE conversion)
mc mcp proxy add github ghcr.io/mcp/github:latest --proxy-image ghcr.io/sparfenyuk/mcp-proxy:latest --command "github-mcp" --sse-port 8080

Using MCP Servers with Sessions

MCP servers can be attached to sessions when they are created:

# Create a session with a single MCP server
mc session create --mcp github

# Create a session with multiple MCP servers
mc session create --mcp github --mcp jira

# Using MCP with a project repository
mc github.com/username/repo --mcp github

MCP servers are persistent and can be shared between sessions. They continue running even when sessions are closed, allowing for efficient reuse across multiple sessions.