quads-mcp

grafuls/quads-mcp

3.2

If you are the rightful owner of quads-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

This document provides a comprehensive overview of the QUADS Model Context Protocol (MCP) server, detailing its installation, configuration, and usage.

Tools

  1. calculate

    Performs calculations based on input parameters.

  2. fetch_data

    Retrieves data from specified sources.

  3. long_task

    Executes long-running tasks asynchronously.

quads-mcp

A Model Context Protocol for QUADS

Overview

This is a Model Context Protocol (MCP) server that exposes tools, resources, and prompts for use with LLM applications like Claude. MCP servers let you extend AI applications with custom functionality, data sources, and templated interactions.

Installation

Option 1: Install from PyPI (Recommended)

# Install the latest version from PyPI
pip install quads-mcp

# Or using uvx for isolated installation
uvx install quads-mcp

# Run the server
quads-mcp

Option 2: Run directly via uvx

# Run the server
uvx quads-mcp

#### Claude Desktop Configuration (PyPI Installation)

```json
{
  "mcpServers": {
    "quads-mcp": {
      "command": "quads-mcp",
      "env": {
        "MCP_QUADS__BASE_URL": "https://your-quads-server.com/api/v3",
        "MCP_QUADS__USERNAME": "your-username",
        "MCP_QUADS__PASSWORD": "your-password",
        "MCP_QUADS__VERIFY_SSL": "false"
      }
    }
  }
}


#### Claude Desktop Configuration (via uvx)

```json
{
  "mcpServers": {
    "quads-mcp": {
      "command": "uvx",
      "args": [
        "--from", "quads-mcp", "quads-mcp"
      ],
      "env": {
        "MCP_QUADS__BASE_URL": "https://your-quads-server.com/api/v3",
        "MCP_QUADS__USERNAME": "your-username",
        "MCP_QUADS__PASSWORD": "your-password",
        "MCP_QUADS__VERIFY_SSL": "false"
      }
    }
  }
}

Option 2: Install from Source

Quick Start

Option 1: Run with uvx (Easiest)

The fastest way to run the server without any setup:

# Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh

# Run the server directly (from project directory)
uvx --from . quads-mcp

# Or run the module
uvx --from . python -m quads_mcp.server

Option 2: Setup with uv (Recommended)

# Set up the environment
make setup

# Check virtual environment status
make status

# Run the server (automatically uses virtual environment)
make run

# Run in development mode with MCP Inspector
make dev

# Install the server in Claude Desktop
make install

Note: You don't need to manually activate the virtual environment when using make commands - they automatically use the .venv environment!

If you encounter import errors, run make reinstall to refresh the package installation.

Option 3: Manual Setup

# Install uv if you don't have it
pip install uv

# Create a virtual environment
uv venv

# Activate the virtual environment
source .venv/bin/activate  # On Unix/MacOS
# or
.venv\Scripts\activate     # On Windows

# Install the package in development mode
uv pip install -e .

# Run in development mode
mcp dev quads_mcp.server

# Install in Claude Desktop
mcp install quads_mcp.server

uvx Configuration

When running with uvx, you can configure the server using environment variables or .env files:

# Option 1: Environment variables
MCP_QUADS__BASE_URL="https://your-quads-api.com/api/v3" \
MCP_QUADS__AUTH_TOKEN="your-token" \
uvx --from . quads-mcp

# Option 2: .env file (recommended)
cp .env.example .env
# Edit .env with your configuration
uvx --from . quads-mcp

# Option 3: Development mode
MCP_DEBUG=true uvx --from . quads-mcp
Installing as Global Tool
# Install globally with uvx
uvx install .

# Now run from anywhere
quads-mcp

# Uninstall when done
uvx uninstall quads-mcp

Containers

This project uses Podman for containerization. Podman is a daemonless container engine that's compatible with OCI containers and provides better security than traditional container engines.

Quick Start with Podman

# Build the container image
make container-build
# or
podman build -t quads-mcp .

# Run the container
make container-run
# or
podman run -p 8000:8000 quads-mcp

Podman Compose (Recommended)

For easier development and deployment, use Podman Compose:

# Run with Podman Compose
make compose-up
# or
podman-compose up -d

# View logs
make compose-logs
# or
podman-compose logs -f

# Stop the service
make compose-down
# or
podman-compose down

Development with Podman

For development with live code reloading:

# Run development profile
make compose-dev
# or
podman-compose --profile dev up -d quads-mcp-dev

# The development container mounts your code for live updates

Configuration with Podman

Option 1: Environment Variables
podman run -p 8000:8000 \
  -e MCP_QUADS__BASE_URL=https://your-quads-api.com/api/v3 \
  -e MCP_QUADS__AUTH_TOKEN=your-token \
  quads-mcp
Option 2: .env File
# Create .env file with your configuration
cp .env.example .env
# Edit .env with your values

# Run with .env file
podman run -p 8000:8000 \
  -v $(pwd)/.env:/app/.env:ro \
  quads-mcp
Option 3: Podman Compose with .env
# Edit podman-compose.yml to uncomment the .env volume mount
# Then run:
podman-compose up -d

Production Builds

Multi-stage Build (Recommended)

For smaller, optimized production images:

# Build with multi-stage Containerfile
make container-build-prod
# or
podman build -f Containerfile.multistage -t quads-mcp:production .

# Run production image
make container-run-prod
# or
podman run -p 8000:8000 quads-mcp:production
Ultra-Secure Build (Distroless)

For maximum security with minimal attack surface:

# Build with distroless base image
make container-build-distroless
# or
podman build -f Containerfile.distroless -t quads-mcp:distroless .

# Run distroless image
make container-run-distroless
# or
podman run -p 8000:8000 quads-mcp:distroless

Security Features

  • Alpine Linux Base: Minimal, security-focused distribution
  • Non-root User: Runs as unprivileged mcp user (UID/GID 1001)
  • Distroless Option: Ultra-minimal base with no shell or package manager
  • Security Updates: Automatically includes latest security patches
  • Minimal Attack Surface: Only includes necessary dependencies

Server Architecture

The server is organized into several components:

  • server.py: Main MCP server setup and configuration
  • config.py: Configuration management
  • tools/: Tool implementations (functions that LLMs can execute)
  • resources/: Resource implementations (data that LLMs can access)
  • prompts/: Prompt template implementations (reusable conversation templates)

MCP Features

This server implements all three MCP primitives:

  1. Tools: Functions that the LLM can call to perform actions

    • Example: calculate, fetch_data, long_task

  2. Resources: Data sources that provide context to the LLM

    • Example: static://example, dynamic://{parameter}, config://{section}

  3. Prompts: Reusable templates for LLM interactions

    • Example: simple_prompt, structured_prompt, data_analysis_prompt

Adding Your Own Components

Adding a New Tool

Create or modify files in the tools/ directory:

@mcp.tool()
def my_custom_tool(param1: str, param2: int = 42) -> str:
    """
    A custom tool that does something useful.
    
    Args:
        param1: Description of first parameter
        param2: Description of second parameter with default value
        
    Returns:
        Description of the return value
    """
    # Your implementation here
    return f"Result: {param1}, {param2}"

Adding a New Resource

Create or modify files in the resources/ directory:

@mcp.resource("my-custom-resource://{param}")
def my_custom_resource(param: str) -> str:
    """
    A custom resource that provides useful data.
    
    Args:
        param: Description of the parameter
        
    Returns:
        The resource content
    """
    # Your implementation here
    return f"Resource content for: {param}"

Adding a New Prompt

Create or modify files in the prompts/ directory:

@mcp.prompt()
def my_custom_prompt(param: str) -> str:
    """
    A custom prompt template.
    
    Args:
        param: Description of the parameter
        
    Returns:
        The formatted prompt
    """
    return f"""
    # Custom Prompt Template
    
    Context: {param}
    
    Please respond with your analysis of the above context.
    """

Configuration

The server supports configuration via:

  1. Environment Variables: Prefix with MCP_ (e.g., MCP_QUADS__BASE_URL=https://quads.example.com)

    • Nested config: Use double underscores (MCP_QUADS__USERNAME=myuser)

  2. Config File: Specify via MCP_CONFIG_FILE environment variable

  3. .env File: Place a .env file in the project directory

QUADS Configuration

# Required: QUADS API URL
MCP_QUADS__BASE_URL=https://your-quads-server.com/api/v3

# Authentication (use either username/password OR token)
MCP_QUADS__USERNAME=your-username
MCP_QUADS__PASSWORD=your-password
# OR
MCP_QUADS__AUTH_TOKEN=your-auth-token

# Optional settings
MCP_QUADS__TIMEOUT=30
MCP_QUADS__VERIFY_SSL=true  # Set to false for self-signed certificates

SSL Certificates

For QUADS servers with self-signed certificates, set:

MCP_QUADS__VERIFY_SSL=false

⚠️ Security Note: Only disable SSL verification for trusted internal servers. See for details.

JSON Configuration Example

{
  "quads": {
    "base_url": "https://quads.example.com/api/v3",
    "username": "your-username",
    "password": "your-password",
    "timeout": 30,
    "verify_ssl": false
  }
}

Development

# Run tests
make test

# Format code
make format

# Type checking
make type-check

# Clean up build artifacts
make clean

License

[Include your license information here]