feat(mcp): PR1 - Add MCP service scaffold for Apache Superset

.devcontainer/README.md

@@ -3,14 +3,3 @@
 For complete documentation on using GitHub Codespaces with Apache Superset, please see:
 
 **[Setting up a Development Environment - GitHub Codespaces](https://superset.apache.org/docs/contributing/development#github-codespaces-cloud-development)**
-
-## Pre-installed Development Environment
-
-When you create a new Codespace from this repository, it automatically:
-
-1. **Creates a Python virtual environment** using `uv venv`
-2. **Installs all development dependencies** via `uv pip install -r requirements/development.txt`
-3. **Sets up pre-commit hooks** with `pre-commit install`
-4. **Activates the virtual environment** automatically in all terminals
-
-The virtual environment is located at `/workspaces/{repository-name}/.venv` and is automatically activated through environment variables set in the devcontainer configuration.

.devcontainer/default/devcontainer.json

@@ -0,0 +1,19 @@
+{
+  // Extend the base configuration
+  "extends": "../devcontainer-base.json",
+
+  "name": "Apache Superset Development (Default)",
+
+  // Forward ports for development
+  "forwardPorts": [9001],
+  "portsAttributes": {
+    "9001": {
+      "label": "Superset (via Webpack Dev Server)",
+      "onAutoForward": "notify",
+      "visibility": "public"
+    }
+  },
+
+  // Auto-start Superset on Codespace resume
+  "postStartCommand": ".devcontainer/start-superset.sh"
+}

.devcontainer/devcontainer-base.json

@@ -0,0 +1,39 @@
+{
+  "name": "Apache Superset Development",
+  // Keep this in sync with the base image in Dockerfile (ARG PY_VER)
+  // Using the same base as Dockerfile, but non-slim for dev tools
+  "image": "python:3.11.13-bookworm",
+
+  "features": {
+    "ghcr.io/devcontainers/features/docker-in-docker:2": {
+      "moby": true,
+      "dockerDashComposeVersion": "v2"
+    },
+    "ghcr.io/devcontainers/features/node:1": {
+      "version": "20"
+    },
+    "ghcr.io/devcontainers/features/git:1": {},
+    "ghcr.io/devcontainers/features/common-utils:2": {
+      "configureZshAsDefaultShell": true
+    },
+    "ghcr.io/devcontainers/features/sshd:1": {
+      "version": "latest"
+    }
+  },
+
+  // Run commands after container is created
+  "postCreateCommand": "chmod +x .devcontainer/setup-dev.sh && .devcontainer/setup-dev.sh",
+
+  // VS Code customizations
+  "customizations": {
+    "vscode": {
+      "extensions": [
+        "ms-python.python",
+        "ms-python.vscode-pylance",
+        "charliermarsh.ruff",
+        "dbaeumer.vscode-eslint",
+        "esbenp.prettier-vscode"
+      ]
+    }
+  }
+}

.devcontainer/setup-dev.sh

@@ -3,76 +3,30 @@
 
 echo "🔧 Setting up Superset development environment..."
 
-# System dependencies and uv are now pre-installed in the Docker image
-# This speeds up Codespace creation significantly!
-
-# Create virtual environment using uv
-echo "🐍 Creating Python virtual environment..."
-if ! uv venv; then
-    echo "❌ Failed to create virtual environment"
-    exit 1
-fi
-
-# Install Python dependencies
-echo "📦 Installing Python dependencies..."
-if ! uv pip install -r requirements/development.txt; then
-    echo "❌ Failed to install Python dependencies"
-    echo "💡 You may need to run this manually after the Codespace starts"
-    exit 1
-fi
-
-# Install pre-commit hooks
-echo "🪝 Installing pre-commit hooks..."
-if source .venv/bin/activate && pre-commit install; then
-    echo "✅ Pre-commit hooks installed"
-else
-    echo "⚠️  Pre-commit hooks installation failed (non-critical)"
-fi
+# The universal image has most tools, just need Superset-specific libs
+echo "📦 Installing Superset-specific dependencies..."
+sudo apt-get update
+sudo apt-get install -y \
+    libsasl2-dev \
+    libldap2-dev \
+    libpq-dev \
+    tmux \
+    gh
+
+# Install uv for fast Python package management
+echo "📦 Installing uv..."
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Add cargo/bin to PATH for uv
+echo 'export PATH="$HOME/.cargo/bin:$PATH"' >> ~/.bashrc
+echo 'export PATH="$HOME/.cargo/bin:$PATH"' >> ~/.zshrc
 
 # Install Claude Code CLI via npm
 echo "🤖 Installing Claude Code..."
-if npm install -g @anthropic-ai/claude-code; then
-    echo "✅ Claude Code installed"
-else
-    echo "⚠️  Claude Code installation failed (non-critical)"
-fi
+npm install -g @anthropic-ai/claude-code
 
 # Make the start script executable
 chmod +x .devcontainer/start-superset.sh
 
-# Add bashrc additions for automatic venv activation
-echo "🔧 Setting up automatic environment activation..."
-if [ -f ~/.bashrc ]; then
-    # Check if we've already added our additions
-    if ! grep -q "Superset Codespaces environment setup" ~/.bashrc; then
-        echo "" >> ~/.bashrc
-        cat .devcontainer/bashrc-additions >> ~/.bashrc
-        echo "✅ Added automatic venv activation to ~/.bashrc"
-    else
-        echo "✅ Bashrc additions already present"
-    fi
-else
-    # Create bashrc if it doesn't exist
-    cat .devcontainer/bashrc-additions > ~/.bashrc
-    echo "✅ Created ~/.bashrc with automatic venv activation"
-fi
-
-# Also add to zshrc since that's the default shell
-if [ -f ~/.zshrc ] || [ -n "$ZSH_VERSION" ]; then
-    if ! grep -q "Superset Codespaces environment setup" ~/.zshrc; then
-        echo "" >> ~/.zshrc
-        cat .devcontainer/bashrc-additions >> ~/.zshrc
-        echo "✅ Added automatic venv activation to ~/.zshrc"
-    fi
-fi
-
 echo "✅ Development environment setup complete!"
-echo ""
-echo "📝 The virtual environment will be automatically activated in new terminals"
-echo ""
-echo "🔄 To activate in this terminal, run:"
-echo "   source ~/.bashrc"
-echo ""
-echo "🚀 To start Superset:"
-echo "   start-superset"
-echo ""
+echo "🚀 Run '.devcontainer/start-superset.sh' to start Superset"

.devcontainer/start-superset.sh

@@ -1,14 +1,14 @@
 #!/bin/bash
 # Startup script for Superset in Codespaces
 
-# Log to a file for debugging
-LOG_FILE="/tmp/superset-startup.log"
-echo "[$(date)] Starting Superset startup script" >> "$LOG_FILE"
-echo "[$(date)] User: $(whoami), PWD: $(pwd)" >> "$LOG_FILE"
-
 echo "🚀 Starting Superset in Codespaces..."
 echo "🌐 Frontend will be available at port 9001"
 
+# Check if MCP is enabled
+if [ "$ENABLE_MCP" = "true" ]; then
+    echo "🤖 MCP Service will be available at port 5008"
+fi
+
 # Find the workspace directory (Codespaces clones as 'superset', not 'superset-2')
 WORKSPACE_DIR=$(find /workspaces -maxdepth 1 -name "superset*" -type d | head -1)
 if [ -n "$WORKSPACE_DIR" ]; then
@@ -18,71 +18,32 @@ else
     echo "📁 Using current directory: $(pwd)"
 fi
 
-# Wait for Docker to be available
-echo "⏳ Waiting for Docker to start..."
-echo "[$(date)] Waiting for Docker..." >> "$LOG_FILE"
-max_attempts=30
-attempt=0
-while ! docker info > /dev/null 2>&1; do
-    if [ $attempt -eq $max_attempts ]; then
-        echo "❌ Docker failed to start after $max_attempts attempts"
-        echo "[$(date)] Docker failed to start after $max_attempts attempts" >> "$LOG_FILE"
-        echo "🔄 Please restart the Codespace or run this script manually later"
-        exit 1
-    fi
-    echo "   Attempt $((attempt + 1))/$max_attempts..."
-    echo "[$(date)] Docker check attempt $((attempt + 1))/$max_attempts" >> "$LOG_FILE"
-    sleep 2
-    attempt=$((attempt + 1))
-done
-echo "✅ Docker is ready!"
-echo "[$(date)] Docker is ready" >> "$LOG_FILE"
-
-# Check if Superset containers are already running
-if docker ps | grep -q "superset"; then
-    echo "✅ Superset containers are already running!"
-    echo ""
-    echo "🌐 To access Superset:"
-    echo "   1. Click the 'Ports' tab at the bottom of VS Code"
-    echo "   2. Find port 9001 and click the globe icon to open"
-    echo "   3. Wait 10-20 minutes for initial startup"
-    echo ""
-    echo "📝 Login credentials: admin/admin"
-    exit 0
+# Check if docker is running
+if ! docker info > /dev/null 2>&1; then
+    echo "⏳ Waiting for Docker to start..."
+    sleep 5
 fi
 
 # Clean up any existing containers
 echo "🧹 Cleaning up existing containers..."
-docker-compose -f docker-compose-light.yml down
+docker-compose -f docker-compose-light.yml --profile mcp down
 
 # Start services
-echo "🏗️  Starting Superset in background (daemon mode)..."
+echo "🏗️  Building and starting services..."
 echo ""
-
-# Start in detached mode
-docker-compose -f docker-compose-light.yml up -d
-
-echo ""
-echo "✅ Docker Compose started successfully!"
-echo ""
-echo "📋 Important information:"
-echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-echo "⏱️  Initial startup takes 10-20 minutes"
-echo "🌐 Check the 'Ports' tab for your Superset URL (port 9001)"
-echo "👤 Login: admin / admin"
+echo "📝 Once started, login with:"
+echo "   Username: admin"
+echo "   Password: admin"
 echo ""
-echo "📊 Useful commands:"
-echo "   docker-compose -f docker-compose-light.yml logs -f    # Follow logs"
-echo "   docker-compose -f docker-compose-light.yml ps         # Check status"
-echo "   docker-compose -f docker-compose-light.yml down       # Stop services"
-echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-echo ""
-echo "💤 Keeping terminal open for 60 seconds to test persistence..."
-sleep 60
-echo "✅ Test complete - check if this terminal is still visible!"
+echo "📋 Running in foreground with live logs (Ctrl+C to stop)..."
 
-# Show final status
-docker-compose -f docker-compose-light.yml ps
+# Run docker-compose and capture exit code
+if [ "$ENABLE_MCP" = "true" ]; then
+    echo "🤖 Starting with MCP Service enabled..."
+    docker-compose -f docker-compose-light.yml --profile mcp up
+else
+    docker-compose -f docker-compose-light.yml up
+fi
 EXIT_CODE=$?
 
 # If it failed, provide helpful instructions

.devcontainer/with-mcp/devcontainer.json

@@ -0,0 +1,29 @@
+{
+  // Extend the base configuration
+  "extends": "../devcontainer-base.json",
+
+  "name": "Apache Superset Development with MCP",
+
+  // Forward ports for development
+  "forwardPorts": [9001, 5008],
+  "portsAttributes": {
+    "9001": {
+      "label": "Superset (via Webpack Dev Server)",
+      "onAutoForward": "notify",
+      "visibility": "public"
+    },
+    "5008": {
+      "label": "MCP Service (Model Context Protocol)",
+      "onAutoForward": "notify",
+      "visibility": "private"
+    }
+  },
+
+  // Auto-start Superset with MCP on Codespace resume
+  "postStartCommand": "ENABLE_MCP=true .devcontainer/start-superset.sh",
+
+  // Environment variables
+  "containerEnv": {
+    "ENABLE_MCP": "true"
+  }
+}

docker/docker-bootstrap.sh

@@ -86,6 +86,10 @@ case "${1}" in
     echo "Starting web app..."
     /usr/bin/run-server.sh
     ;;
+  mcp)
+    echo "Starting MCP service..."
+    superset mcp run --host 0.0.0.0 --port ${MCP_PORT:-5008} --debug
+    ;;
   *)
     echo "Unknown Operation!!!"
     ;;

pyproject.toml

@@ -139,6 +139,7 @@ solr = ["sqlalchemy-solr >= 0.2.0"]
 elasticsearch = ["elasticsearch-dbapi>=0.2.9, <0.3.0"]
 exasol = ["sqlalchemy-exasol >= 2.4.0, <3.0"]
 excel = ["xlrd>=1.2.0, <1.3"]
+fastmcp = ["fastmcp>=2.10.6"]
 firebird = ["sqlalchemy-firebird>=0.7.0, <0.8"]
 firebolt = ["firebolt-sqlalchemy>=1.0.0, <2"]
 gevent = ["gevent>=23.9.1"]

requirements/base.txt

@@ -160,7 +160,6 @@ greenlet==3.1.1
     # via
     #   apache-superset (pyproject.toml)
     #   shillelagh
-    #   sqlalchemy
 gunicorn==23.0.0
     # via apache-superset (pyproject.toml)
 h11==0.16.0

requirements/development.in

@@ -16,5 +16,5 @@
 # specific language governing permissions and limitations
 # under the License.
 #
--e .[development,bigquery,druid,duckdb,gevent,gsheets,mysql,postgres,presto,prophet,trino,thumbnails]
+-e .[development,bigquery,druid,duckdb,fastmcp,gevent,gsheets,mysql,postgres,presto,prophet,trino,thumbnails]
 -e ./superset-extensions-cli[test]