v0.1.0

🚀 MCP Apache Spark History Server v0.1.0 Release

🚀 Initial Release Highlights

We're excited to announce the first official release of the MCP Apache Spark History Server! This groundbreaking tool enables AI-powered debugging and optimization of Apache Spark jobs through natural language interactions.

🤖 AI Integration

• Claude Desktop Integration - Seamless AI-powered Spark job analysis
• Amazon Q CLI Support - Native AWS AI assistant integration
• LangGraph Example with Ollama - Local AI model integration capabilities

⚙️ Configuration & Flexibility

• Configurable MCP Server Settings - Customizable server parameters
• Environment Variable Support - .env file configuration with default values
• Configurable Listen Address & NodePort - Flexible networking options
• SSL Verification Toggle - Support for self-signed certificates

🏗️ Development & Testing

• End-to-End Testing Suite - Comprehensive test coverage
• Local Kind Cluster Support - Easy local development setup
• Taskfile Build System - Streamlined development workflow
• Pre-commit Security Guardrails - Prevents hardcoded credentials

🔗 Platform Support

• EMR Persistent UI Support - Enhanced AWS EMR integration
• Glue SHS Compatibility - AWS Glue Spark History Server support
• KIRO Integration - Complete integration instructions

📦 Distribution

• PyPI Publishing - Easy installation via pip install mcp-apache-spark-history-server
• Docker Image Builds - Automated container publishing
• Helm Chart Support - Kubernetes deployment ready

👥 Core Contributors and Maintainers

• @vara-bonthu
• @nabuskey
• @andrewdkim47

📚 Documentation & Examples

• Comprehensive README with demo videos
• Step-by-step setup guides for multiple AI platforms
• Complete integration examples and use cases

Get Started: pip install mcp-apache-spark-history-server

---

What's Changed

• feat: SHS MCP Optimizaiton by @vara-bonthu in #1
• feat: Migrated to Taskfile by @vara-bonthu in #4
• feat: Claude desktop and Amazon Q CLI integration by @vara-bonthu in #6
• make mcp server settings configurable by @nabuskey in #8
• Update env var keys by @nabuskey in #9
• make run tasks interactive by @nabuskey in #11
• use task in workflows by @nabuskey in #13
• add e2e tests by @nabuskey in #12
• update documentation for q configuration by @nabuskey in #14
• Make listen address configurable by @nabuskey in #16
• add tasks for local kind deployment by @nabuskey in #17
• make service nodeport configurable by @nabuskey in #20
• add task to deploy shs to kind cluster with examples by @nabuskey in #21
• Updating Q CLI Setup Readme, and removing suggestion to --trust-all-tools by @andrewdkim47 in #22
• add complete kind setup by @nabuskey in #24
• break up task file by @nabuskey in #25
• pin dependencies to major versions by @nabuskey in #31
• add repo lint files by @nabuskey in #33
• ensure script fails when there's an error by @nabuskey in #35
• Adding guidelines for Glue SHS compatibility: Adding verify_ssl flag to allow user to disable SSL verification for SHS URLs that are self-signed by @andrewdkim47 in #34
• add demo video link by @nabuskey in #38
• ensure background tasks start by @nabuskey in #37
• feat: Langgraph example with SHS MCP and Ollama Models by @vara-bonthu in #40
• fix: Readme update with correct tools and added missing doc string by @vara-bonthu in #41
• Adding EMR persistent UI support by @andrewdkim47 in #43
• Restructuring files by @andrewdkim47 in #47
• Fixing EMR base url to include shs, upgrading pymodule versions, removing duplicate emr client by @andrewdkim47 in #48
• Adding wait for EMR Persistent UI Client status STARTING by @andrewdkim47 in #51
• Updating spark_id to app_id by @andrewdkim47 in #49
• Adding spark_history_server_mcp_launcher.sh to see MCP server output logs by @andrewdkim47 in #52
• Updating get to list when retrieving mutiple items, following native spark standards by @andrewdkim47 in #50
• update lock file and project name by @nabuskey in #60
• reflect repo name change in readme by @nabuskey in #57
• update dockerfile to run the mcp server correctly by @nabuskey in #62
• Update README.md by @vara-bonthu in #61
• rename helm chart to reflect repo name changes by @nabuskey in #64
• Updating KIRO integration instructions by @andrewdkim47 in #65
• Updating diagram and youtube video demo in README by @andrewdkim47 in #63
• Fix Q CLI doc by @nabuskey in #69
• Adding pre-commit guardrail for hardcoded username, password, or authtoken by @andrewdkim47 in #71
• add docker build for sem var tag by @nabuskey in #73
• add configurations for publishing to pypi by @nabuskey in #75
• update gitignore by @nabuskey in #76
• Support dot env file by @nabuskey in #72
• add default config values by @nabuskey in #77
• add pypi index by @nabuskey in #78
• use default pypi settings by @nabuskey in #79

New Contributors

• @vara-bonthu made their first contribution in #1
• @nabuskey made their first contribution in #8
• @andrewdkim47 made their first contribution in #22

Full Changelog: https://github.com/DeepDiagnostix-AI/mcp-apache-spark-history-server/commits/v0.1.0