mcp-apache-spark-history-server: The Kubeflow Spark History MCP Server bridges AI agents with Apache Spark infrastructure, enabling intelligent job analysis, performance monitoring, and failure investigation. It provides 18 specialized MCP tools for querying Spark History Server data, supporting multi-server configurations and AWS integrations.; thunderbit-mcp-server: Thunderbit MCP Server is an open-source toolkit for the Thunderbit Open API that ships three packages: a CLI for scripted extraction, an MCP server exposing seven scraping and distillation tools, and a Claude Code plugin. It converts any web page to clean LLM-ready Markdown, extracts structured data via JSON Schema, and supports batch processing — all backed by a free API key.
Investigate why a Spark job is running slower than usual
Feeding clean web content into LLM pipelines for RAG or summarization