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.; ninjaone-mcp: NinjaOne MCP Server connects AI assistants to the NinjaOne IT management platform via Model Context Protocol. It uses a hierarchical tool-loading architecture to expose device monitoring, patch management, scripting, ticketing, and alert management — loading only the relevant domain tools on demand to reduce context overhead. Supports one-click deployment to DigitalOcean and Cloudflare Workers.
Investigate why a Spark job is running slower than usual
Managing IT devices and running scripts through an AI assistant interface