The Kubeflow Spark AI Toolkit connects AI agents and engineers to an Apache Spark History Server so that Spark applications can be inspected, compared and investigated without opening the web UI. It ships two interfaces over the same data. The MCP server, written in Python and published to PyPI as mcp-apache-spark-history-server, exposes the Spark REST API as Model Context Protocol tools, handling tool selection, routing across several configured history servers and structured data retrieval, so an agent can answer natural-language questions and run multi-step investigations. It also ships prompts, which are guided multi-step workflows invoked as commands in the client, for example investigate_failure with an application id. Installation is through uvx or uv tool install, and registration is documented for Claude Code and Kiro CLI over stdio. Configuration comes from a config.yaml resolved in a fixed order, namely the --config flag, the SHS_MCP_CONFIG variable, the current directory and then the XDG config directory; every other setting is available as an SHS_ prefixed environment variable. The file lists servers with their URL, an optional default flag, optional basic authentication and a switch for including SQL plan descriptions, plus an mcp section choosing the streamable-http or stdio transport, the port and a debug flag. With no configuration the server points at http://localhost:18080. The second interface is shs, a standalone static Go binary with no dependencies, aimed at engineers, shell scripts, CI pipelines and coding agents that prefer running a known command. It offers subcommands to list applications, filter jobs by status, sort stages by duration and compare two applications, and it can emit its own agent skill file with shs setup skill. The project is an official Kubeflow repository under the Apache 2.0 licence.
https://github.com/kubeflow/mcp-apache-spark-history-server
Apache APISIX is a high-performance cloud-native API Gateway and AI Gateway that supports Model Context Protocol (MCP) integration through its mcp-bridge plugin, offering dynamic traffic management, security, and observability features.
AWS MCP Servers is a suite of specialized Model Context Protocol servers that integrate AWS best practices and resources into AI-powered development workflows to enhance cloud-native development and infrastructure management.
Webiny is an open-source, self-hosted headless CMS and framework, built on AWS serverless with AI-assisted development capabilities via an embedded MCP server, designed for large organizations.
MCP Registry is a community-driven centralized service offering a RESTful API for discovering, managing, and publishing Model Context Protocol (MCP) servers with MongoDB and Docker support.
Olares is an open-source personal cloud operating system that enables users to run local AI models and applications with personalized, context-aware AI interactions using a Model Context Protocol-like mechanism, providing a private and secure AI home server environment.
Cloudflare MCP Server is a suite of MCP servers that enable large language model clients to interact with and manage Cloudflare's cloud services through natural language commands, facilitating automation and insights across various domains.
mcp-grafana is an MCP server that provides comprehensive programmatic access to Grafana's dashboards, datasources, alerts, incidents, and on-call management features through MCP clients.
MCP Containers offers containerized versions of hundreds of MCP servers, enabling easy, secure, and up-to-date deployment of Model Context Protocol servers for AI integration and experimentation.