"Amazon EKS" matching MCP servers:

Lets assistants send the same test prompts to as many as four text models across OpenRouter, Amazon Bedrock, Google Vertex AI and Microsoft Foundry, then automatically grade each answer with a judge model, rule checks and a policy gate. Returns scored leaderboards with letter grades, per-response strengths and weaknesses, latency, throughput and estimated cost, plus downloadable PDF and CSV reports.

Enables web scraping, React app testing, and React Native web app inspection using Playwright with multi-browser support. Provides backward compatibility with regular websites while offering enhanced features for React applications including mobile viewport emulation and component analysis.

Enables AI agents and Amazon Alexa+ skills to orchestrate desktop load-testing workflows hands-free, including launching closed-loop or ramp-up traffic campaigns, streaming live RPS and P50/P95/P99 telemetry, gracefully halting runs, and retrieving bilingual executive capacity audits. Tools are Zod-validated and exposed over stdio with built-in circuit-breaker safety monitoring.

An MCP server that lets an AI build hours of operation, queues, routing profiles, and real IVR flows from plain English, diagram them in chat, validate them with the platform's own flow validator, and prove them with simulated test calls. It is deliberately unable to go live on its own — no dialing, no number association, no deletes — so a human always makes the final connection.

Run and test agentic systems in isolated Docker sandboxes, varying system prompts, models, and task prompts while capturing full behavior traces via MCP tools.

An MCP server for Chaos Mesh fault injection, optimized for AWS EKS with namespace support, enabling pod, network, and host-level chaos experiments.