{"id":"zjt-peekaboo-spark-history-mcp-server","name":"spark_history_mcp_server","af_score":32.8,"security_score":21.8,"reliability_score":18.8,"what_it_does":"Provides an MCP (SSE) server wrapper around an Apache Spark History Server, exposing tools to list and inspect Spark applications/jobs/stages/executors and to compare job environments/performance and identify bottlenecks.","best_when":"You have access to a Spark History Server dataset and want an LLM agent to quickly explore Spark execution history via MCP tools.","avoid_when":"You cannot access the History Server data or you need authenticated/secure-by-default access to the MCP endpoint for untrusted users.","last_evaluated":"2026-04-04T20:01:04.680591+00:00","has_mcp":true,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["README does not document parameter schemas, output formats, pagination, or limits for tools—agents may need trial-and-error.","No rate limit or timeout behavior is documented; long history queries could cause slow responses.","No auth details are provided; exposing the SSE endpoint publicly may be unsafe without additional controls.","Local URL example uses localhost; agents running remotely must ensure network reachability and correct configuration of application.yaml."],"error_quality":0.0}