spark_history_mcp_server

zjt-peekaboo/spark_history_mcp_server

3.3

If you are the rightful owner of spark_history_mcp_server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Model Context Protocol (MCP) server is designed to facilitate the management and optimization of Spark applications by providing a suite of tools and resources for performance analysis and diagnostics.

Tools
18
Resources
0
Prompts
0

Quick start

  1. Start Spark history server and modify spark server url in
  2. Run it directly
  3. MCP SSE endpoint：http://localhost:18888/sse

Tools Provided

  • Tool name: compare_job_environments, Description: Compare Spark environment configurations between two jobs
  • Tool name: compare_job_performance, Description: Compare performance metrics between two Spark jobs
  • Tool name: get_application, Description: Get detailed information about a specific Spark application
  • Tool name: get_environment, Description: Get the environment information for a Spark application
  • Tool name: get_executor, Description: Get information about a specific executor
  • Tool name: get_executor_summary, Description: Get a summary of executors about a application
  • Tool name: get_job_bottlenecks, Description: Identify performance bottlenecks in a Spark job
  • Tool name: get_resource_usage_timeline, Description: Get resource usage timeline for a Spark application
  • Tool name: get_sql_list, Description: Get a list of SQL queries for a Spark application
  • Tool name: get_stage, Description: Get information about a specific stage
  • Tool name: get_stage_task_summary, Description: Get a summary metrics of all tasks in the given stage attempt
  • Tool name: list_applications, Description: Get a list of applications from the Spark History Server
  • Tool name: list_executors, Description: Get a list of all executors for a Spark application
  • Tool name: list_jobs, Description: Get a list of all jobs for a Spark application
  • Tool name: list_slowest_jobs, Description: Get the N slowest jobs for a Spark application
  • Tool name: list_slowest_sql_queries, Description: Get the N slowest SQL queries for a Spark application
  • Tool name: list_slowest_stages, Description: Get the N slowest stages for a Spark application
  • Tool name: list_stages, Description: Get a list of all stages for a Spark application

Applications Envisioned in agent

  1. Spark-sql task diagnosis
  2. Spark-sql task optimization
  3. Review of historical task execution trends