mcp-apache-spark-history-server
Active·★ 173·Apache-2.0·Updated 2026-05-29
★ Trending★ LLM Infra
MCP Server for Apache Spark History Server. The bridge between Agentic AI and Apache Spark.
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.
#apache-spark#big-data#data-processing#kubernetes#mcp#mcp-server#mcp-servers
01
Features
01Natural language query of Spark job details
02Performance metrics analysis across applications
03Cross-job comparison for regression detection
04Failure investigation with detailed error analysis
05Multi-server and multi-environment support
02
Compatibility
Python
Python 3.12+
Verified via docs
Apache Spark History Server
Spark History Server
Verified via docs
Kubernetes
Kubernetes (Helm)
Verified via docs
AWS Glue
AWS Glue
Verified via docs
Amazon EMR
Amazon EMR
Verified via docs
03
Quick start
1
$ pip install mcp-apache-spark-history-server
04
Use cases
↳Investigate why a Spark job is running slower than usual
↳Analyze root cause of job failures
↳Compare performance of current and previous job runs
05
Alternatives
FunASR★ 16.6k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
thunderbit-mcp-server★ 13
AI-powered web scraping and structured data extraction. CLI + MCP server + Claude Code plugin for the Thunderbit Open API.
Related searches
Comments
Log in to leave a comment
- RRiley ZhangMay 20, 2026
Bridge between agentic AI and Apache Spark operational data is well-designed.
- Rowan ChenMay 12, 2026
Good for data engineers debugging Spark jobs who want AI assistance.
- SSam WilsonMar 25, 2026
Works with standard Spark History Server deployments.
- BBlake WhiteMar 7, 2026
Spark History Server integration via MCP brings job analytics into AI workflows.