kubeflow/mcp-apache-spark-history-server

MCP Server for Apache Spark History Server. The bridge between Agentic AI and Apache Spark.

66
/ 100
Established

Implements an MCP-compatible server that exposes 18+ specialized tools for querying Spark History Server data—including job/stage performance analysis, executor metrics, SQL query analysis, and resource utilization tracking. Operates via stdio or HTTP transport, allowing AI agents (LangChain, LlamaIndex, Claude Desktop) to intelligently select and combine tools for job analysis without reimplementing data access logic. Supports multiple Spark History Server instances through YAML configuration, enabling comparative analysis and failure investigation across environments.

135 stars and 628 monthly downloads. Available on PyPI.

Maintenance 10 / 25
Adoption 16 / 25
Maturity 18 / 25
Community 22 / 25

How are scores calculated?

Stars

135

Forks

46

Language

Python

License

Apache-2.0

Last pushed

Mar 03, 2026

Monthly downloads

628

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/kubeflow/mcp-apache-spark-history-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.