$ loading_
Run stateful local PySpark and SQL sessions for data exploration and validation.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "local-spark-mcp" yet — see the docs or source repo.
In the local Spark session, load sales.csv with PySpark, clean missing values, standardize date formats, and show the first 20 rows plus a schema summary.
Runnable PySpark code plus a preview of cleaned data and schema details.
Register the orders DataFrame as a temp table, then use SQL to calculate monthly order count, total sales, and average order value, sorted by month.
The matching SQL or PySpark cells and a monthly aggregated results table.
Run my ETL transformation steps for Microsoft Fabric in the local Spark environment, verify joins, filters, and aggregations, and flag potential issues.
Validated execution steps, detected issues, and recommendations to fix them before deployment.
Provides Spark query plans and catalog data for optimization and discovery.
Search and analyze Spark Desktop meeting transcripts and emails with natural language.
Simulate cloud services locally for faster development and testing workflows.
Query Fabric Lakehouse data and manage Eventstreams with natural language.
Query Spark History Server apps, jobs, stages, and metrics in natural language.
Use MCP to manage Microsoft Fabric data and analytics operations.