Apache Spark – MCP tools

query_dataset
Foundry MCP Server
Execute Spark SQL queries on Foundry datasets to retrieve and analyze data directly through natural language commands.
MIT License
create_batch_job
Dataproc MCP Server
Submit and manage batch jobs on Google Cloud Dataproc. Define job types (Spark, PySpark, Spark SQL), include main files, JARs, arguments, and configure properties for efficient job execution.
MIT License
create_cluster
Databricks MCP Server
Set up a new Databricks cluster with custom parameters like cluster name, Spark version, node type, worker count, and auto-termination settings using Databricks MCP Server.
submit_job
Dataproc MCP Server
Submit a job to a Dataproc cluster by specifying project ID, region, cluster name, job type, main file, and optional arguments, JAR files, and properties. Supports Spark, PySpark, Hive, Pig, and Hadoop job types.
MIT License
generate_echarts
MCP ECharts
Create dynamic, interactive charts using Apache ECharts by providing customizable configurations. Export visualizations as PNG, SVG, or raw option formats for seamless integration into web applications.
MIT License
create_cluster
Databricks MCP Server
Set up a new Databricks cluster by defining its name, Spark version, node type, and worker count, enabling execution of data processing workflows.

Interested in MCP?

Join the MCP community for support and updates.