MCP.so
Sign In
Servers

Apache Spark MCP Server by CData

@CDataSoftware

This read-only MCP Server allows you to connect to Apache Spark data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Overview

What is Apache Spark MCP Server by CData?

Apache Spark MCP Server by CData is a local, read-only MCP server that enables LLMs (like Claude Desktop) to query live data from Apache Spark using natural language. It wraps the CData JDBC Driver for Apache Spark, which exposes Spark data as relational SQL models.

How to use Apache Spark MCP Server by CData?

Clone, build with Maven (mvn clean install), download and license the CData JDBC Driver for Apache Spark, configure the connection string via the JDBC utility, create a .prp file with driver path, class, and JDBC URL, then configure Claude Desktop’s claude_desktop_config.json with the Java command and the .prp file. The server runs locally via stdio.

Key features of Apache Spark MCP Server by CData

  • Read-only access to Apache Spark data
  • Natural language querying via LLM clients
  • Built-in tools: get_tables, get_columns, run_query
  • JDBC-driven connectivity to live data
  • Local stdio transport (same machine only)

Use cases of Apache Spark MCP Server by CData

  • Ask an LLM “What is the correlation between my closed won opportunities and account industry?”
  • Query “How many open tickets do I have in the SUPPORT project?”
  • Retrieve live Apache Spark data without writing SQL
  • Analyze calendar events or any structured data in Spark

FAQ from Apache Spark MCP Server by CData

Is this server read-only?

Yes, this read-only MCP server only supports SELECT queries. For full read, write, update, delete, and action capabilities, consider the managed CData MCP Server or CData Connect AI.

Where does my data live?

Data remains in your Apache Spark instance. The server connects to it via the CData JDBC Driver and does not store or copy data externally.

What dependencies are required?

Java (runtime), Maven (build), and the CData JDBC Driver for Apache Spark (download and license separately) are required.

How does authentication work?

Authentication is handled via the JDBC connection string (e.g., OAuth credentials). The server does not manage authentication itself.

What transport does the server use?

The server uses stdio transport, so it can only run with clients on the same machine (e.g., Claude Desktop locally).

Tags

More from Other