apache-spark-mcp-server-by-cdata
If you are the rightful owner of apache-spark-mcp-server-by-cdata and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
CData's Model Context Protocol (MCP) Server for Apache Spark is a read-only server that allows LLMs to query live data from Apache Spark using the CData JDBC Driver.
The Apache Spark MCP Server by CData is designed to facilitate the interaction between large language models (LLMs) and Apache Spark data. By leveraging the CData JDBC Driver, this server exposes Apache Spark data as relational SQL models, enabling LLMs to query live data using natural language without the need for SQL knowledge. This read-only server is ideal for users who need to access real-time data from Apache Spark in a simplified manner. The server is built using Java and requires the CData JDBC Driver for Apache Spark to function. It is particularly useful for applications like Claude Desktop, where users can ask questions about their data and receive immediate insights.
Features
- Read-only access to Apache Spark data through MCP interface.
- Integration with CData JDBC Driver for Apache Spark.
- Natural language querying without SQL.
- Compatible with LLMs like Claude Desktop.
- Simplified setup and configuration.
Tools
{servername}_get_tables
Get a list of available tables in the data source
{servername}_get_columns
Get the column list of specified tables
{servername}_run_query
Execute SQL SELECT query