Spark SQL

Spark SQL MCP Server is an open-source MCP (Model Context Protocol) server that allows AI assistants (like Claude, Cursor, Windsurf, and other MCP-compatible clients) to query Spark SQL clusters using the Thrift/HiveServer2 protocol. It supports SQL querying, schema discovery, and works with major Big Data engines including Apache Spark, AWS EMR, Hive, Impala, and Presto. Intended for data engineers, analytics teams, and organizations looking to enable natural language or automated access to Spark-hosted data, it enforces read-only SQL for safety, supports multiple authentication methods (NONE, LDAP, Kerberos, etc.), and features safety defaults such as automatic query LIMITs and sanitized error messages.