Install Spark SQL in Claude Code
claude mcp add spark-sql -e SPARK_HOST=... -- uvx spark-sql-mcp-server{
"mcpServers": {
"spark-sql": {
"command": "uvx",
"args": [
"spark-sql-mcp-server"
],
"env": {
"SPARK_HOST": "..."
}
}
}
}Replace each ... with your own value.
Frequently asked questions
What does the Spark SQL MCP server do?
Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.
Is the Spark SQL MCP server free?
Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.
Does Spark SQL run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add Spark SQL to Claude Code?
Run: claude mcp add spark-sql -e SPARK_HOST=... -- uvx spark-sql-mcp-server
More databases MCP servers
View allSQLite Local AI Memory
cheveguerra/sqlite-local-ai-memory
100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).
Pitstop
praneethravuri/pitstop
F1 MCP server: live timing, telemetry, standings, news, and a queryable 1950-present database.
SQLite MCP Sidecar
xakpc/sqlite-mcp-sidecar
Agent-safe MCP sidecar for one live SQLite database: read-only default, bounded writes.
Open Quality
FHIR-IQ/openquality
Open healthcare quality measures: CQL, SQL and FHIR with provenance and known issues
SupaForge
akalsoftware/supaforge
Find and fix drift between Supabase environments: schema, RLS, roles, auth, storage and more.
NicheDB
profullstack/niche-db
Sources in, feeds out: an open, ever-growing database of real-time public data, enriched.