Skip to content
MCP server

Spark SQL

Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.

Runs locallyStatus and history
Install
Pricing
Open source
Runs
Locally
Version
0.1.2
Listing updated
4 days ago

About Spark SQL

Spark SQL is an open-source MCP server for databases. It runs locally on your machine and is started by your AI client.

Install

Run in a terminal

claude mcp add spark-sql-mcp-server --env SPARK_HOST='<SPARK_HOST>' --env SPARK_PASSWORD='<SPARK_PASSWORD>' -- uvx spark-sql-mcp-server

Add to claude_desktop_config.json

{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "<SPARK_HOST>",
        "SPARK_PASSWORD": "<SPARK_PASSWORD>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "<SPARK_HOST>",
        "SPARK_PASSWORD": "<SPARK_PASSWORD>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "spark-sql-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "<SPARK_HOST>",
        "SPARK_PASSWORD": "<SPARK_PASSWORD>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "<SPARK_HOST>",
        "SPARK_PASSWORD": "<SPARK_PASSWORD>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "<SPARK_HOST>",
        "SPARK_PASSWORD": "<SPARK_PASSWORD>"
      }
    }
  }
}

Configuration

  • SPARK_HOSTHostname of the Spark Thrift ServerRequired
  • SPARK_PORTPort of the Spark Thrift Server (default: 10000)
  • SPARK_DATABASEDefault database to use
  • SPARK_AUTHAuthentication method: NONE, LDAP, KERBEROS, CUSTOM, or NOSASL
  • SPARK_USERNAMEUsername for LDAP authentication
  • SPARK_PASSWORDPassword for LDAP authentication
  • SPARK_KERBEROS_SERVICE_NAMEKerberos service name (default: hive)

Pricing

Open source

Spark SQL FAQ

Is Spark SQL free?

Yes. Spark SQL is open source, so you can use and self-host it for free.

How do I add Spark SQL to Claude Code?

Run this command in your terminal: claude mcp add spark-sql-mcp-server --env SPARK_HOST='<SPARK_HOST>' --env SPARK_PASSWORD='<SPARK_PASSWORD>' -- uvx spark-sql-mcp-server

What are the best alternatives to Spark SQL?

The closest alternatives to Spark SQL are Midplane, PlatypusDB, Lorebase, Sovaria and model2data studio.

Alternatives to Spark SQL

  1. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  2. PlatypusDB

    MCP server

    Gives MCP clients access to your PlatypusDB database connections, scoped per agent

    Runs locally
    • Open source
    • Databases
  3. Lorebase

    MCP server

    Lets agents read and change a governed, versioned Postgres knowledge graph

    Runs locally
    • Open source
    • Knowledge and memory
  4. Sovaria

    MCP server

    Manage a Sovaria backend (Postgres, auth, storage, functions) from an AI assistant

    Not checked yet
    • 4 tools
    • Remote
    • Freemium
    • Databases
  5. Generate realistic connected test data, dbt projects and dashboards from a schema

    • Remote
    • Freemium
    • Databases
  6. semlayer

    MCP server

    Infers a semantic layer from your data warehouse and serves it to agents

    Runs locally
    • Free
    • Databases