PluginBench
MCP Server
Maintained
MIT

Spark SQL MCP Server

io.github.aidancorrell/spark-sql-mcp-server

RepositoryRegistry
How to choose

What this kind of tool is for

  • Query, inspect, or seed a database without writing a one-off script.
  • Let your agent look up schema details before it writes migration code.
  • Move a small dataset between tools without leaving the terminal.

How to compare servers like this

Engine match:
Confirm it speaks your exact database and version, not just the family.
Access scope:
Read-only connections are the safe default — start there before granting writes.
Safety rails:
Check whether destructive statements need an explicit confirmation before they run.
Maintenance signal:
Database drivers change; a recently updated tool is less likely to break mid-query.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Spark SQL MCP server?

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

How to install Spark SQL

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • SPARK_HOST
    required

    Hostname of the Spark Thrift Server

  • SPARK_PORT

    Port of the Spark Thrift Server (default: 10000)

  • SPARK_DATABASE

    Default database to use

  • SPARK_AUTH

    Authentication method: NONE, LDAP, KERBEROS, CUSTOM, or NOSASL

  • SPARK_USERNAME

    Username for LDAP authentication

  • SPARK_PASSWORD
    secret

    Password for LDAP authentication

  • SPARK_KERBEROS_SERVICE_NAME

    Kerberos service name (default: hive)

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "<YOUR_SPARK_HOST>",
        "SPARK_PORT": "<YOUR_SPARK_PORT>",
        "SPARK_DATABASE": "<YOUR_SPARK_DATABASE>",
        "SPARK_AUTH": "<YOUR_SPARK_AUTH>",
        "SPARK_USERNAME": "<YOUR_SPARK_USERNAME>",
        "SPARK_PASSWORD": "<YOUR_SPARK_PASSWORD>",
        "SPARK_KERBEROS_SERVICE_NAME": "<YOUR_SPARK_KERBEROS_SERVICE_NAME>"
      }
    }
  }
}

Related MCP servers

Post-scrape data cleaner, no LLM: repairs mojibake, HTML, invisible chars. Plus a verdict.

AIDC MCP for OPR/BOD sizing, validation, and rackPlan layout from the shared 3D graph.

View repository →

Hosted MCP for Pagent: review Bayesian A/B tests, capture hypotheses, manage websites via OAuth.

View repository →
BTBTCFi API logo

BTCFi API

Active

Bitcoin data for AI agents. 27 tools with x402 micropayments. No API keys needed.

0
TypeScript
MIT
View repository →
AIaide-memory logo

Persistent memory layer for AI coding agents — your agent remembers what you taught it.

1
View repository →

MCP server that teaches any AI agent the AIDE methodology via progressive disclosure

2
TypeScript
MIT
View repository →