Spark SQL MCP

This community MCP server enables AI assistants to query Spark SQL clusters via the Thrift/HiveServer2 protocol. It supports schema discovery, listing databases and tables, and executing read-only SQL queries. It is compatible with Apache Spark, AWS EMR, Hive, Impala, and Presto, offering multiple authentication methods including NONE, LDAP, Kerberos, and CUSTOM.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

Community listingLocal stdioSource reviewed; not executedPublished by aidancorrell

You need:pip install spark-sql-mcp-server

Vendor documentation

What you can do with it

Execute read-only SQL queries against a Spark cluster
List all available databases in the cluster
Describe table structures and schemas
Discover tables within a specific database

Source and maintenance

Community listingRegistry 0.1.2

mcp-registry: io.github.aidancorrell/spark-sql-mcp-server@0.1.2 Source repository

Maintenance checked: Nov 1, 2026, 6:06 AM UTC

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

spark-sql-mcp-server 0.1.2

pypi

spark-sql-mcp-server package definition

{
  "version": "0.1.2",
  "transport": "stdio",
  "identifier": "spark-sql-mcp-server",
  "registryType": "pypi",
  "environmentVariables": [
    {
      "name": "SPARK_HOST",
      "format": "string",
      "isRequired": true,
      "description": "Hostname of the Spark Thrift Server"
    },
    {
      "name": "SPARK_PORT",
      "format": "number",
      "description": "Port of the Spark Thrift Server (default: 10000)"
    },
    {
      "name": "SPARK_DATABASE",
      "format": "string",
      "description": "Default database to use"
    },
    {
      "name": "SPARK_AUTH",
      "format": "string",
      "description": "Authentication method: NONE, LDAP, KERBEROS, CUSTOM, or NOSASL"
    },
    {
      "name": "SPARK_USERNAME",
      "format": "string",
      "description": "Username for LDAP authentication"
    },
    {
      "name": "SPARK_PASSWORD",
      "format": "string",
      "description": "Password for LDAP authentication"
    },
    {
      "name": "SPARK_KERBEROS_SERVICE_NAME",
      "format": "string",
      "description": "Kerberos service name (default: hive)"
    }
  ]
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.

Cursor configuration

{
  "mcpServers": {
    "spark-sql-mcp": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server==0.1.2"
      ],
      "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>"
      }
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.

Cline configuration

{
  "mcpServers": {
    "spark-sql-mcp": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server==0.1.2"
      ],
      "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>"
      }
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.

VS Code configuration

{
  "servers": {
    "spark-sql-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server==0.1.2"
      ],
      "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>"
      }
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.

Claude Desktop configuration

{
  "mcpServers": {
    "spark-sql-mcp": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server==0.1.2"
      ],
      "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>"
      }
    }
  }
}

Let your agent find its tools

Find servers like Spark SQL MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 4,066