Skip to content
mcp/harbor
LangChain

Spark SQL for LangChain

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

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

client:LangChain transport:stdio runtime:pypi

Install Spark SQL in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "spark-sql-mcp-server": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["spark-sql-mcp-server"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

Spark SQL in other clients

Spark SQL MCP server