LangChain

Databricks for LangChain

io.github.mcp-dir/databricks-mcp

Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu

client:LangChain transport:streamable-http tools:17

Install Databricks in LangChain

pip install langchain-mcp-adapters

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "databricks-mcp": {
            "transport": "streamable_http",
            "url": "https://api.mcp.ai/p_databricks",
        }
})

tools = await client.get_tools()

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

What LangChain can do once it is connected

Databricks in other clients

Databricks MCP server