Skip to main content
Glama
will-sh

Spark Iceberg MCP Server

by will-sh

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SPARK_HOMENoOptional SPARK_HOME for subprocess
SPARK_MASTERNoSpark master URL (local[2], yarn, etc.)local[2]
MCP_TRANSPORTNoMCP transport: stdio, http, or ssestdio
SPARK_MAX_ROWSNoMax rows returned per query1000
HADOOP_CONF_DIRNoHadoop config directory
SPARK_SUBMIT_BINNoSpark submit binary for subprocess modespark3-submit
SPARK_EXECUTION_MODENosubprocess, pyspark, or auto (subprocess if SPARK_SUBMIT_BIN set)auto
SPARK_ICEBERG_CATALOGNoIceberg catalog namelocal
SPARK_ICEBERG_WAREHOUSEYesWarehouse path (required for Hadoop catalog)
SPARK_ICEBERG_RUNTIME_JARNoPath to iceberg-spark-runtime JAR (glob supported)
SPARK_ICEBERG_CATALOG_TYPENoCatalog type (hadoop, hive, rest, …)hadoop

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources