[WIP] HIVE-29370: Text-to-SQL with HMS MCP Server

[deniskuzZ]

What changes were proposed in this pull request?

MCP Server that exposes Hive Metastore metadata via the Iceberg REST Catalog API.

Why are the changes needed?

Expose Data Lake metadata through MCP

Does this PR introduce any user-facing change?

No

How was this patch tested?

pip install -r $HIVE_HOME/scripts/nlsql/requirements.txt

mvn clean install -DskipTests -T8 -Pdist -Dmaven.javadoc.skip -Drat.skip --fail-at-end

export HIVE_VERSION=4.3.0-SNAPSHOT
docker-compose --profile llap down --rmi all
./build.sh -hive ${HIVE_VERSION} -hadoop 3.4.2 -tez 0.10.5
./start-hive.sh --llap

export ANTHROPIC_BASE_URL="https://api.anthropic.com"   # or your gateway URL
export ANTHROPIC_AUTH_TOKEN="your-token"                 # or use ANTHROPIC_API_KEY
export ANTHROPIC_MODEL="anthropic.claude-opus-4-6"       
export MCP_SERVER_URL="http://localhost:3000/sse"

$HIVE_HOME/bin/beeline -u "jdbc:hive2://localhost:10000"

beeline> !nlsql show me the top 10 orders by amount
beeline> !nlsql count all rows in the customers table
beeline> !nlsql which tables have more than 1 million rows

[Aggarwal-Raghav]

I initally thought the implemenation will be in java using spring-ai 😅

[sonarqubecloud]

Quality Gate passed

Issues
19 New issues
0 Accepted issues

Measures
1 Security Hotspot
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud