Skip to main content
Glama
frothkoetter

iceberg-mcp-server-hive

by frothkoetter
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Cloudera Iceberg MCP Server (via Hive)

Fork of cloudera/iceberg-mcp-server that uses Apache Hive (HiveServer2) instead of Impala for read-only access to Iceberg tables on CDP.

MCP Tools

Tool

Description

execute_query(query)

Run read-only SQL (SELECT, SHOW, DESCRIBE, WITH, EXPLAIN)

get_schema(database?)

List tables in the configured or given database

list_databases()

List all visible Hive databases

Related MCP server: MCP Trino Server

Configuration

Connection uses impyla against HiveServer2 (HTTP transport for CDP/Knox).

Example JDBC URL from CDP Data Warehouse:

jdbc:hive2://hs2-cdw-aw-se-hive.dw-se-sandbox-aws.a465-9q4k.cloudera.site/default;transportMode=http;httpPath=cliservice;ssl=true

Maps to MCP env vars:

JDBC / CDP

Env var

Host in URL

HIVE_HOST

Path after host (/default)

HIVE_DATABASE

httpPath=cliservice

HIVE_HTTP_PATH

transportMode=http

HIVE_USE_HTTP_TRANSPORT=true

ssl=true

HIVE_USE_SSL=true

Port (443 implied)

HIVE_PORT=443

LDAP user/password

HIVE_USER, HIVE_PASSWORD

Variable

Default

Description

HIVE_HOST

—

HiveServer2 or Knox gateway host

HIVE_PORT

443

HS2 port (443 for Knox HTTP)

HIVE_USER

—

LDAP / service user

HIVE_PASSWORD

—

Password

HIVE_DATABASE

default

Default database for SHOW TABLES

HIVE_AUTH_MECHANISM

LDAP

impyla auth mechanism

HIVE_USE_HTTP_TRANSPORT

true

HTTP transport (typical on CDP)

HIVE_HTTP_PATH

cliservice

Knox / HS2 HTTP path

HIVE_USE_SSL

true

TLS

MCP_TRANSPORT

stdio

stdio, http, or sse

Claude Desktop / Agent Studio

{
  "mcpServers": {
    "iceberg-mcp-server-hive": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/<your-org>/iceberg-mcp-server-hive@main",
        "run-server"
      ],
      "env": {
        "HIVE_HOST": "hs2-your-cluster.example.cloudera.site",
        "HIVE_PORT": "443",
        "HIVE_USER": "username",
        "HIVE_PASSWORD": "password",
        "HIVE_DATABASE": "default"
      }
    }
  }
}

Local development

git clone https://github.com/<your-org>/iceberg-mcp-server-hive.git
cd iceberg-mcp-server-hive
uv sync --dev
export HIVE_HOST=... HIVE_USER=... HIVE_PASSWORD=...
uv run run-server

Differences from upstream (Impala)

  • Environment variables use HIVE_* instead of IMPALA_*

  • get_schema returns {database, tables} and accepts an optional database name

  • Added list_databases tool

  • execute_query returns {columns, rows} for SELECT results

Examples

See ./examples for LangChain and OpenAI SDK notebooks (update env vars from IMPALA_* to HIVE_*).

Copyright (c) 2025 - Cloudera, Inc. All rights reserved.

Install Server
A
license - permissive license
A
quality
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/frothkoetter/iceberg-mcp-server-hive'

If you have feedback or need assistance with the MCP directory API, please join our Discord server