Cloudera Iceberg MCP Server (via Impala)

@peterableda

リポジトリ

基本情報

カテゴリ

その他

ライセンス

Apache-2.0 license

トランスポート

stdio

作者

peterableda

Cloudera Iceberg MCP Server について

Cloudera Iceberg MCP Server via Impala

Cloudera Iceberg MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "iceberg-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/iceberg-mcp-server",
        "run",
        "server.py"
      ],
      "env": {
        "IMPALA_HOST": "coordinator-default-impala.example.com",
        "IMPALA_PORT": "443",
        "IMPALA_USER": "username",
        "IMPALA_PASSWORD": "password",
        "IMPALA_DATABASE": "default"
      }
    }
  }
}

Cloudera Iceberg MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Cloudera Iceberg MCP Server (via Impala)?

A Model Context Protocol server that provides read-only access to Iceberg tables via Apache Impala. It enables LLMs to inspect database schemas and execute read-only SQL queries.

How to use Cloudera Iceberg MCP Server (via Impala)?

Configure it in Claude Desktop as an MCP server by adding a JSON entry to claude_desktop_config.json with uv run server.py and environment variables (IMPALA_HOST, IMPALA_PORT, IMPALA_USER, IMPALA_PASSWORD, IMPALA_DATABASE). Example integrations for LangChain/LangGraph and OpenAI SDK are included in the ./examples folder.

Key features of Cloudera Iceberg MCP Server (via Impala)

execute_query: Run any SQL query on Impala and return results as JSON.
get_schema: List all tables available in the current database.
Read‑only access to Iceberg tables.
Designed for LLM integration (Claude Desktop, LangChain, OpenAI SDK).
Uses Impala as the query engine.

Use cases of Cloudera Iceberg MCP Server (via Impala)

Allow an LLM to discover table schemas in an Iceberg data lake.
Query Iceberg tables with natural language through an LLM agent.
Integrate read‑only SQL access into AI‑powered data analysis workflows.
Validate data or run ad‑hoc analytics without granting write permissions.

よくある質問

What data sources does this server work with?

It works with any Iceberg table that is accessible via an Apache Impala cluster. You must provide the Impala host, port, credentials, and a target database.

Is the server read‑only?

Yes. The server only exposes `execute_query` (any SQL) and `get_schema`; the README explicitly states it provides “read‑only access to Iceberg tables.”

What runtime does the server require?

The server is distributed as a Python script and launched with `uv`. It requires Python and the `uv` package manager installed on the machine running the MCP host (e.g., Claude Desktop).

How do I authenticate to Impala?

Authentication is done via environment variables: `IMPALA_USER` and `IMPALA_PASSWORD`. The server does not support other authentication methods as described in the README.

Are there example integrations available?

Yes, the `./examples` folder contains examples for integrating with LangChain/LangGraph and the OpenAI SDK.

「その他」の他のコンテンツ

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct