Dremio MCP server

Name: Dremio MCP server
Author: dremio

@dremio

リポジトリ

Dremio MCP server について

Dremio MCP server

#ai #mcp #dremio #llm #agentic-ai #mcp-server

基本情報

カテゴリ

その他

ライセンス

Apache-2.0

ランタイム

python

トランスポート

stdio

公開者

dremio

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": {
    "dremio-mcp": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "dremio-mcp:0.1.0",
        "."
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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 Dremio MCP server?

Dremio MCP server is an MCP (Model Context Protocol) server that enables LLMs to integrate with Dremio for querying, analyzing, and discovering data. It is intended for developers and data professionals who want to use AI assistants like Claude with Dremio.

How to use Dremio MCP server?

Install locally using uv and Python 3.11+. Create a Dremio config file with your Dremio URI and PAT (or OAuth), then configure the LLM desktop app (Claude) to reference the server. For production, deploy via Helm chart with streaming HTTP, OAuth, and autoscaling.

Key features of Dremio MCP server

Local and remote (Kubernetes/Helm) deployment
Supports PAT and OAuth + external token authentication
Three server modes: FOR_DATA_PATTERNS, FOR_SELF, FOR_PROMETHEUS
Automatic logging to platform-specific locations
Optional semantic search and DML operations
Prometheus metrics and horizontal pod autoscaling (Helm)

Use cases of Dremio MCP server

Let an LLM discover and query Dremio tables for pattern analysis
Introspect Dremio system internals, workload analysis (FOR_SELF mode)
Combine Dremio metrics from Prometheus for enriched insights
Deploy a scalable, production‑grade MCP server for enterprise AI assistants

FAQ from Dremio MCP server

How do I install Dremio MCP server locally?

Clone the repository, install uv, ensure Python 3.11+, then run uv run dremio-mcp-server --help to verify.

What authentication methods are supported?

PAT for development/testing; OAuth with an external token provider for production. A PAT can be stored in a file and referenced with @ to avoid leaking in shell history.

What are the three server modes?

FOR_DATA_PATTERNS (normal): allows LLM to read tables and data. FOR_SELF: introspects Dremio system, including workload analysis. FOR_PROMETHEUS: connects to Prometheus for Dremio‑related metrics.

Where are logs stored?

Logs are written automatically to platform‑specific directories: ~/.local/share/dremioai/logs/ (Linux), ~/Library/Logs/dremioai/ (macOS), or %LOCALAPPDATA%\dremioai\logs\ (Windows).

Does Dremio MCP server support Dremio Cloud?

Yes. You must provide a project ID when configuring for Dremio Cloud, and use the URI https://api.dremio.cloud (US) or https://api.eu.dremio.cloud (EMEA).