Dremio MCP server

Table of Contents

• Introduction

• Installation

• Initial setup

  • Quick start

    • Demo

  • Configuration details

    • MCP server config file

      • Format

      • Modes

    • The LLM (Claude) config file

• Logging

  • Log File Locations

  • Log Features

  • Enabling File Logging

• Further Documentation

• Additional Information

Introduction

This repo provides an Model Context Protocol (MCP) server for easing LLM integration with Dremio. If you are new to MCP and MCP Servers take our Dremio MCP Server course on Dremio University (DremioU). If you are familiar with these concepts already please proceed below.

Installation

The Dremio MCP server can be deployed in two ways:

Remote / Streaming HTTP Deployment

For production deployments in Kubernetes environments, use the Helm chart:

📦 Helm Chart Documentation

Quick Start with Helm

Key Features

• ✅ OAuth + External Token Provider authentication (recommended for production)

• ✅ Streaming HTTP mode for web-based deployments

• ✅ Horizontal Pod Autoscaling for scalability

• ✅ Prometheus metrics integration

• ✅ Ingress support with TLS/SSL

• ✅ Security best practices (non-root, read-only filesystem)

Documentation

• Helm Chart README - Complete installation and configuration guide

• Authentication Guide - OAuth + External Token Provider implementation

• Example Configurations - Production and development examples

Local Installation (Desktop/Development)

The MCP server runs locally on the machine that runs the LLM frontend (eg Claude). The installation steps are simple:

1. Clone or download this repository.

2. Install the uv package manager (note that the MCP server requires python 3.11 or later)

• If you install this for the first time, restart your terminal at the end of the install

3. Ensure that you have python installed by running the command below. It should show python 3.11 or later (If you don't have python installed, follow the instructions here OR simply run uv python install)

4. Do a sanity check by running the command and validating the output as shown below.

Initial setup

There are two configurations necessary before the MCP server can be invoked.

1. The server config file: This will cover the details of connecting and communicating with Dremio

2. The LLM config file: This covers configuring the LLM desktop app (Claude for now) to make it aware of the MCP server

Quick start

The quickest way to do this setup is -

1. Create the dremio config file as outlined below and be prepared with these values

Note: the uri is api endpoint associated with your environment:

• For Dremio cloud based in the US region (https://app.dremio.cloud) use https://api.dremio.cloud or use the short hand prod

• For Dremio cloud based in the EMEA region (https://app.eu.dremio.cloud) use https://api.eu.dremio.cloud or use the short hand prodemea

• For SW/K8S deployments use https://<coordinator‑host>:<9047 or custom port>

Note: For security purposes, if you don't want the PAT to leak into your shell history file, create a file with your PAT in it and give it as an argument to the dremio config.

Example:

2. Download and install Claude Desktop (Claude)

Note: Claude has system requirements, such as node.js, please validate your system requirements with Claude official documentation.

3. Create the Claude config file using

4. Validate the config files using

You are done!. You can start Claude and start using the MCP server

Demo (Local install)

The rest of the documentation below provides details of the config files

Configuration details

MCP server config file

This file is located by default at $HOME/.config/dremioai/config.yaml but can be overriden using the --cfg option at runtime for dremio-mcp-server

Format

Modes

There are 3 modes

1. FOR_DATA_PATTERNS - the normal mode where MCP server will allow LLM to look at tables and data to allow pattern discovery and other use cases

2. FOR_SELF - a mode which allows the MCP server to introspect Dremio system, including workload analysis and so on.

3. FOR_PROMETHEUS - a mode that allow MCP server to connect to your prometheus setup, if one exists, to enhance insights with Dremio related metrics

Multiple modes can be specified with separated by ,

The LLM (Claude) config file

Note: This is applicable only for local installs

To setup the Claude config file (refer to this as an example) edit the Claude desktop config file

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

• Windows: %APPDATA%\Claude\claude_desktop_config.json

And then add this section

This will pickup the default location of MCP server config file. It can also be passed in the args section above as "--config-file", "<custom config file>" after run

Logging

The Dremio MCP server automatically writes log files to platform-specific directories following operating system conventions. This helps with troubleshooting and monitoring the server's operation.

Log File Locations

The log files are stored in the following locations based on your operating system:

Linux

• Directory: ~/.local/share/dremioai/logs/

• Full path: ~/.local/share/dremioai/logs/dremioai.log

• XDG compliance: Respects $XDG_DATA_HOME environment variable if set

macOS

• Directory: ~/Library/Logs/dremioai/

• Full path: ~/Library/Logs/dremioai/dremioai.log

Windows

• Directory: %LOCALAPPDATA%\dremioai\logs\

• Full path: %LOCALAPPDATA%\dremioai\logs\dremioai.log

• Typical location: C:\Users\<username>\AppData\Local\dremioai\logs\dremioai.log

Controlling File Logging

By default, the MCP server logs to the logfile mentioned above. To control it further, you can use the following environment variables and command line options:

1. Use JSON format: JSON_LOGGING=1 or pass --enable-json-logging for structured JSON logs

2. Disable file logging: pass --no-log-to-file to disable writing logs to file

Example:

The log directory is automatically created if it doesn't exist, so no manual setup is required.

Further Documentation

1. Architecture: Detailed overview of the Dremio MCP server architecture, including component interactions and data flows.

2. Tools: Comprehensive guide to available tools, including:

   • Tool categories and types

   • Usage examples

   • Development guidelines

   • Integration support

3. Settings: Complete configuration reference covering:

   • Dremio connection settings

   • Tool configurations

   • Framework integrations

   • Environment variables

4. Remote HTTP streaming / Helm Chart

Additional Information

This repository is intended to be open source software that encourages contributions of any kind, like adding features, reporting issues and contributing fixes. This is not a part of Dremio product support.

Testing

The project uses pytest for testing. To run the tests:

GitHub Actions automatically runs tests on pull requests and pushes to the main branch.

Contributing

Please see our Contributing Guide for details on:

• Setting up your development environment

• Making contributions

• Code style guidelines

• Documentation requirements

• Running tests