Dremio MCP server
About
Integrate Large Language Models (LLMs) with the Dremio data lakehouse platform.
Details
- Author
- dremio
- GitHub stars
- 52
- Downloads
- 474
- Categories
- Database, Other, AI
Jump to
- 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)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Dremio MCP serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"dremio mcp server": {
"dremio-mcp": {
"command": "docker",
"args": [
"build",
"-t",
"dremio-mcp:0.1.0",
"."
]
}
}
}
}
McpServers
{
"dremio-mcp": {
"command": "docker",
"args": [
"build",
"-t",
"dremio-mcp:0.1.0",
"."
]
}
}
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
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





