Dremio Python MCP
Description
# Dremio Model-Context Protocol (MCP) This project implements a Model-Context Protocol (MCP) server for Dremio. It provides a standardized way to interact with Dremio databases through the MCP. ## Features ### Resources Exposes Dremio data through **Resources**: *…
About
# Dremio Model-Context Protocol (MCP) This project implements a Model-Context Protocol (MCP) server for Dremio. It provides a standardized way to interact with Dremio databases through the MCP. ## Features ### Resources Exposes Dremio data through **Resources**: * `dremio://catalogs` - Lists all catalogs *…
Details
- Author
- ucesys
- Downloads
- 243
- Categories
- Other
Jump to
- Exposes Dremio catalogs, schemas, and tables as MCP Resources.
- Tools: list_catalogs, list_schemas, list_tables, execute_sql.
- SQL validation prevents non-read-only queries.
- Input validation protects against SQL injection.
- Supports username/password and token authentication.
- TLS support for secure communication.
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 Python MCPCommand (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 the package with pip install -e . or uv pip install -e .. Create a config.yaml file or set environment variables for Dremio connection details. Run the server with mcp-dremio-server or python run_mcp_server.py. Add the server configuration to your MCP client (e.g., Claude) using the provided JSON snippet.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"dremio python mcp": {
"dremio-mcp": {
"command": "mcp-dremio-server",
"args": []
}
}
}
}McpServers
{
"dremio-mcp": {
"command": "mcp-dremio-server",
"args": []
}
}Dremio Model-Context Protocol (MCP)
This project implements a Model-Context Protocol (MCP) server for Dremio. It provides a standardized way to interact with Dremio databases through the MCP.
Features
Resources
Exposes Dremio data through Resources:
dremio://catalogs - Lists all catalogs
dremio://schemas/{catalog} - Lists all schemas in a catalog
dremio://tables/{catalog}/{schema} - Lists all tables in a schema
dremio://schema/{table_name} - Gets schema information for a table
Tools
list_catalogs
Lists all available catalogs in Dremio
Usage: list_catalogs()
list_schemas
Lists all schemas in a specific catalog
Usage: list_schemas("catalog_name")
list_tables
Lists all tables in a specific schema
Usage: list_tables("catalog_name", "schema_name")
execute_sql
Executes a SQL query against Dremio
Returns results in a structured format with metadata
Usage: execute_sql("SELECT FROM catalog.schema.table LIMIT 10")
Requirements
Python 3.10+
Dremio instance (Cloud or Software)
PyArrow with Flight support
Installation
Using pip
pip install -e .
Using uv (recommended)
# Install uv if you don't have it
curl -sSf https://astral.sh/uv/install.sh | bash
Install the package
uv pip install -e .
Configuration
Create a config.yaml file in the root directory with the following configuration:
# Dremio connection settings
dremio:
# Connection type: 'software' for Dremio Software or 'cloud' for Dremio Cloud
type: software
# Dremio Software connection details
software:
hostname: localhost
port: 32010
username: your_username
password: your_password
use_ssl: false
Query settings
query:
# Maximum number of rows to return in a query result
max_rows: 10000
# Maximum number of columns to return in schema request
max_columns: 1000
# Timeout in seconds for query execution
timeout: 300
Environment Variables
You can also configure the server using environment variables:
DREMIO_HOSTNAME=localhost
DREMIO_PORT=32010
DREMIO_USERNAME=your_username
DREMIO_PASSWORD=your_password
DREMIO_USE_SSL=false
For Dremio Cloud:
DREMIO_TYPE=cloud
DREMIO_ENDPOINT=data.dremio.cloud
DREMIO_PAT_TOKEN=your_personal_access_token
Usage
Running the Server
# If installed from package
mcp-dremio-server
Or run directly
python run_mcp_server.py
Integration with Claude or Other MCP Clients
Add the following configuration to your MCP client settings:
MacOS
// ~/Library/Application\ Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"dremio_service": {
"command": "/Users/USERNAME/.local/bin/uv",
"args": [
"--directory",
"/Users/USERNAME/PycharmProjects/dremio-python-mcp",
"run",
"run_mcp_server.py"
]
}
}
}
Windows
// %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"dremio-mcp": {
"command": "mcp-dremio-server",
"args": []
}
}
}
Example Usage
Listing Catalogs and Schemas
// List all catalogs
list_catalogs()
// List schemas in a catalog
list_schemas("my_catalog")
// List tables in a schema
list_tables("my_catalog", "my_schema")
Executing SQL Queries
// Execute a query
results = execute_sql("SELECT FROM my_catalog.my_schema.my_table LIMIT 10")
Security Features
SQL Validation: Prevents execution of non-read-only queries
Input Validation: Prevents SQL injection via table/schema names
TLS Support: Secure communication with Dremio
Authentication: Support for username/password and token authentication
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, use the MCP Inspector:
npx @modelcontextprotocol/inspector mcp-dremio-server
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
