Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HUE_HOST | Yes | Hue server URL (e.g., https://hue.example.com) | |
| HUE_PASSWORD | Yes | Password for Hue authentication | |
| HUE_USERNAME | Yes | Username for Hue authentication | |
| HUE_VERIFY_SSL | No | Verify SSL certificates (default: true) | true |
| HUE_SSL_WARNINGS | No | Show SSL warnings (default: false) | false |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| hue_execute_query | Execute a SQL query on Hue and return the results. This tool executes a SQL statement, waits for completion, and fetches all results.
Use this for SELECT queries where you want to retrieve data.
Args:
statement: The SQL statement to execute (e.g., "SELECT * FROM table LIMIT 100")
dialect: SQL dialect to use - 'hive', 'sparksql', or 'impala' (default: 'hive')
timeout: Maximum time to wait for query completion in seconds (default: 300)
batch_size: Number of rows to fetch per batch for pagination (default: 1000)
Returns:
QueryResult with headers, rows, and row_count |
| hue_run_query_to_csv | Execute a SQL query and save results directly to a CSV file. This is a convenience method that combines query execution with CSV export.
Ideal for exporting large result sets to files.
Args:
statement: The SQL statement to execute
filename: Output CSV filename (default: 'results.csv')
dialect: SQL dialect - 'hive', 'sparksql', or 'impala' (default: 'hive')
batch_size: Number of rows to fetch per batch (default: 1000)
Returns:
OperationResult indicating success and the output filename |
| hue_export_and_download | Execute an INSERT OVERWRITE DIRECTORY query and download the results. This tool is for queries that write output to HDFS (like INSERT OVERWRITE DIRECTORY),
then downloads the resulting files to the local filesystem.
Args:
statement: SQL statement with INSERT OVERWRITE DIRECTORY
hdfs_directory: The HDFS directory where results are written
local_directory: Local directory to download files to (default: '.')
dialect: SQL dialect - 'hive', 'sparksql', or 'impala' (default: 'hive')
file_pattern: Optional regex pattern to filter files to download
timeout: Maximum wait time in seconds (default: 300)
Returns:
OperationResult with list of downloaded files in message |
| hue_list_directory | List files and directories in an HDFS path. Use this to browse the contents of HDFS directories.
Args:
directory_path: The HDFS directory path (e.g., '/user/data', '/tmp')
page_size: Maximum number of items to return (default: 1000)
Returns:
DirectoryListing with path, items, and total_count |
| hue_check_directory_exists | Check if a directory exists in HDFS. Args:
directory_path: The HDFS directory path to check
Returns:
True if the directory exists, False otherwise |
| hue_download_file | Download a single file from HDFS. Args:
remote_path: The full path to the file in HDFS
local_filename: Local filename to save as (optional, defaults to original name)
Returns:
OperationResult with the local filename where file was saved |
| hue_download_directory | Download all files from an HDFS directory. Args:
directory_path: The HDFS directory path to download from
local_directory: Local directory to save files to (default: '.')
file_pattern: Optional regex pattern to filter files (e.g., '.*\.csv')
Returns:
OperationResult with list of downloaded files |
| hue_upload_file | Upload a local file to HDFS. Args:
local_file_path: Path to the local file to upload
hdfs_destination: Destination directory in HDFS
Returns:
OperationResult indicating success |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |