Cloudera Iceberg MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IMPALA_HOST | Yes | The Impala host (e.g., coordinator-default-impala.example.com) | |
| IMPALA_PORT | Yes | The Impala port (e.g., 443) | |
| IMPALA_USER | Yes | The Impala username | |
| MCP_TRANSPORT | No | The MCP transport protocol (stdio, http, or sse) | stdio |
| IMPALA_DATABASE | Yes | The Impala database name (e.g., default) | |
| IMPALA_PASSWORD | Yes | The Impala password |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_queryC | Execute a SQL query on the Impala database and return results as JSON. |
| get_schemaA | Retrieve the list of table names in the current Impala database. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: execute_query runs SQL queries and returns results, while get_schema retrieves metadata about table names. There is no overlap in functionality or ambiguity about when to use each tool.
Both tools follow a consistent verb_noun naming pattern (execute_query, get_schema) with clear action-object relationships. The naming style is uniform throughout the set.
With only 2 tools for a database/query server, the surface feels severely limited. While the tools cover basic query execution and schema inspection, typical database operations like table creation, data manipulation, or metadata exploration beyond table names are missing, making this feel under-scoped.
For an Impala/Cloudera Iceberg database server, the toolset is significantly incomplete. There are no tools for creating/dropping tables, inserting/updating data, managing partitions, or accessing detailed schema information beyond table names. This creates dead ends for agents trying to perform common database operations.