Redshift MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDSHIFT_HOST | Yes | The Redshift host address | |
| REDSHIFT_PORT | No | The Redshift port number | 5432 |
| REDSHIFT_USER | Yes | The Redshift username | |
| REDSHIFT_DATABASE | Yes | The Redshift database name | |
| REDSHIFT_PASSWORD | Yes | The Redshift 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 |
|---|---|
| redshift_queryC | |
| redshift_list_tablesC | |
| redshift_describe_tableB | |
| redshift_get_sample_dataC | |
| redshift_connection_statusB | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_tables_resource | List of available tables in the public schema. |
| get_status_resource | Current Redshift connection status. |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose with no overlap: connection status check, table description, data sampling, table listing, and query execution. The descriptions make it unambiguous which tool to use for each database interaction task.
All tools follow a perfect 'redshift_verb_noun' pattern with consistent snake_case throughout. The naming convention is predictable and immediately communicates both the domain (Redshift) and the specific action.
Five tools is well-scoped for a database server, covering essential operations without bloat. Each tool earns its place by addressing a core database interaction need, from metadata exploration to data querying.
The toolset covers the most critical database operations well: schema exploration (list_tables, describe_table), data access (get_sample_data, query), and system status. The main gap is the lack of write/update operations (CREATE, INSERT, UPDATE, DELETE), though this might be intentional for a read-focused server.