warehouse-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | Yes | Required; point it at a read-only role. | |
| MAX_ROW_LIMIT | No | Hard ceiling the caller cannot raise. | 5000 |
| EXPOSED_SCHEMAS | No | Comma-separated list of schemas to expose. | mart |
| DEFAULT_ROW_LIMIT | No | Default row limit for queries. | 200 |
| STATEMENT_TIMEOUT_MS | No | Statement timeout in milliseconds. | 15000 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_tablesA | List every table, view and materialized view available in the mart schema(s), with its description. Call this first — it is cheap and tells you what exists. |
| describe_tableA | Show the columns, types, nullability and column comments for one table or view. Call this before writing a query against a relation you have not queried before. |
| run_queryA | Run a read-only SQL SELECT against the warehouse and return rows as JSON. Only SELECT (and WITH ... SELECT) is permitted; a single statement per call. Results are capped at 200 rows by default and 5000 at most — aggregate in SQL rather than pulling rows and counting them yourself. |
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 3 tools
Each tool targets a distinct concern: discovering relations, inspecting their schema, and executing queries. There is no functional overlap between listing, describing, or querying.
All three tool names follow a consistent verb_noun pattern (list_tables, describe_table, run_query), with clear verbs and direct objects. The naming style is uniform across the set.
Three tools is a well-scoped size for a read-only warehouse server. Each tool is essential for the workflow of exploring and querying data, with no redundancy or excessive surface area.
The toolset fully covers the core lifecycle of read-only data access: discover what exists, understand its schema, and query it. There are no obvious gaps for the stated purpose, and the server's read-only constraint makes additional write/update tools unnecessary.