Chinook MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHINOOK_DB_PATH | No | Set to any SQLite file to use your own database instead of the bundled Chinook sample database. |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_tablesA | List every table in the database with its row count. |
| describe_tableB | Show a table's columns, primary key, foreign keys and row count. |
| sample_rowsB | Return the first few rows of a table to show what its data looks like. |
| run_queryA | Run one read-only SQL query (SQLite dialect) and return the rows. Only SELECT and WITH ... SELECT statements are accepted. At most |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| schema | CREATE statements for every table and index in the database. |
TDQS
Scored across 4 tools
list_tables (inventory), describe_table (schema detail), and sample_rows (data preview) are clearly distinct discovery tools. run_query overlaps somewhat with sample_rows since a preview could be achieved via a limited SELECT, but the read-only arbitrary-query purpose is still recognizable.
All four names follow a consistent verb_noun snake_case pattern (run_query, list_tables, describe_table, sample_rows). The convention is uniform and immediately readable.
Four tools is a tight, well-scoped set for a read-only database explorer, and each tool serves a distinct discovery or query step. It is on the lean side, but nothing feels redundant or missing for the stated scope.
For a read-only exploration surface, discovery (list, describe, sample) plus arbitrary querying covers the main lifecycle. Writes are intentionally excluded, though there is no way to search for a table/column by name or inspect indexes, which would be minor conveniences.