sql-copilot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_tablesA | List all tables and views in the database. Call this first to see what data exists. |
| describe_tableA | Show the columns of one table (name, type, nullable). Use before writing SQL. |
| get_schemaA | Get ALL tables and their columns in one call. Faster than list_tables + describe_table. |
| run_queryA | Run ONE read-only PostgreSQL SELECT query. Returns up to 100 rows. Writes, multiple statements and risky functions are rejected with a reason. If a query fails, read the error message, fix the SQL, and try again. |
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 4 tools
list_tables and get_schema overlap in that both provide table listings, but get_schema also includes column details, making it a superset. describe_table is distinct (columns of a single table), and run_query is clearly separate. The overlap between list_tables and get_schema is the only source of potential confusion, but the descriptions clarify their difference in scope.
All tool names follow a consistent verb_noun pattern: list_tables, describe_table, get_schema, run_query. The verbs are all imperative and the nouns are clear resources or actions. This pattern is predictable and easy to extrapolate.
The server has 4 tools, which is on the lower end but reasonable for a database introspection and querying server. It covers the essential operations without bloat. It might feel slightly thin for a full DB tool, but the scope is clearly read-only querying and inspection, so 4 tools is appropriate.
The tool set covers the main workflow: explore schema (list_tables, get_schema), inspect a table (describe_table), and run queries (run_query). The only minor gap is the lack of a tool to view query history or a more detailed table metadata (e.g., indexes, foreign keys), but these are not essential for basic read-only usage.