sql-query-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SQL_QUERY_MCP_CONFIG | No | The absolute path to the connections.json configuration file. Defaults to 'config/connections.json' if not set. | |
| PG_CONN_CRM_PROD_MUQIAO_RO | No | Example PostgreSQL DSN (e.g., postgresql://user:password@host:5432/dbname). The environment variable name must match the 'dsn_env' field in your connections.json. | |
| MYSQL_CONN_CRM_PROD_MUQIAO_RO | No | Example MySQL DSN (e.g., mysql://user:password@host:3306/crm). The environment variable name must match the 'dsn_env' field in your connections.json. |
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_connectionsB | List configured SQL connections by connection_id. |
| list_schemasB | List visible schemas for a PostgreSQL connection. |
| list_databasesB | List visible databases for a MySQL or Hive connection. |
| list_tablesC | List tables and views for a resolved schema or database. |
| describe_tableB | Describe columns, keys, and indexes for a table. |
| run_selectA | Run a read-only SELECT or CTE query. |
| explain_queryB | Run EXPLAIN on a read-only SELECT or CTE query. |
| get_table_sampleC | Fetch a small sample from a table for schema discovery. |
| export_query_fileB | Export a read-only query result to a local CSV or XLSX file. |
| start_queryB | Start an asynchronous read-only SELECT or CTE query. |
| get_queryB | Get asynchronous query status and paginated results when complete. |
| cancel_queryB | Cancel a running asynchronous query. |
| import_table_fileA | Import a local CSV or XLSX file into an existing table. |
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 13 tools
Each tool has a clearly distinct purpose: cancel_query, describe_table, explain_query, etc. The only potentially overlapping pair (run_select and start_query) are distinguished by synchronous vs asynchronous execution, and descriptions make this explicit.
All tools follow a consistent verb_noun pattern in snake_case, e.g., list_connections, run_select, export_query_file. No mixing of styles or ambiguous verb usage.
With 13 tools, the set is well-scoped for a SQL query interface. It covers all necessary operations without being bloated or insufficient.
The tool surface covers schema discovery, synchronous and asynchronous queries, query explanation, export, and import. Minor gaps include lack of a tool to modify queries or view history, but core workflows are well supported.