Search and list database objects (schemas, tables, columns, procedures, functions, indexes) with pattern matching. This unified tool supports both targeted searches and browsing all objects, implementing progressive disclosure to minimize token usage.Documentation Index
Fetch the complete documentation index at: https://dbhub.ai/llms.txt
Use this file to discover all available pages before exploring further.
Parameters
object_type(required): Type of object to search -"schema","table","column","procedure","function", or"index"pattern(optional): Search pattern using SQL LIKE syntax (%for wildcard,_for single character). Defaults to"%"(match all)schema(optional): Filter results to a specific schemadetail_level(optional): Level of detail -"names"(default),"summary", or"full"limit(optional): Maximum results to return (default: 100, max: 1000)
Detail Levels
Examples
Pattern Syntax
Use SQL LIKE pattern syntax for flexible matching:%- Matches any sequence of characters_- Matches exactly one character- Case-insensitive matching
user%→ Matches “users”, “user_profiles”, “user_sessions”%_id→ Matches “user_id”, “order_id”, “product_id”test_→ Matches “test_1”, “test_a” (but not “test_10”)%user%→ Matches “users”, “user_profiles”, “app_users”
Token Efficiency
This tool can reduce token usage by 90-99% compared to listing all objects:| Scenario | Traditional Approach | Search Approach | Token Savings |
|---|---|---|---|
| Find “users” table in 500 tables | List all (full) | Search (names) | 99% |
| Explore table structure | List all tables first | Search + drill down | 95% |
| Find ID columns | Load all schemas | Search columns | 85% |
Table and Column Comments
When usingdetail_level: "summary" or "full", the tool includes database comments/descriptions if they exist. This helps LLMs understand the purpose of tables and columns, especially in complex or legacy databases.
- Table comments appear as the
commentfield on table results (summary and full levels) - Column descriptions appear as the
descriptionfield on each column (full level only) - Fields are omitted when no comment is set, keeping responses token-efficient
| Database | Table Comments | Column Comments |
|---|---|---|
| PostgreSQL | COMMENT ON TABLE | COMMENT ON COLUMN |
| MySQL | ALTER TABLE ... COMMENT | ALTER TABLE ... MODIFY COLUMN ... COMMENT |
| MariaDB | ALTER TABLE ... COMMENT | ALTER TABLE ... MODIFY COLUMN ... COMMENT |
| SQL Server | sp_addextendedproperty (MS_Description) | sp_addextendedproperty (MS_Description) |
| SQLite | Not supported | Not supported |
Usage Patterns
The tool supports all three detail levels (
names, summary, full) and works seamlessly with multi-database configurations. Results are limited by the limit parameter (default: 100, max: 1000) to prevent excessive token usage.