io.github.schemacrawler/schemacrawler-ai

Provides database environment and server configuration metadata, including engine type and version, collation, encoding, parameters, capabilities, and platform details. Adapts output to the specific database (such as Oracle, SQL Server, PostgreSQL and so on) to support platform-aware SQL generation and schema analysis.

Generates detailed documentation for relationships in the ER model, including 1..1, 1..M, M..N and optional relationships. Supports regular expression based relationship name filtering to optimize tool performance. Returns conceptual ER-model relationships. For raw physical schema details such as columns, constraints, and DDL, use `describe_tables`. Returns data as a JSON object.

Generates detailed documentation for database routines (stored procedures and functions), including parameter metadata (input/ output parameters, data types, default values), return types, dependencies (on tables, views, or other routines), and full DDL definitions. Supports regular expression based routine name filtering and configurable detail levels to optimize tool performance. Returns data as a JSON object.

Generates detailed documentation for database tables and views, including column definitions (names, data types, constraints, nullability), primary and foreign key relationships, index and trigger information, table attributes, and complete DDL definitions. Supports regular expression based table name filtering and configurable detail levels to optimize tool performance. Includes entity type information, such as whether the table is a strong or weak entity, a sub-entity, or a bridge-table. For relationship cardinality and other ER relationship concepts, use `describe_er_relationships`. Returns data as a JSON object.

Returns communities or clusters of related tables and views. Communities can be selected by a regular expression matching any member's fully qualified name. Each community includes its full names of the tables in the community, and the anchor table.

Generates a database diagram in the specified format.

Analyzes and validates database schema structure and design. Detects missing or redundant indexes, foreign keys without supporting indexes, and unique indexes with nullable columns. Checks data type consistency across similarly named columns, validates key patterns, and enforces naming conventions. Assesses design quality by inspecting documentation completeness, reserved word usage, and structural anomalies like single-column or all-nullable tables. Returns data as a JSON object.

Makes an inventory of database schema objects such as tables, views, stored procedures, functions, sequences, synonyms, and more. This is an essential starting point for database exploration, database asset management, and schema analysis. The tool supports object type filtering and pattern-based searching. Use `list_members_of_tables` instead when you need columns, indexes, foreign keys, or triggers belonging to one or more tables. Returns JSON data.

Lists members belonging to one or more database tables across the schema, including columns, indexes, foreign keys, and triggers. Use this tool when you need members belonging to one or more tables, not when you need to discover tables or other schema objects; use `list` for that. Supports regular expression based table and member name filtering. For complete physical table details, use `describe_tables`. Returns JSON data.

Gets the SchemaCrawler AI MCP Server version and uptime status.

Returns schema graph importance metrics, composite scores, counts, and traits for tables and views to identify key entities and structural hubs. The entry for each table includes: 1) Importance score: composite integer (0-100) combining structural graph metrics (50%) and data-modeling attributes (50%) 2) Importance metrics: graph topology metrics including in-degree, out-degree, betweenness centrality, and "impact reachability count"(blast radius for changes to the table) 3) Table counts: Attribute column (columns with data values) count, total column_count, and foreign key, index, trigger, and row counts 4) Table traits: Entity model type (strong entity, weak entity, subtype, bridge table, non entity) and boolean flags for whether primary_keys, foreign keys, indexes, has triggers are present, and whether the table has data Returns data as a JSON object.

Finds the shortest forward dependency path from a source table or view to a target table or view in the schema graph. Requires source table name and target table name, each specified as a regular expression matching a fully qualified table or view name (each must resolve to exactly one match). Foreign-key relationships are preferred; implied associations (from column name matching) are used as a fallback. Searches are limited to 5 relationship hops by default; use `max_path_depth` to select another limit. A -1 value allows an unlimited search. Returns an ordered array of fully qualified table or view names representing the step-by-step dependency chain from source to target and a boolean flag indicating whether implied associations (implicit relationships) were required to complete the path. Returns a JSON object.

Profiles and samples table data by retrieving random rows for quick content analysis without full scans. Helps infer data patterns, validate types, and assess quality. Results vary per run (they are random picks) and offer insight for ETL, query design, and pipeline planning. Returns data as a JSON object.