Enables natural language schema queries — explore tables, keys, procedures, and get SQL help fast
io.github.schemacrawler/schemacrawler-ai
https://schemacrawler.github.io
STDIO
No auth required
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
MCP Server transport type - valid values are 'http' or 'stdio', defaulting to 'stdio'.
Database user name. Can be optional depending on the database connection type.
Database user password. Can be optional depending on the database connection type.
JDBC URL for database connection. If this is provided, the server, host, port and database are not used.
SchemaCrawler database plugin, for example, 'sqlserver' or 'sqlite'. Used only if the JDBC URL is not provided.
Database host. Defaults to localhost. Used only if the JDBC URL is not provided.
Database port. Defaults to the default port for the server type. Used only if the JDBC URL is not provided.
Database to connect to (optional). Used only if the JDBC URL is not provided.
How much database metadata to retrieve. Values are 'minimum', 'standard', 'detailed' or 'maximum'.
Logging verbosity level. Values are 'SEVERE', 'WARNING', 'INFO', 'CONFIG', or 'FINE'.
MCP Server tools to exclude, as a comma-separated list.
Where to find authoritative docs and source for schemacrawler-ai.
Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.
Open Agent Studio