schemacrawler-ai

Enables natural language schema queries — explore tables, keys, procedures, and get SQL help fast

stdio vv17.7.0-1

Connection Configuration

Add this to your AI agent's MCP config file to connect.

Run in your terminal:

claude mcp add io.github.schemacrawler--schemacrawler-ai -- docker

Transport

stdio

Authentication

None

Version

vv17.7.0-1

Server Name

io.github.schemacrawler/schemacrawler-ai

Last Updated

Mar 6, 2026

How to install and connect this MCP server.

Environment variables you must provide when running this server.

Variable	Description	Required
`SCHCRWLR_MCP_SERVER_TRANSPORT`	MCP Server transport type - valid values are 'http' or 'stdio', defaulting to 'stdio'.	Optional
`SCHCRWLR_DATABASE_USER` secret	Database user name. Can be optional depending on the database connection type.	Optional
`SCHCRWLR_DATABASE_PASSWORD` secret	Database user password. Can be optional depending on the database connection type.	Optional
`SCHCRWLR_JDBC_URL`	JDBC URL for database connection. If this is provided, the server, host, port and database are not used.	Optional
`SCHCRWLR_SERVER`	SchemaCrawler database plugin, for example, 'sqlserver' or 'sqlite'. Used only if the JDBC URL is not provided.	Optional
`SCHCRWLR_HOST`	Database host. Defaults to localhost. Used only if the JDBC URL is not provided.	Optional
`SCHCRWLR_PORT`	Database port. Defaults to the default port for the server type. Used only if the JDBC URL is not provided.	Optional
`SCHCRWLR_DATABASE`	Database to connect to (optional). Used only if the JDBC URL is not provided.	Optional
`SCHCRWLR_INFO_LEVEL`	How much database metadata to retrieve. Values are 'minimum', 'standard', 'detailed' or 'maximum'.	Optional
`SCHCRWLR_LOG_LEVEL`	Logging verbosity level. Values are 'SEVERE', 'WARNING', 'INFO', 'CONFIG', or 'FINE'.	Optional
`SCHCRWLR_EXCLUDE_TOOLS`	MCP Server tools to exclude, as a comma-separated list.	Optional