SchemaCrawler-AI

Package (oci)

docker run -i --rm -e SCHCRWLR_DATABASE_USER=<YOUR_VALUE> -e SCHCRWLR_DATABASE_PASSWORD=<YOUR_VALUE> -e SCHCRWLR_JDBC_URL=<YOUR_VALUE> -e SCHCRWLR_ADDITIONAL_CONFIG=<YOUR_VALUE> schemacrawler/schemacrawler-ai:18.0.2-1

Or add to your MCP client config:

{
  "mcpServers": {
    "schemacrawler-ai": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SCHCRWLR_DATABASE_USER=<YOUR_VALUE>",
        "-e",
        "SCHCRWLR_DATABASE_PASSWORD=<YOUR_VALUE>",
        "-e",
        "SCHCRWLR_JDBC_URL=<YOUR_VALUE>",
        "-e",
        "SCHCRWLR_ADDITIONAL_CONFIG=<YOUR_VALUE>",
        "schemacrawler/schemacrawler-ai:18.0.2-1"
      ]
    }
  }
}

• SCHCRWLR_MCP_SERVER_TRANSPORT — MCP Server transport type - valid values are 'http' or 'stdio', defaulting to 'stdio'.
• SCHCRWLR_DATABASE_USER secret — Database user name. Can be optional depending on the database connection type.
• SCHCRWLR_DATABASE_PASSWORD secret — Database user password. Can be optional depending on the database connection type.
• SCHCRWLR_JDBC_URL secret — Optional JDBC URL for database connection. If nonblank, server, host, port, and database are ignored. Credentials may still be supplied separately.
• SCHCRWLR_SERVER — SchemaCrawler database connector identifier, for example, 'sqlserver' or 'sqlite'. Required if the JDBC URL is blank or unset.
• SCHCRWLR_HOST — Database host. Defaults to the connector's host default. Used only if the JDBC URL is blank or unset.
• SCHCRWLR_PORT — Database port. Valid decimal values from 1024 through 65535 are used; otherwise the connector's default port is retained. Used only if the JDBC URL is blank or unset.
• SCHCRWLR_DATABASE — Optional database name or connector-specific database value. Used only if the JDBC URL is blank or unset.
• SCHCRWLR_DATABASE_ALIAS — Optional stable alias used to identify this database server in MCP instructions and tool results.
• SCHCRWLR_DATABASE_DESCRIPTION — Optional description of this database server, included in MCP instructions and the about_database response.
• SCHCRWLR_INFO_LEVEL — How much database metadata to retrieve: 'minimum', 'standard', 'detailed', or 'maximum'. Defaults to 'standard'; unset or unrecognized values also use 'standard'.
• SCHCRWLR_LOG_LEVEL — Java logging level. Defaults to 'INFO'. Java logging names such as 'SEVERE', 'WARNING', 'INFO', 'CONFIG', 'FINE', 'FINER', 'FINEST', 'ALL', and 'OFF', and numeric levels are accepted.
• SCHCRWLR_EXCLUDE_TOOLS — MCP Server tools to exclude, as a comma-separated list.
• SCHCRWLR_OFFLINE_DATABASE — Optional path to a serialized offline catalog snapshot. When set, catalog loading uses this snapshot.
• SCHCRWLR_ADDITIONAL_CONFIG secret — Additional SchemaCrawler configuration encoded as a JSON object. Invalid JSON logs a warning and uses empty additional configuration; do not include secrets.