export_model
Export trained models from Tuning Engines cloud storage to your AWS S3 bucket for local deployment and control.
Instructions
Export a trained model from Tuning Engines cloud storage to your S3 bucket.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model_id | Yes | Model ID (UUID) to export | |
| s3_bucket | Yes | Destination S3 bucket name | |
| s3_prefix | No | Optional S3 key prefix for the exported model | |
| s3_access_key_id | Yes | AWS access key ID | |
| s3_secret_access_key | Yes | AWS secret access key | |
| s3_region | Yes | AWS region (e.g. us-east-1) | |
| delete_after | No | Delete the model from Tuning Engines storage after export (default: false) |
Implementation Reference
- src/client.ts:115-131 (handler)The actual implementation of the export_model logic, calling the API endpoint.
async exportModel( modelId: string, params: { s3_bucket: string; s3_prefix?: string; s3_access_key_id: string; s3_secret_access_key: string; s3_region: string; delete_after?: boolean; } ): Promise<any> { return this.request( "POST", `/api/v1/user_models/${modelId}/export`, params ); } - src/mcp.ts:487-491 (registration)Tool handler registration and argument extraction for export_model in the MCP server implementation.
case "export_model": result = await client.exportModel(args!.model_id as string, { s3_bucket: args!.s3_bucket as string, s3_prefix: args?.s3_prefix as string | undefined, s3_access_key_id: args!.s3_access_key_id as string,