WarpGBM — Claude Code MCP server: what it does, how to install
WarpGBM trains gradient boosting models and runs inference directly from your assistant, exporting results to ONNX or joblib.
no license 678 installs updated 2025-10-17
claude mcp add --transport http warpgbm-mcp https://warpgbm-mcp--jefferythewind.run.toolsWhat WarpGBM does
The server connects to your coding assistant over HTTP to handle gradient boosting workloads. It accepts tabular data in CSV or Parquet formats via upload_data, converting raw files into feature and target matrices ready for training. The train tool outputs portable ONNX or joblib artifacts using either the warpgbm or lightgbm backend.
Fresh training runs yield a temporary artifact_id that remains valid for 5 minutes, so immediate predictions with predict_from_artifact must run before that window closes. Other utilities include get_agent_guide for usage tips and submit_feedback for reporting issues.
What it helps with
- train gradient boosting models on lightgbm or warpgbm engines
- parse CSV or Parquet files into training matrices
- export models into portable ONNX or joblib formats
- run quick predictions using temporary artifact identifiers
Example prompts for the agent
- Parse data from
train.parquetinto feature arrays - Train a gradient boosting model with the lightgbm engine and export to ONNX
- Generate inference using the new
artifact_id
How to install WarpGBM
Platform CLI: remote server
claude mcp add --transport http warpgbm-mcp https://warpgbm-mcp--jefferythewind.run.toolsPlatform CLI: remote server
codex mcp add warpgbm --url https://warpgbm-mcp--jefferythewind.run.toolsConfig file
{
"mcpServers": {
"warpgbm": {
"url": "https://warpgbm-mcp--jefferythewind.run.tools"
}
}
}Config file
{
"servers": {
"warpgbm": {
"type": "http",
"url": "https://warpgbm-mcp--jefferythewind.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http warpgbm https://warpgbm-mcp--jefferythewind.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about WarpGBM
How do I install WarpGBM in Claude Code?
Run claude mcp add --transport http warpgbm-mcp https://warpgbm-mcp--jefferythewind.run.tools in your terminal.
Which ML model engines are available?
The server supports warpgbm and lightgbm via the list_models tool.
How long is the trained artifact ID valid?
The artifact_id stays valid for 5 minutes right after training finishes.