autocarver — Claude Code MCP server: install and use
This MCP server lets an AI assistant classify dataset columns and carve them against a target through local tool calls.
claude mcp add autocarver -- uvx autocarverWhat autocarver does
autocarver connects AutoCarver to an MCP-aware coding assistant. Give it a data file and target column; the server identifies feature types, proposes the carving, and returns a summary table. The workflow runs through tool calls, so you do not need to write the setup code by hand.
AutoCarver converts numeric, categorical, and ordinal columns into readable bins. It searches candidate groupings and checks them on held-out data; cv adds cross-validation views during fitting. The MCP process starts locally with uvx autocarver, and the dataset is not sent to AutoCarver or another external service.
The LLM affects the carving result. Have a person review the inferred feature definitions before production use.
What it helps with
- classify columns in a dataset
- carve features against a target column
- return a summary of the resulting bins
- check groupings against held-out data
Example prompts for the agent
- Qualify the columns in
titanic.csvand carve them againstSurvived. - Inspect
data.csv, infer its feature types, and propose bins fortarget. - Process the columns in
train.csvagainst its target and show the summary table.
How to install autocarver
Platform CLI
claude mcp add autocarver -- uvx autocarveruvx runs the command named after the package; if the README names another one, use uvx --from autocarver <command>
Platform CLI
codex mcp add autocarver -- uvx autocarveruvx runs the command named after the package; if the README names another one, use uvx --from autocarver <command>
Config file
{
"mcpServers": {
"autocarver": {
"command": "uvx",
"args": [
"autocarver"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from autocarver <command>
Config file
{
"servers": {
"autocarver": {
"type": "stdio",
"command": "uvx",
"args": [
"autocarver"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from autocarver <command>
Platform CLI
gemini mcp add autocarver uvx autocarveruvx runs the command named after the package; if the README names another one, use uvx --from autocarver <command>
Step 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 autocarver
How do I install autocarver in Claude Code?
Run claude mcp add autocarver -- uvx autocarver.
What does autocarver do?
It exposes AutoCarver through MCP tools so an assistant can classify dataset columns, carve them against a target, and return a summary.
Should I review autocarver's result?
Yes. The LLM influences the carving quality, so a person should confirm the inferred feature definitions before production use.
