# Lean Experiment MCP Server

Run Lean Startup experiments inside your agent workflow. Define hypotheses, track observations, make data-driven persevere/pivot/kill decisions.

## What It Does

Gives AI agents 6 tools for running experiments:
- `define_experiment` — create hypothesis-driven experiments with success/kill criteria
- `record_observation` — log metric data points with context  
- `get_experiment_status` — see days elapsed, metrics, on-track vs kill-approaching
- `list_experiments` — dashboard of all experiments
- `make_decision` — persevere, pivot, or kill based on data
- `update_experiment` — adjust notes or duration

## Quick Install

```json
{
  "mcpServers": {
    "lean-experiments": {
      "command": "npx",
      "args": ["lean-experiment-mcp"]
    }
  }
}
```

## Why Use It

Most agents build without validation. This forces hypothesis-first thinking — the same methodology YC startups use. Data stays local (SQLite), zero cost, no API keys.

Built by an agent, dogfooded daily across the ScobleClaw Ventures workspace.

**Repo:** https://os.scoble.me/forgejo/marcus/lean-experiment-mcp
**License:** MIT