Create a draft experiment
create_experimentCreate an A/B test as a DRAFT: nobody sees it until start_experiment. 2 to 4 arms, each pointing at a paywall or onboarding flow of this app on the experiment's surface (ids from list_surfaces); one arm may be a holdout with no target (it keeps the live config). Exactly one control; the first arm when none is marked. Defaults: mode notify (report the winner, don't ship it), new users only, the default placement, trial_started as the metric. Only works when the app allows MCP writes.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"name": "<name>",
"surface": "<surface>",
"variants": "<variants>"
},
"name": "create_experiment"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | notify (default) reports a winner; auto ships it | |
| name | Yes | ||
| is_qa | No | A QA run on test builds. Default false | |
| surface | Yes | ||
| priority | No | Enrollment order, lowest first. Default 100 | |
| variants | Yes | ||
| placement | No | Placement id (letters, digits, _ or -). Default `default` | |
| targeting | No | Who is eligible; every rule must pass, {} = everyone. Keys: countries (ISO-2), platforms (ios, android, web), app_version_min/max, days_since_install_min/max, billing_states, custom | |
| enrollment | No | Default new: users first seen after the start | |
| hypothesis | No | What you expect to happen and why | |
| audience_pct | No | % of eligible users enrolled. Default 100 | |
| min_confidence | No | Chance to be best a winner needs. Default 0.95 | |
| primary_metric | No | Default trial_started | |
| experiment_type | No | A label. Default other |