This is the v1 reference. v1 stops answering on November 1, 2026. Build on v2: see where this route went.
Create a strategy
MCP tool: save_strategy
Deploys a rule that survived testing. The strategy records every matching trade from now on and notifies you in a daily digest.
Create-only by design: an agent that can delete or rewrite strategies can destroy an account's history in one confused turn, and there is no undo. Editing stays in the app.
An account holds at most 20 strategies. A rule that names traders counts each one toward the account's 100 different traders a day.
Body parameters
namestringrequiredA short name you will recognise, 1 to 60 characters.
criteriaobjectrequiredThe rule: which trades to include. The same shape a saved strategy uses, so a rule you test is a rule you can deploy without translation.
platformsstring[]Venues to include: "polymarket", "polymarket_us", "kalshi", "hyperliquid", "novig", "prophetx", "gemini". Omit for every venue, which is usually right. See the Venues reference.
categoriesstring[]Market categories: "sports", "politics", "crypto", "finance", "culture". Omit for all.
sportsLeaguesstring[]Leagues, e.g. ["NBA", "NFL"]. Only applies to sports markets. Max 20.
minAmountUsdnumberMinimum trade size in USD. Typical values are 10000 to 50000.
maxAmountUsdnumberMaximum trade size in USD. Must be at least minAmountUsd when both are set.
priceMinnumberMinimum entry price, 0 to 1. 0.75 and up is heavy favourites.
priceMaxnumberMaximum entry price, 0 to 1. 0.20 and below is longshots. Must be at least priceMin when both are set.
eventTypesstring[]How the trade changed the trader's position: "open", "add", "flip", "trim", "close", "unknown". Entries only is ["open", "add", "flip"], which is the usual choice. Trims and closes are exits and never settle, so they cannot be scored.
directionsstring[]Trade direction: "buy_yes", "buy_no", "sell_yes", "sell_no". Only buys are ever scored; sells never resolve.
keywordsstring[]Case-insensitive substrings matched against the market name. Any one matching is enough. Max 10.
excludeLosingTradersbooleanLeave out traders on a losing 90-day record. On unless false. A backtest uses each trader's record today.
backfillbooleandefault: falseClaim matching history immediately so the strategy has a record from day one. Off by default so a clean forward-only run is possible.
backfillDaysintegerdefault: 30How far back a backfill reaches, 1 to 30 days.
defaultStakeUsdnumber | nulldefault: 100Hypothetical stake per bet, staked once on each market and outcome. Pass null explicitly to size every trade at whatever the whale bet.
endsAtstring | nullISO datetime or YYYY-MM-DD. When set, the strategy stops claiming trades and sends a final summary.
Response
backfill is null when backfill was not requested, and { pending: true } when it was: the strategy is created at once and its matching history is written in the background, usually within seconds. Read the strategy's performance to see it.
curl -X POST https://api.rivo.markets/v1/strategies \
-H "Authorization: Bearer rivo_live_..." \
-H "Content-Type: application/json" \
-d '{
"name": "Longshot Hunters",
"criteria": {
"priceMax": 0.2,
"minAmountUsd": 10000,
"eventTypes": [
"open",
"add",
"flip"
]
},
"backfill": true
}'import requests
r = requests.post(
"https://api.rivo.markets/v1/strategies",
headers={"Authorization": "Bearer rivo_live_..."},
json={
"name": "Longshot Hunters",
"criteria": {
"priceMax": 0.2,
"minAmountUsd": 10000,
"eventTypes": ["open", "add", "flip"],
},
"backfill": True,
},
)
print(r.json()["data"])const res = await fetch("https://api.rivo.markets/v1/strategies", {
method: "POST",
headers: {
Authorization: "Bearer rivo_live_...",
"Content-Type": "application/json",
},
body: JSON.stringify({
name: "Longshot Hunters",
criteria: {
priceMax: 0.2,
minAmountUsd: 10000,
eventTypes: ["open", "add", "flip"],
},
backfill: true,
}),
});
const { data } = await res.json();{
"success": true,
"data": {
"id": "b4a4f7a0-4a5e-4e9d-9c1e-2f6d8f3a1c77",
"name": "Longshot Hunters",
"backfill": { "pending": true }
}
}