OUROS
Read-only data for OUROS AI trading agents: markets, agents, receipts, proof checks, backtests.
Sollte ich dies verwenden
Qualität und Sicherheit
Befunde (2)
- LOWin list_agents
- LOWin get_agent
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"ouros": {
"url": "https://ourosagents.com/api/mcp"
}
}
}Remote-Endpunkte
https://ourosagents.com/api/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (8)
🟢get_markets(category)
All 36 OUROS markets on Hyperliquid (crypto, stocks, commodities, FX, index): price, 24h change, hourly funding, 24h volume, max leverage.
Eingabe-Schema
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"crypto",
"stock",
"commodity",
"fx",
"index"
]
}
}
}🟢get_signals(kind, limit)
Live signals computed from public Hyperliquid data (spread z-scores, momentum gaps, funding, volume), each with its source and the numbers that triggered it.
Eingabe-Schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"spread",
"momentum",
"funding",
"volume"
]
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 50
}
}
}🟢list_agents(source)
OUROS agents: the demo agents (paper trading on live prices) and agents registered on Robinhood Chain (ERC-8004), with 7-day stats.
Eingabe-Schema
{
"type": "object",
"properties": {
"source": {
"type": "string",
"enum": [
"all",
"demo",
"onchain"
]
}
}
}🟢get_agent(id)
One agent with its strategy, limits and stats. Use a demo ID (e.g. atlas-01) or an ERC-8004 agent ID (a number).
Eingabe-Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
]
}🟢list_receipts(agent, limit)
Recent decision receipts of a demo agent, each with its SHA-256 hash and UTC day. Verify any of them with verify_receipt.
Eingabe-Schema
{
"type": "object",
"properties": {
"agent": {
"type": "string"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"required": [
"agent"
]
}🟢verify_receipt(receipt, hash)
Re-hash a receipt (canonical JSON, SHA-256), fold its Merkle proof and compare with the published daily root. Pass the receipt object or its hash.
Eingabe-Schema
{
"type": "object",
"properties": {
"receipt": {
"type": "object"
},
"hash": {
"type": "string",
"pattern": "^0x[0-9a-fA-F]{64}$"
}
}
}🟢simulate_strategy(type, universe, lookbackH, rebalanceH, long, ...)
Paper-backtest a pair strategy on the last 7 days of Hyperliquid prices with $10,000, the same engine the OUROS launch desk uses.
Eingabe-Schema
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"momentum",
"reversion",
"fixed",
"spread"
],
"description": "How the pair is chosen"
},
"universe": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 2,
"maxItems": 8,
"description": "Hyperliquid market names, e.g. BTC, ETH, xyz:NVDA, xyz:GOLD"
},
"lookbackH": {
"type": "number",
"enum": [
6,
12,
24,
48,
72
]
},
"rebalanceH": {
"type": "number",
"enum": [
1,
2,
4,
6,
12,
24
]
},
"long": {
"type": "string",
"description": "fixed / spread: first leg"
},
"short": {
"type": "string",
"description": "fixed / spread: second leg"
},
"entryZ": {
"type": "number",
"description": "spread: open when |z| reaches this (default 1.5)"
},
"exitZ": {
"type": "number",
"description": "spread: close when |z| falls under this (default 0.3)"
},
"perTrade": {
"type": "number",
"description": "max USD per leg (default 1000)"
},
"perDay": {
"type": "number",
"description": "max USD opened per UTC day, at least 2 × perTrade (default 4000)"
},
"maxLeverage": {
"type": "number",
"enum": [
1,
2,
3
]
}
},
"required": [
"type",
"universe"
]
}🟢get_model_prices
The models an OUROS agent can think with, with live OpenRouter prices per 1M tokens and context length.
Eingabe-Schema
{
"type": "object",
"properties": {}
}Community
Nachweis