VARRD

pip install varrd

varrd research "Does buying SPY after a 3-day losing streak actually work?"

varrd research "When VIX spikes above 30, is there a bounce in ES?"

varrd research "Is there a seasonal pattern in wheat before harvest?"

varrd research "What happens to gold when the dollar drops 3 days straight?"

varrd research "Does Bitcoin rally after the halving?"

varrd research "When crude oil drops 5% in a week, what happens next?"

STRONG EDGE — Statistically significant vs both zero and market baseline.

 Direction: LONG
 Win Rate: 62%
 Sharpe: 1.45
 Signals: 247

 Trade Setup:
 Entry: $5,150.25
 Stop Loss: $5,122.00
 Take Profit: $5,192.50
 Risk/Reward: 1:1.5

NO EDGE — Neither test passed. No tradeable signal found.

You found out for 25 cents instead of $25,000 in live losses.

from varrd import VARRD

v = VARRD() # auto-creates free account, $2 in credits

# Research a trading idea
r = v.research("When RSI drops below 25 on ES, is there a bounce?")
r = v.research("test it", session_id=r.session_id)

print(r.context.edge_verdict) # "STRONG EDGE" / "NO EDGE"

# Get exact trade levels
r = v.research("show me the trade setup", session_id=r.session_id)

# What's firing right now across all your strategies?
signals = v.scan(only_firing=True)
for s in signals.results:
 print(f"{s.name}: {s.direction} {s.market} @ ${s.entry_price}")

# Morning briefing — today's news connected to your specific edges
b = v.briefing()
print(b.news)
# "**ES selling accelerates into the open** Three consecutive lower highs..."
# "↳ Your ES mean-reversion setups are live territory here..."

# Let VARRD discover edges autonomously
result = v.discover("mean reversion on futures")
print(result.edge_verdict, result.market, result.win_rate)

# Full research workflow (auto-follows chart → test → trade setup)
varrd research "When wheat drops 3 days in a row, is there a snap-back?"

# What's firing right now?
varrd scan --only-firing

# Personalized market briefing — news filtered to your edge library
varrd briefing

# Search saved strategies
varrd search "momentum on grains"

# Let VARRD discover edges on its own
varrd discover "mean reversion on futures"

{
 "mcpServers": {
 "varrd": {
 "transport": {
 "type": "streamable-http",
 "url": "https://app.varrd.com/mcp"
 }
 }
 }
}

{
 "mcpServers": {
 "varrd": {
 "command": "npx",
 "args": ["-y", "mcp-remote", "https://app.varrd.com/mcp"]
 }
 }
}

from varrd import VARRD
from varrd.freqtrade import generate_strategy

v = VARRD()
result = v.discover("RSI oversold reversal on BTC")

if result.has_edge:
 hyp = v.get_hypothesis(result.hypothesis_id)
 strategy_code, config = generate_strategy(hyp)
 # Drop into your bot's strategies/ folder and run it

from crewai import Agent, Task, Crew

researcher = Agent(
 role="Trading Researcher",
 goal="Find statistically validated trading edges",
 backstory="You are a quantitative researcher who tests trading ideas rigorously.",
 mcps=[{"type": "streamable-http", "url": "https://app.varrd.com/mcp"}]
)

task = Task(
 description="Research whether RSI oversold conditions on ES lead to a bounce within 5 days.",
 agent=researcher,
 expected_output="Edge verdict with trade setup if edge is found."
)

crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-sonnet-4-20250514")

async with MultiServerMCPClient({
 "varrd": {"url": "https://app.varrd.com/mcp", "transport": "streamable_http"}
}) as client:
 agent = create_react_agent(model, client.get_tools())
 result = await agent.ainvoke({"messages": [
 {"role": "user", "content": "Does gold rally when the dollar drops 3 days in a row?"}
 ]})

# Any MCP-compatible client can connect to:
https://app.varrd.com/mcp
# Transport: Streamable HTTP | No auth required | $2 free credits