Long-short Hyperliquid portfolio
Query Forecast price thresholds, reconstruct market-implied price distributions, size via half-Kelly, and output Hyperliquid 1x perp order instructions.
Cookbook 2
Long-short Hyperliquid portfolio
Query four Forecast price thresholds for BTC, SPX, OP, BERA, and WTI; reconstruct market-implied price distributions; size via half-Kelly; and output Hyperliquid 1x perp order instructions.
Run in Colab
Open the notebook and run all cells. The notebook returns survival probabilities, expected return / implied volatility sizing, and Hyperliquid order instructions JSON.
Run locally
zsh
git clone https://github.com/crowdvector/polybridge-cookbooks.git
cd polybridge-cookbooks/longshort-portfolio
bash setup.sh
python3 portfolio.pyRun with Claude + MCP
The same threshold workflow can be driven from an MCP client once polybridge_forecast is available.
steps
Hosted MCP:
1. Connect a supported MCP client to https://mcp.polybridge.ai/mcp.
2. No API key is required at anonymous limits.
Local MCPB:
1. Download polybridge-mcp-v0.3.1.mcpb from the MCP release.
2. Install it in Claude Desktop.
3. No API key is required at anonymous limits.
4. Add POLYBRIDGE_API_KEY only for higher usage.
After the connection is available, paste the prompt below into the chat.prompt
You have access to the PolyBridge MCP tool (polybridge_forecast).
Assets and spot prices:
BTC $74,000 · SPX $7,580 · OP $0.12 · BERA $0.38 · WTI $87
For each asset, query PolyBridge Forecast at four price thresholds
(0.60×, 0.85×, 1.15×, 1.50× spot), all resolving July 31, 2026.
Round thresholds: to nearest $100 if spot ≥ $1,000; to nearest $1
if spot ≥ $10; to nearest $0.01 otherwise.
Question format: "Will {ASSET} exceed ${T} on July 31, 2026?"
Collect all 20 probabilities first. Then write and execute a Python
script that:
1. Enforces monotonicity (clip so P(> Tᵢ₊₁) ≤ P(> Tᵢ)).
2. Reconstructs a piecewise price distribution per asset:
Below T₁: prob = 1 − P(> T₁), midpoint = T₁ / 2
Between Tᵢ and Tᵢ₊₁: prob = P(> Tᵢ) − P(> Tᵢ₊₁), midpoint = (Tᵢ + Tᵢ₊₁) / 2
Above T₄: prob = P(> T₄), midpoint = (T₄ + 1.5 × T₄) / 2
3. Computes per asset:
E[price] = Σ midpoint × prob
E[return] = (E[price] − spot) / spot
Vol = √(Σ midpoint² × prob − E[price]²) / spot
4. Sizes via half-Kelly:
weight = 0.5 × E[return] / Vol²
notional = weight × $50,000
Constraints:
Gross notional ≤ $50,000
No single position > $20,000 (40%)
Scale all positions proportionally if gross exceeds budget
Round to nearest $100
Direction = sign of E[return]
Output:
1. Survival probability table per asset
2. Expected returns, implied vols, and sized position table
3. Hyperliquid 1× perp order instructions as JSON