hip4-mcp
Provides read-only tools for discovering, analyzing, and monitoring Hyperliquid HIP-4 prediction markets (outcome trading) on testnet.
README
hip4-mcp
⚠️ EXPERIMENTAL — HIP-4 is currently live on Hyperliquid testnet only. Mainnet launch is expected in 2026 (no exact date announced). This server will be updated for mainnet once HIP-4 goes live.
MCP server for Hyperliquid HIP-4 prediction markets (outcome trading). Provides read-only tools for discovering, analyzing, and monitoring outcome contracts.
What is HIP-4?
HIP-4 adds outcome trading to Hyperliquid — fully collateralized binary contracts that settle to 0 or 1 based on whether an event occurs. Think prediction markets built natively on HyperCore's orderbook.
- Binary YES/NO contracts priced 0–1 (price = implied probability)
- No leverage, no liquidations — fully collateralized
- Settles in USDH (Hyperliquid's native stablecoin)
- Traded on HyperCore's central limit orderbook (same infra as perps/spot)
Install
npm install -g hip4-mcp
Or clone and build:
git clone https://github.com/yashhsm/hip4-mcp.git
cd hip4-mcp
npm install
npm run build
Configure in Claude Code
Add to your MCP config (.mcp.json or Claude Code settings):
{
"mcpServers": {
"hip4": {
"command": "node",
"args": ["/path/to/hip4-mcp/dist/index.js"]
}
}
}
Tools
list_outcomes
List all HIP-4 outcome markets with metadata, side specs, and linked questions. For priceBinary markets, returns parsed underlying asset, target price, expiry, and period.
get_outcome_book
Get the L2 orderbook for a specific outcome side. Returns bids, asks, spread, and depth summary.
get_outcome_prices
Get mid prices for all outcome markets with decoded outcome IDs and side names.
get_outcome_positions
Get a user's outcome token balances (prediction market positions).
get_outcome_depth_summary
Get depth summary across ALL outcome markets — bid/ask depth, spread, best prices for every active side.
search_outcomes
Search and filter outcomes by underlying asset (BTC, HYPE), type (priceBinary), or keyword. Optionally filter to only markets with orderbook depth.
get_outcome_candles
Get OHLCV candle data for an outcome side. Useful for charting price history.
get_outcome_trades
Get a user's fill history filtered to outcome markets only.
get_outcome_open_orders
Get a user's open orders filtered to outcome markets only.
encoding_helper
Convert between outcome IDs, side indices, coin symbols (#xxx), token names (+xxx), and asset IDs. Useful for understanding the HIP-4 encoding system.
HIP-4 Asset Encoding
Outcome assets use a special encoding on Hyperliquid:
| Component | Formula | Example (BTC outcome 2146, YES) |
|---|---|---|
| Encoding | 10 * outcomeId + side |
21460 |
| Spot coin | #<encoding> |
#21460 |
| Token name | +<encoding> |
+21460 |
| Asset ID | 100_000_000 + encoding |
100021460 |
Side is 0 for the first outcome (usually YES), 1 for the second (usually NO).
Network
All tools accept a network parameter ("testnet" or "mainnet"), defaulting to "testnet".
- Testnet:
https://api.hyperliquid-testnet.xyz - Mainnet:
https://api.hyperliquid.xyz
Testing
npm run build
node dist/test.js
Runs integration tests against the Hyperliquid testnet API.
Status
- [x] Read endpoints (outcomeMeta, L2 book, mids, positions, candles, fills, orders)
- [x] Encoding helpers
- [x] PriceBinary description parsing
- [x] Search/filter outcomes
- [x] Complementary pricing validation (YES + NO = 1)
- [ ] Write endpoints (place order, cancel) — coming with mainnet launch
- [ ] WebSocket subscriptions for real-time price updates
- [ ] USDH collateral management helpers
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.