Designed, built, explored
Cerebrus Pulse
A multi-protocol crypto-intelligence API for AI agents, distributed through an MCP server, a Python SDK, and a LangChain toolkit.
- API
- Crypto
- x402
- MCP
Live interface
Query it live.
Choose an asset to try the market-data interface. If the service is unavailable, explore the public project and integrations instead.
Real-time technicals for 50+ Hyperliquid perpetuals — click to pull a live read from the Cerebrus Pulse API.
Operating brief
The constraint.
Market data can be fragmented across sources. The project explores how to make technical analysis, sentiment, and market signals accessible through interfaces that applications and agents can call.
What the system does
Provides tools for multi-timeframe technicals, sentiment, funding rates, open interest, liquidation heatmaps, correlation, and market stress.
Explores Hyperliquid perpetual markets across timeframes with confluence scoring.
Provides an MCP server, a typed Python SDK, and a LangChain toolkit so applications and agents can use the same data.
Explores agent-commerce patterns alongside free health and discovery tools.
Architecture
How it moves.
One gateway, multiple client surfaces: a common interface for market data and analysis.
- AI client (Claude · Cursor · LangChain)
- MCP server / Python SDK
- Cerebrus gateway
- Hyperliquid + Chainlink data
The integration ecosystem includes MCP, Python, and LangChain clients.
Build ledger
What carries it.
- Interface
- MCP server, Python SDK (PyPI), LangChain toolkit, CLI
- Protocols
- MCP · x402
- Data
- Hyperliquid perpetuals · Chainlink oracles
- Analysis
- RSI, EMAs, ATR, Bollinger Bands, VWAP · regime & confluence scoring
Current status
Delivered.
Live at cerebruspulse.xyz; published to PyPI as cerebrus-pulse-mcp and cerebrus-pulse-python.
Published integrations include an MCP server, Python SDK, and LangChain toolkit.
Includes work on agent-facing interfaces and commerce protocols.