Horus Flow Intelligence — Institutional Orderflow for AI Agents

What is Horus Flow Intelligence — Institutional Orderflow for AI Agents?

An MCP server that provides sub-second institutional orderflow intelligence for autonomous AI agents and HFT traders. It ingests Level 2 orderbook data from Binance (crypto) and Alpaca (US equities) via WebSocket, then uses a physics-based engine to measure tick imbalances, flow deltas, and liquidity events. The server is designed for AI agents such as Claude and Cursor, and for trading bots that need real-time market microstructure signals.

How to use Horus Flow Intelligence — Institutional Orderflow for AI Agents?

Install dependencies (pip install mcp httpx), set the RAPIDAPI_KEY environment variable, and run the SSE server with python horus_mcp_public.py --transport sse --port 8011. Then pull live flow data via the API endpoint (e.g., https://flow.horustek.pro/v1/flow/crypto/BTCUSDT) using your API key in the X-API-Key header.

Key features of Horus Flow Intelligence — Institutional Orderflow for AI Agents

• Sub-second institutional orderflow detection.
• Physics-based decision matrix (bid/ask ratio, delta acceleration).
• L2 orderbook, tick imbalance, and flow delta analysis.
• Sub-millisecond response time (local) with 29ms latency.
• Zero-hallucination logic for AI agent data gathering.
• Native MCP integration for plug-and-play AI agent connection.

Use cases of Horus Flow Intelligence — Institutional Orderflow for AI Agents

• AI agents detecting liquidity events and spoofing in real time.
• HFT traders using orderflow physics for sub-second decision making.
• Trading bots executing bailout strategies based on market state signals.
• Developers visualizing live market edge proof via the developer portal.

FAQ from Horus Flow Intelligence — Institutional Orderflow for AI Agents

What is Horus Flow Intelligence and how does it differ from traditional indicators?

Horus uses Level 2 orderbook physics, tick imbalances, and 5-second flow deltas to measure institutional whale activity in real time, unlike lagging indicators like RSI or MACD.

What are the runtime dependencies and how do I get an API key?

Requires Python 3.12+, the mcp and httpx libraries, and a RapidAPI key (available on RapidAPI) or direct API key. Set the RAPIDAPI_KEY environment variable.

Where does the data come from and how is it processed?

Data is ingested from Binance (crypto) and Alp