Horus Flow Intelligence — Institutional Orderflow for AI Agents

by horustechltd

2 stars

381 downloads

Not rated

GitHub Website

About

Institutional-grade orderflow intelligence for AI agents. Detects spoofing, buy-absorption, and liquidity events with a 15-30s lead time over price action. Audited by Manus AI (0.85 confidence)

Details

Author: horustechltd
GitHub stars: 2
Downloads: 381
Categories: Other, Finance, Productivity

- 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.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Horus Flow Intelligence — Institutional Orderflow for AI Agents

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "horus flow intelligence \u2014 institutional orderflow for ai agents": {
            "horus-flow": {
                "command": "python",
                "args": [
                    "horus_mcp_public.py",
                    "--transport",
                    "sse",
                    "--port",
                    "8011"
                ],
                "env": {
                    "RAPIDAPI_KEY": "your_rapidapi_key_here"
                }
            }
        }
    }
}

McpServers

{
    "horus-flow": {
        "command": "python",
        "args": [
            "horus_mcp_public.py",
            "--transport",
            "sse",
            "--port",
            "8011"
        ],
        "env": {
            "RAPIDAPI_KEY": "your_rapidapi_key_here"
        }
    }
}

🦅 Horus Flow MCP Server

<div align="center">
<h1>HORUS 👁️ | Sub-Second Institutional Orderflow Intelligence</h1>

<p><strong>A True Market Gravity Engine for Autonomous AI Agents and HFT Traders.</strong></p>

<p>
<a href="https://glama.ai/mcp/servers/horustechltd/horus-flow-mcp">
horus-flow-mcp MCP server
</a>
</p>
<p>
<a href="https://glama.ai/mcp/servers/horustechltd/horus-flow-mcp">

</a>
</p>

---

🧠 Why Horus? The AI Agent's "Nervous System"

In the world of autonomous trading, an AI Agent without real-time orderflow is like a pilot flying blind. Technical indicators (RSI, MACD) are lagging echoes of the past. Horus is the Nervous System that provides:

Proprioception: Real-time awareness of market "muscle" (Orderbook Depth).
Reflexes: Sub-second detection of institutional "pain" (Liquidity Collapses).
Intelligence: A context-aware decision matrix that translates raw physics into actionable signals.

> "If you want your AI Agent to trade like a whale, you must give it the whale's eyes. Horus is that vision."

---

🧪 Manus AI Audit: Live Performance Proof

Horus Flow MCP has been rigorously audited by Manus AI (an autonomous execution agent). The results confirm that Horus isn't just code—it's a high-performance reality.

Audit Highlights (Live Test on BTCUSDT):
Signal Accuracy: Successfully detected STRONG_SELL_PRESSURE with a 0.85 Confidence Score. Physics Engine Validation: Confirmed bid_ask_ratio of 0.156, proving the engine's ability to read thin limit books and aggressive selling. Zero-Hallucination Logic: The MCP server correctly identified symbols in "Data Gathering" mode (e.g., SOLUSDT), preventing the AI from making false assumptions.

---

💰 The $29 Arbitrage: Institutional Intelligence for the Price of a Lunch

Why pay thousands for institutional terminals when you can get the same Microstructure Intelligence for a fraction of the cost?

---

🛑 Stop Predicting Candles. Start Measuring Gravity.

Retail traders use trailing indicators to guess what the market will do based on the past. Horus uses Level 2 Orderbook physics, Tick imbalances, and 5-Second Flow Deltas to measure exactly what institutional whales are doing right now.

Horus doesn't ask "Are we overbought?". It measures gravitational pull and tells you: "Whales are spoofing the bid and aggressive takers are tearing through the ask. Liquidity is collapsing. Bailout now."

---

⚡ Why AI Agents (Claude, Cursor) Love Horus

If you hook up an AI Agent to a basic technical indicator feed, it gets confused by noise.
If you feed an AI Agent Horus, it gets an institutional grade decision matrix.

Look at what Horus catches in real-time during a Liquidity Withdrawal / Flash Crash attempt:

{
  "symbol": "BTCUSDT",
  "signal": "LIQUIDITY_EVENT",
  "confidence": 0.99,
  "market_state": "DISTRIBUTION",
  "risk": "EXTREME",
  "description": "Liquidity withdrawn under price. Aggressive taking.",
  "metrics": {
    "bid_ask_ratio": 7.934,
    "buy_sell_ratio": 0.393,
    "delta_5s": -83040.05,
    "whale_activity": true,
    "large_sell_count": 4,
    "delta_accel": 3.8,
    "wall_side": "BID",
    "wiseman_climate": {
      "market_mode": "CHOP",
      "health": "FRAGILE",
      "confidence": 0.85
    },
    "flags": [
      "GLOBAL_LIQUIDITY_EVENT",
      "SPOOFING_DETECTED(wall=BID)"
    ]
  },
  "timestamp": 1776107738.975
}

The Institutional Alpha:

1. bid_ask_ratio: 7.934 & wall_side: BID: Massive spoofed bid walls are placed by whales below the market to create fake support. 2. buy_sell_ratio: 0.393: Horus sees through the spoofing (SPOOFING_DETECTED flag). It measures real taker flow and discovers aggressive selling is devastating the orderbook. 3. delta_accel: 3.8 & whale_activity: true: Selling momentum accelerated by 3.8x natively tracking 4 major whale dumps within milliseconds. 4. wiseman_climate: FRAGILE: Integrates perfectly with the overarching Horus SaaS macro brain, verifying that Bitcoin's holistic environment is fragile before attacking. 5. The Verdict: With a 0.99 Confidence factor, the AI engine triggers LIQUIDITY_EVENT. It front-runs the ensuing 1-minute crash. This is Institutional Grade.

---

🏗️ Architecture

graph TD
    %% Styling
    classDef crypto_stream fill:#F3BA2F,stroke:#000,color:#000,stroke-width:2px;
    classDef equity_stream fill:#000,stroke:#09b533,color:#09b533,stroke-width:2px;
    classDef compute fill:#1A1F36,stroke:#00D6FF,color:#fff,stroke-width:2px;
    classDef mcp fill:#632CA6,stroke:#fff,color:#fff,stroke-width:2px;
    classDef client fill:#FF3366,stroke:#fff,color:#fff,stroke-width:2px;
%% Ingestion

    subgraph Data_Pipelines [Sub-Millisecond Websocket Ingestion]

        B[Binance WSS <br/> L1/L2 Book]:::crypto_stream

        A[Alpaca WSS <br/> SIP Equities]:::equity_stream

    end
%% Engine

    subgraph Core_Engine [The Physics Engine]

        IC[Imbalance Calculator <br/> Bid/Ask Spread]:::compute

        FC[Flow Calculator <br/> Tape Deltas]:::compute

        Tkr[Prediction Tracker <br/> In-Memory Evaluator]:::compute

        BC[Behavioral Court <br/> Spoofing & Liquidity Rules]:::compute

    end
%% Output

    subgraph Output_Layer [Data Shield & Delivery]

        MCP[AI Agent MCP Context <br/> Context-Aware Prompts]:::mcp

        API[FastAPI Client <br/> Safe Shielded Outputs]:::client

        Dash[Real-time Dashboard <br/> Live Edge Proof]:::client

    end
B --> IC

    A --> IC

    B --> FC

    A --> FC

    

    IC --> BC

    FC --> BC

    

    BC --> Tkr

    Tkr -- "Validates 1M accuracy" --> BC

    

    BC --> MCP

    BC --> API

    BC --> Dash

---

🚀 Quickstart for Trading Bots

Getting started with Horus takes less than 60 seconds.
⚡ Test Instantly: Download our Postman Collection to ping the API directly from your browser.

1. Fire up the Core Engine

```bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

🦅 Horus Flow MCP Server

🧠 Why Horus? The AI Agent's "Nervous System"

🧪 Manus AI Audit: Live Performance Proof

Audit Highlights (Live Test on BTCUSDT):

💰 The $29 Arbitrage: Institutional Intelligence for the Price of a Lunch

🛑 Stop Predicting Candles. Start Measuring Gravity.

⚡ Why AI Agents (Claude, Cursor) Love Horus

The Institutional Alpha:

🏗️ Architecture

🚀 Quickstart for Trading Bots

1. Fire up the Core Engine

Install

More like this

Sequential Thinking

Time

Filesystem

EverArt

Google Drive

Reactive Resume