horus-flow-mcp
Real-time institutional crypto & equity orderflow intelligence. Detects BUY/SELL pressure from live Binance L2 orderbook and aggressive trade feeds for any USDT pair or US equity.
README
š¦ Horus Flow Intelligence ā MCP Server
An official Model Context Protocol (MCP) server that empowers AI coding assistants (like Claude Desktop, Cursor, and Cline) with Institutional-Grade Crypto & Equity Orderflow Intelligence.
Rather than relying on lagging indicators (RSI, MACD), this MCP server gives your AI agents direct access to live Level 2 Orderbook imbalances and aggressive trade deltas (BUY vs SELL pressure) in milliseconds.
š Features Exposed to AI
Your AI Agent can now autonomously use these tools when analyzing markets or building trading bots for you:
get_crypto_flow(symbol): Returns real-time Microstructure AI verdicts (BUY_PRESSURE,SELL_PRESSURE) based on live Binance L2 depth for any USDT pair.get_equity_flow(symbol): Returns live orderflow metrics for US Equities via Alpaca IEX.scan_crypto_flow(symbols): Scans multiple assets simultaneously to find the exact coin with the highest institutional buying momentum.
š Prerequisites (API Key)
To use this MCP server, you must provide your AI agent with a valid RapidAPI Key from Horus Tech Ltd.
- Go to the Horus Flow Intelligence on RapidAPI
- Subscribe to a tier (Free and Pro tiers available).
- Copy your
x-rapidapi-key.
š» Installation
Option A: Cursor IDE
- Open Cursor Settings (
Cmd + Shift + JorCtrl + Shift + J). - Navigate to Features > MCP Servers.
- Click + Add New MCP Server.
- Set Name:
HorusFlow - Set Type:
command - Set Command:
python3 /absolute/path/to/horus_mcp_public.py --transport stdio - Under Environment Variables, add:
RAPIDAPI_KEY=your-rapidapi-key-here
Option B: Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"horus-flow": {
"command": "python3",
"args": [
"/absolute/path/to/horus_mcp_public.py",
"--transport",
"stdio"
],
"env": {
"RAPIDAPI_KEY": "YOUR_RAPIDAPI_KEY_HERE"
}
}
}
}
Option C: Smithery (CLI)
You can install the server globally using the Smithery CLI:
npx @smithery/cli install horus-flow-mcp
# The installer will prompt you to enter your RAPIDAPI_KEY
š ļø How to Prompt your AI
Once installed, simply ask your AI (Claude / Cursor):
"Can you write a Binance trading bot in Python? But before generating the buy conditions, use the Horus Flow tool to check the current orderflow for BTCUSDT. Only buy if the flow shows BUY_PRESSURE."
The AI will intelligently fetch the live data, verify the institutional delta, and write the code accordingly!
Ā© 2026 HORUS TECH LTD - The Backbone of Quantitative Execution
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.