FEAT NEXUS PRIME
An institutional-grade algorithmic trading platform that bridges MetaTrader 5 with an autonomous AI cortex for high-frequency data extraction, ML-driven analysis, and autonomous decision-making using the FEAT methodology.
README
🦅 FEAT NEXUS PRIME
<div align="center">
The first institutional-grade Algorithmic Trading Platform that bridges MetaTrader 5 with an Autonomous AI Córtex (Dockerized Brain + SSE + RAG).
Mission • Command Center • Architecture • Omni-Audit • Institutional DB
</div>
🎯 The Mission
NEXUS PRIME is not just an indicator or a bot; it is a Mission-Critical Ecosystem designed for high-frequency data extraction, ML-driven analysis, and autonomous decision-making using the FEAT (Form, Space, Acceleration, Time) methodology.
🎮 Command Center (One-Switch Control)
The entire system lifecycle is controlled via a unified Python Orchestrator:
nexus.bat: Initializes the "Golden Start".- Bootstraps MetaTrader 5.
- Orchestrates Docker Compose (Brain + Dashboard).
- Executes Internal Sync Audit.
- Runs the War Room Report.
- Opens the Visual Interface.
stop_nexus.bat: Executes a Graceful Shutdown.- Safe Docker teardown (Persistence guaranteed).
- Professional MT5 process termination.
check_system.bat: The Omni-Auditor on demand.
🏗️ Architecture: NEXUS PRIME
The system operates on a decentralized core-peripheral model:
- THE BRIDGE (MQL5): Native indicators (
UnifiedModel_Main.mq5,InstitutionalPVP.mq5) extraction engine with high-performance ZMQ streaming. - THE BRAIN (Docker/Python): A specialized MCP Server hosting the ML Engine, Data Collectors, and the RAG Memory (ChromaDB).
- THE PERSISTENCE (Supabase): Institutional-grade schema for high-frequency tick logging, signal auditing, and model performance tracking.
- THE VISION (Dashboard): Next.js + Framer Motion visual cockpit for real-time monitoring.
🕵️ Omni-Audit (Self-Healing)
Every component is monitored by the NEXUS Omni-Auditor. If a data blocker is detected (MT5 Offline, ZMQ Latency > 50ms, DB Sync Failed), the system generates a machine-readable REPAIR_REQUEST to trigger autonomous self-healing by the Antigravity Agent.
📊 Institutional Persistence
The database schema (institutional_schema.sql) is designed for senior quantitative analysis:
market_ticks: Nanosecond-aware price capture.feat_signals: Comprehensive audit trail with confidence scores and top-drivers.ml_inference_logs: Feature snapshots at the moment of prediction for retrospective learning.knowledge_base: RAG persistence for the autonomous agent.
⚡ Quick Start (The NEXUS Protocol)
1. Requirements
- Windows 11 (for MT5 Terminal).
- Docker Desktop.
- Python 3.12+.
2. Configuration
Fill your .env with the Supabase credentials and MT5 paths:
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_KEY=your-service-role-key
MT5_PATH=C:\Program Files\LiteFinance MT5 Terminal\terminal64.exe
3. Ignition
Run the main orchestrator:
.\nexus.bat
📜 Repository Hygiene
This project follows strictly the Saneamiento Protocol:
- No binary files in Git.
- No local logs in Git.
- No environment variables in Git.
- Clean development/production branch harmonization.
<div align="center">
Built for the Next Generation of Quantitative Trading.
Powered by SrAndres629 & Antigravity Agent.
</div>
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.