Skip to main content
Glama

CryptoSignal-MCP

📈 CryptoSignal MCP

Python MCP License Binance

AI-Powered Cryptocurrency Direction Prediction & Market Signal Analysis

Powered by Machine Learning Ensemble Models with 30+ Technical Indicators

FeaturesInstallationAPI ToolsExamplesIndicators

🎬 Demo


✨ Features

Feature

Description

🧠

Advanced ML Predictions

Ensemble models (Random Forest + Gradient Boosting) with 30+ technical indicators

📊

Comprehensive Technical Analysis

RSI, MACD, Bollinger Bands, Stochastic, Williams %R, ATR, and more

Multiple Timeframes

Support for 1m, 3m, 5m, 15m, 30m, 1h, 2h, 4h, 6h, 8h, 12h, 1d, 3d, 1w, 1M

🔄

Real-time Data

Live market data from Binance API with intelligent rate limiting and caching

🎯

Smart Filtering

Automatically filters incomplete trading periods for accurate analysis

🔍

WebSearch Integration

Optimized search queries for Claude Code's WebSearch tool with sentiment analysis prompts

📊

Polymarket Trader Analysis

Monitor successful crypto traders' activities, positions, and trading patterns for behavioral insights

🚀 Installation

Prerequisites

  • Python 3.11+

  • Required packages (automatically installed)

Quick Start

# Clone the repository git clone https://github.com/khalilbalaree/CryptoSignal-MCP.git cd CryptoSignal-MCP # Install dependencies pip install -r requirements.txt # Run the server python crypto_predictor_server.py

🔧 MCP Integration

With Claude Desktop

Add this server to your Claude Desktop configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{ "mcpServers": { "cryptosignal-mcp": { "command": "python", "args": ["/path/to/CryptoSignal-MCP/crypto_predictor_server.py"], "env": {} } } }

🛠️ API Tools

🎯 predict_crypto_direction

Advanced ML prediction using ensemble models to predict price direction

predict_crypto_direction( symbol="BTCUSDT", # Trading pair interval="1h", # Time interval (default: 1h) training_periods=1000 # Training data size (default: 1000) )

Supported Intervals: 1m 3m 5m 15m 30m 1h 2h 4h 6h 8h 12h 1d 3d 1w 1M

Returns: Prediction direction, confidence scores, model performance, market context, feature importance, risk assessment


📈 analyze_crypto_indicators

Fast technical analysis without ML training - immediate market insights

analyze_crypto_indicators( symbol="ETHUSDT", # Trading pair interval="1h", # Time interval (default: 1h) limit=100, # Data points (default: 100) short_period=5, # Short-term period (default: 5) medium_period=10, # Medium-term period (default: 10) long_period=20 # Long-term period (default: 20) )

Returns: Moving averages, trends, momentum analysis, volatility metrics, support/resistance levels, trend signals


🔍 get_crypto_news_search

Generate optimized search queries for Claude Code's WebSearch tool

get_crypto_news_search( symbol="bitcoin" # Crypto symbol (default: bitcoin) )

Returns: Structured search data including optimized queries, reliable domains, and analysis prompts for use with Claude Code's WebSearch tool


📊 monitor_polymarket_trader

Analyze successful crypto traders' positions and patterns on Polymarket

monitor_polymarket_trader( trader_address="0x1234567890abcdef1234567890abcdef12345678", # Ethereum wallet address limit=100 # Activities to fetch (default: 100) )

Returns: Complete trading activity history including positions, bet sizes, outcomes, timing, and P&L performance across crypto prediction markets

💡 Usage Examples

# Get ML prediction for Bitcoin (1-hour timeframe) predict_crypto_direction("BTCUSDT", "1h", 1000) # Quick technical analysis for Ethereum (4-hour timeframe) analyze_crypto_indicators("ETHUSDT", "4h", 200) # Get search query for Bitcoin news analysis get_crypto_news_search("bitcoin") # Monitor successful crypto trader's activities monitor_polymarket_trader("0x1234567890abcdef1234567890abcdef12345678", 100)
# Short-term scalping prediction (15-minute intervals) predict_crypto_direction("BTCUSDT", "15m", 500) # Long-term investment analysis (daily timeframe) analyze_crypto_indicators("ETHUSDT", "1d", 365, 10, 20, 50) # Custom altcoin analysis analyze_crypto_indicators("ADAUSDT", "2h", 100, 3, 7, 14) # Multi-timeframe analysis for timeframe in ["1h", "4h", "1d"]: analyze_crypto_indicators("BTCUSDT", timeframe) # Copy trading successful traders successful_traders = [ "0x1234567890abcdef1234567890abcdef12345678", "0xabcdef1234567890abcdef1234567890abcdef12" ] for trader in successful_traders: monitor_polymarket_trader(trader, 100)

📊 Technical Indicators

Our ML models leverage 30+ advanced technical indicators across multiple categories:

Category

Indicators

📈 Price & Momentum

Price change, acceleration, velocity

Momentum (3, 5, 10, 20 periods)

Rate of change, Sharpe ratio

📉 Moving Averages

Simple MA (5, 10, 20, 50)

Exponential MA (5, 12, 26, 50)

MA ratios and crossover signals

🎯 Oscillators

RSI (7, 14 periods)

Stochastic Oscillator (K%, D%)

Williams %R

🔊 Volume Analysis

Volume ratios and rate of change

On-Balance Volume (OBV)

Volume spikes and trends

📐 Volatility & Bands

Bollinger Bands (width, position)

Average True Range (ATR)

Volatility regimes

🏗️ Market Structure

Support/resistance levels

Fractal patterns (local max/min)

Trend strength and regime detection

🎯 Model Architecture

graph TD A[Historical Data] --> B[Feature Engineering] B --> C[30+ Technical Indicators] C --> D[Data Preprocessing] D --> E[Ensemble Models] E --> F[Random Forest] E --> G[Gradient Boosting] E --> H[Extra Trees] F --> I[Voting Classifier] G --> I H --> I I --> J[Prediction + Confidence]

⚠️ Risk Disclaimer

🚨 IMPORTANT: This tool is designed for educational and research purposes only.

Cryptocurrency trading involves significant financial risk. Past performance does not guarantee future results. Always:

  • Conduct your own research and analysis

  • Implement proper risk management strategies

  • Never invest more than you can afford to lose

  • Consider seeking advice from qualified financial professionals

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.


Built with ❤️ for the crypto community

⭐ Star this repo🐛 Report Issues💡 Request Features

-
security - not tested
A
license - permissive license
-
quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

AI-Powered Cryptocurrency Direction Prediction & Market Signal Analysis

  1. 🎬 Demo
    1. ✨ Features
      1. 🚀 Installation
        1. Prerequisites
        2. Quick Start
        3. 🔧 MCP Integration
      2. 🛠️ API Tools
        1. 🎯 predict_crypto_direction
        2. 📈 analyze_crypto_indicators
        3. 🔍 get_crypto_news_search
        4. 📊 monitor_polymarket_trader
      3. 💡 Usage Examples
        1. 📊 Technical Indicators
          1. 🎯 Model Architecture
            1. ⚠️ Risk Disclaimer
              1. 📄 License

                Related MCP Servers

                • A
                  security
                  A
                  license
                  A
                  quality
                  Coinmarket API integration to fetch cryptocurrency listings and quotes
                  Last updated -
                  2
                  41
                  MIT License
                  • Apple
                • A
                  security
                  A
                  license
                  A
                  quality
                  Enables AI agents to access crypto-related information including latest news, prices, and market trends through ChainGPT capabilities.
                  Last updated -
                  3
                  0
                  5
                  MIT License
                  • Apple

                View all related MCP servers

                MCP directory API

                We provide all the information about MCP servers via our MCP API.

                curl -X GET 'https://glama.ai/api/mcp/v1/servers/khalilbalaree/CryptoSignal-MCP'

                If you have feedback or need assistance with the MCP directory API, please join our Discord server