Using Madjik API for MCP

Integrate Madjik data into AI models using the Model Context Protocol for enhanced context and decision-making.

Overview

MCP (Model Context Protocol) provides a standardized way to give AI models access to external data and tools. Madjik API can serve as an MCP resource for crypto market context.

MCP Server Implementation

1. Basic MCP Server for Madjik

from mcp import Server, Resource

class MadjikMCPServer(Server):
    def __init__(self, api_key):
        self.api_key = api_key
        self.base_url = "https://api.madjik.io/v1"
    
    @Resource("madjik://metrics/{metric_id}")
    def get_metric(self, metric_id: str):
        resp = requests.get(
            f"{self.base_url}/metrics/{metric_id}",
            headers={"Authorization": f"Bearer {self.api_key}"}
        )
        return resp.json()
    
    @Resource("madjik://market-summary")
    def get_market_summary(self):
        key_metrics = ["ME10030", "ME10014", "ME10016", "ME10010"]
        summary = {}
        for m in key_metrics:
            summary[m] = self.get_metric(m)
        return summary

# Start server
server = MadjikMCPServer(api_key="YOUR_API_KEY")
server.run()

2. MCP Resource Definitions

{
  "resources": [
    {
      "uri": "madjik://metrics/me10030",
      "name": "Social Sentiment Index",
      "description": "Current crypto market sentiment (0-100)",
      "mimeType": "application/json"
    },
    {
      "uri": "madjik://metrics/me10016",
      "name": "Liquidation Risk Index", 
      "description": "Current liquidation cascade probability (0-100)",
      "mimeType": "application/json"
    },
    {
      "uri": "madjik://market-summary",
      "name": "Market Summary",
      "description": "Overview of key crypto market metrics",
      "mimeType": "application/json"
    }
  ]
}

3. Using Madjik MCP with Claude

# Claude Desktop config (claude_desktop_config.json)
{
  "mcpServers": {
    "madjik": {
      "command": "python",
      "args": ["madjik_mcp_server.py"],
      "env": {
        "MADJIK_API_KEY": "your_api_key"
      }
    }
  }
}

Then in conversation:

"What's the current crypto market sentiment according to Madjik?"

Claude will query madjik://metrics/me10030 and respond with the data.

MCP Tools for Madjik

@Tool("analyze_market")
def analyze_market(timeframe: str = "1h"):
    """Analyze current crypto market conditions using Madjik metrics."""
    metrics = {
        "sentiment": get_metric("ME10030"),
        "risk": get_metric("ME10016"),
        "whale_activity": get_metric("ME10010"),
        "funding": get_metric("ME10014")
    }
    
    analysis = {
        "overall": "bullish" if metrics["sentiment"]["value"] > 60 else "bearish",
        "risk_level": "high" if metrics["risk"]["value"] > 70 else "normal",
        "smart_money": "accumulating" if metrics["whale_activity"]["value"] > 60 else "distributing"
    }
    
    return analysis

Best Practices

1. Cache MCP responses - Reduce API calls, update periodically

2. Provide descriptions - Help AI understand metric meaning

3. Include context - Add related hypotheses to responses

4. Handle errors - Return graceful fallbacks

See Also

• AI Integration Guide

• A2A Integration Guide

• All Metrics