Crypto Indicators MCP server

This MCP server provides cryptocurrency technical analysis indicators and strategies, allowing AI trading agents to analyze market trends and develop quantitative strategies. It includes over 50 indicators across trend, momentum, volatility, and volume categories with corresponding trading strategies that output buy, hold, or sell signals.

Installation Requirements

Prerequisites

• Node.js (v18.x or higher)
• npm (v8.x or higher)

Setup Instructions

1. Clone the repository:

   git clone https://github.com/kukapay/crypto-indicators-mcp.git
   cd crypto-indicators-mcp
   

2. Install dependencies:

   npm install
   

3. Configure MCP Client: To use with an MCP client like Claude Desktop, add this to your config file:

   {
     "mcpServers": {
       "crypto-indicators-mcp": {
         "command": "node",
         "args": ["path/to/crypto-indicators-mcp/index.js"],
         "env": {
           "EXCHANGE_NAME": "binance"
         }
       }
     }
   }
   

Available Tools

Trend Indicators

• calculate_absolute_price_oscillator: Measures difference between two EMAs to identify trend strength
• calculate_aroon: Identifies trend changes using high/low price extremes
• calculate_exponential_moving_average: Weights recent prices more heavily for trend analysis
• calculate_moving_average_convergence_divergence: Tracks momentum and trend direction via EMA differences
• calculate_parabolic_sar: Provides stop-and-reverse points for trend following
• calculate_simple_moving_average: Averages prices over a period to identify trends

Momentum Indicators

• calculate_awesome_oscillator: Measures market momentum using midline crossovers
• calculate_ichimoku_cloud: Provides comprehensive view of support, resistance, and momentum
• calculate_relative_strength_index: Identifies overbought/oversold conditions
• calculate_stochastic_oscillator: Compares closing prices to ranges for momentum signals
• calculate_williams_r: Measures momentum relative to recent high-low ranges

Volatility Indicators

• calculate_average_true_range: Measures market volatility based on price ranges
• calculate_bollinger_bands: Encloses price action with volatility-based bands
• calculate_keltner_channel: Combines ATR and EMA for volatility bands
• calculate_donchian_channel: Tracks volatility with high/low price channels

Volume Indicators

• calculate_accumulation_distribution: Tracks volume flow to confirm price trends
• calculate_chaikin_money_flow: Measures buying/selling pressure with volume
• calculate_money_flow_index: Identifies overbought/oversold via price-volume
• calculate_on_balance_volume: Accumulates volume to predict price movements
• calculate_volume_weighted_average_price: Averages prices weighted by volume

Using the MCP Server

Example 1: Calculate MACD Indicator

Input (Natural Language Prompt):

Calculate the MACD for BTC/USDT on a 1-hour timeframe with fast period 12, slow period 26, signal period 9, and fetch 100 data points.

Output:

{"macd": [...], "signal": [...], "histogram": [...]}

Example 2: Calculate RSI Strategy

Input (Natural Language Prompt):

Give me the RSI strategy signals for ETH/USDT on a 4-hour timeframe with a period of 14 and 50 data points.

Output:

[-1, 0, 1, 0, ...]

Strategy Signal Interpretation

The strategy functions output numerical signals that can be interpreted as:

• -1: SELL signal
• 0: HOLD signal
• 1: BUY signal

These signals can be used directly by AI agents to make trading decisions or as part of a more complex trading system.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.