Skip to main content
Glama
crypto_price_tracker

crypto_price_tracker

by Adity-star

πŸͺ™ MCP Crypto Price Lookup Server using ALPACA API

This project sets up a cryptocurrency price lookup service powered by the ALPACA API and built for integration with MCP (Multi-Agent Control Protocol).

The server allows AI agents or clients to fetch real-time cryptocurrency prices and market data efficiently using Alpaca's API.


πŸ“¦ Step 1: Set Up the Environment with uv

We'll use uv β€” a fast, modern Python package manager β€” to create and manage the project environment.

πŸ› οΈ Installation & Setup

Run these commands in your terminal (not in Jupyter):

# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh 

# Create and navigate to your project directory
mkdir mcp-crypto-server
cd mcp-crypto-server

# Initialize a new project
uv init

# Create and activate the virtual environment
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install required dependencies
uv add "mcp[cli]" httpx

Related MCP server: coingecko-mcp-server

Step 2: Running the MCP Server

Once the environment is set up, we're ready to build and run our crypto price lookup tool. Copy the server script from the scripts folder:

cp ../mcp_server.py .

Start the MCP server:
uv run mcp_server.py

πŸ’‘ Check out mcp_server.py for implementation details on how the tool interfaces with the Alpaca API.

About the Server

The MCP-compatible server includes tools that:

  • Fetch real-time crypto prices (e.g., BTC/USD, ETH/USD)

  • Access market data using Alpaca's REST API

  • Serve AI agents with quick, formatted responses

Step 3: Configure Your MCP Server

Add the following to your MCP config to register the server:

{
    "mcpServers": {
        "crypto-price-tracker": {
            "command": "/ABSOLUTE/PATH/TO/uv",
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/GenAI_Agents//mcp-crypto-server",
                "run",
                "mcp_server.py"
            ]
        }
    }
}

πŸ” Replace /ABSOLUTE/PATH/TO/... with the full paths to your uv binary and project folder.

Step 4: Restart Claude Desktop for the changes to take effect.

Step 5: Try ask the price of Bitcoin

  • You can add your own tools to mcp_server.py

"""
This script demonstrates how to create a simple MCP server that fetches
the current price of a cryptocurrency using the CoinGecko API.
It uses the FastMCP library to create the server and handle requests.
"""
import httpx
from dotenv import load_dotenv
from mcp.server.fastmcp import FastMCP

load_dotenv()

COINGECKO_BASE_URL = "https://api.coingecko.com/api/v3"

# Create our MCP server with a descriptive name
mcp = FastMCP("crypto_price_tracker")

# Now let's define our first tool - getting the current price of a cryptocurrency
@mcp.tool()
async def get_crypto_price(crypto_id: str, currency: str = "usd") -> str:
    """
    Get the current price of a cryptocurrency in a specified currency.
    
    Parameters:
    - crypto_id: The ID of the cryptocurrency (e.g., 'bitcoin', 'ethereum')
    - currency: The currency to display the price in (default: 'usd')
    
    Returns:
    - Current price information as a formatted string
    """
    # Construct the API URL
    url = f"{COINGECKO_BASE_URL}/simple/price"
    
    # Set up the query parameters
    params = {
        "ids": crypto_id,
        "vs_currencies": currency
    }
    
    try:
        # Make the API call
        async with httpx.AsyncClient() as client:
            response = await client.get(url, params=params)
            response.raise_for_status()  # Raise an exception for HTTP errors
            
            # Parse the response
            data = response.json()
            
            # Check if we got data for the requested crypto
            if crypto_id not in data:
                return f"Cryptocurrency '{crypto_id}' not found. Please check the ID and try again."
            
            # Format and return the price information
            price = data[crypto_id][currency]
            return f"The current price of {crypto_id} is {price} {currency.upper()}"
            
    except httpx.HTTPStatusError as e:
        return f"API Error: {e.response.status_code} - {e.response.text}"
    except Exception as e:
        return f"Error fetching price data: {str(e)}"

# You can add more tools here, following the same pattern as above

# Run the MCP server
# This will start the server and listen for incoming requests
if __name__ == "__main__":
    mcp.run()

πŸ“ˆ Then Level Up: Build the yFinance Stock Server

Once you're familiar with the flow, move on to this more advanced stock tracker πŸ’Ή

πŸ”— GitHub Repo: https://github.com/Adity-star/mcp-yfinance-server

πŸ“ Detailed Blog: πŸ‘‰ How I Built My Own Stock Server with Python, yFinance, and a Touch of Nerdy Ambition

Enjoy Learnings !

Available Tools

1 tool
get_crypto_market_infoA
Get market information for one or more cryptocurrencies using Alpha Vantage.

Parameters:
- crypto_ids: Comma-separated list of cryptocurrency symbols (e.g., 'BTC,ETH')
- currency: The fiat currency to compare against (default: 'USD')

Returns:
- Current exchange rates for each cryptocurrency.

Inputs: crypto_ids (required), currency.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of confusing it with another. The tool's purpose is clearly defined and distinct.

    Naming Consistency5/5

    The single tool follows a clear verb_noun pattern ('get_crypto_market_info'), which is consistent with standard naming conventions and leaves no room for inconsistency.

    Tool Count1/5

    The server has only one tool, which is extremely thin for a typical MCP server. A crypto price tracker would typically need additional capabilities such as historical data, symbol discovery, or alerts to be useful.

    Completeness3/5

    The tool covers the core need of fetching current exchange rates, but it lacks obvious complementary features like historical data or a way to list supported cryptocurrencies, leaving notable gaps for a price tracking domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server providing market data for 15,000+ cryptocurrencies including prices, history, trends, and deep coin metadata via CoinGecko.
      130 npm
      1
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that gives AI agents the ability to check crypto wallet balances, track token prices, calculate portfolio value, monitor gas prices, and track the Fear & Greed Index β€” all with zero external dependencies using free public APIs.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      An MCP server that exposes CoinGecko crypto market data as tools β€” get spot prices and find cross-exchange arbitrage spreads without needing an API key.
      3
      29 npm
      MIT