Crypto

You can run a lightweight MCP server that exposes three tools for cryptocurrency data: get_ticker for live prices and market summaries, get_ohclv for historical OHLCV candles, and stream_ticker for real-time price updates. It includes in-memory caching and robust error handling to make integration with your client smooth and reliable.

How to use

You access the server from a local MCP client by starting the server locally and then invoking the three available tools. The server runs in Python and provides a simple, well-defined interface for requesting live data, historical candles, and streaming updates. Use the client to request a live ticker for a symbol, fetch OHLCV candles for a timeframe, and subscribe to a real-time ticker stream.

How to install

Prerequisites you need on your machine are Python 3.10+ and a working network connection.

1. Clone the project repository.

2. Change into the project directory.

3. Install dependencies.

4. Start the MCP server from the server directory.

Additional notes

To run locally you will execute the following commands exactly as shown.

# 1) Clone the repository
git clone https://github.com/yourusername/crypto-mcp-server

# 2) Enter the project directory
cd crypto-mcp-server

# 3) Install dependencies
pip install -r requirements.txt

# 4) Run the MCP server from the server/ folder
cd server
python -m server.main

Available tools

get_ticker

Fetches live price, high/low, base volume, and price change percentage for a given symbol.

get_ohclv

Returns historical OHLCV candles including timestamp, open, high, low, close, and volume for a specified timeframe.

stream_ticker

Asynchronous generator that yields real-time ticker updates at regular intervals.