- Home
- MCP servers
- CryptoWeather
CryptoWeather
- python
3
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"2051project-cryptoweather": {
"command": "python",
"args": [
"/path/to/cryptoweather/main.py"
]
}
}
}CryptoWeather MCP Server provides real-time Bitcoin price prediction signals powered by the CryptoWeather AI system. You receive hourly AI-driven insights, trading recommendations, and performance metrics through a lightweight MCP setup, enabling you to integrate signals directly into your conversations and automated workflows.
How to use
You access CryptoWeather signals by connecting your MCP client to the CryptoWeather MCP server. Once linked, you can call a small set of tools to fetch the latest Bitcoin price predictions, trading recommendations, and historical performance data. Use these signals to inform decisions in your chats, automation scripts, or trading dashboards.
How to install
Prerequisites you need before install:
- Python 3.10 or newer
- pip (for Python package management)
- network access to install dependencies
Install from source and set up the MCP locally:
git clone https://github.com/2051project/cryptoweather.git
cd cryptoweather
pip install -e .
Additional content
Configure the MCP client to connect to the local CryptoWeather runtime. The recommended local runtime command is shown in the MCP configuration snippet.
Start the local CryptoWeather runtime using the command shown below in the provided MCP configuration example.
{
"mcpServers": {
"cryptoweather": {
"command": "python",
"args": ["/path/to/cryptoweather/main.py"]
}
}
}
Available tools
get_bitcoin_signal
Fetches the current Bitcoin price prediction signal from CryptoWeather AI, including confidence and direction.
get_trading_recommendation
Returns detailed buy/sell/hold recommendations based on the latest prediction signal.
get_performance_metrics
Provides historical backtest results and current profit metrics to gauge AI performance.
get_signal_history
Retrieves the history and methodology of signals to help you understand how decisions are formed.