Cryptoweather

Created By
Satoshia year ago
CryptoWeather MCP Server provides real-time Bitcoin price prediction signals from the CryptoWeather AI system. Get hourly updated trading signals, performance metrics, and AI-driven market insights directly in your Claude conversations.
Overview

CryptoWeather MCP Server

🔮 AI-powered Bitcoin price prediction signals through Model Context Protocol (MCP)

Overview

CryptoWeather MCP Server provides real-time Bitcoin price prediction signals from the CryptoWeather AI system. Get hourly updated trading signals, performance metrics, and AI-driven market insights directly in your Claude conversations.

Features

  • Real-time Bitcoin Signals: Get current AI predictions for Bitcoin price movements
  • Trading Recommendations: Receive detailed buy/sell/hold recommendations
  • Performance Metrics: Access historical backtest results and current profit metrics
  • Signal Analysis: Understand signal clarity and confidence levels
  • Hourly Updates: Fresh predictions updated every hour

Installation

For Claude Desktop Users

  1. Add to your Claude Desktop MCP configuration:
{
  "mcpServers": {
    "cryptoweather": {
      "command": "python",
      "args": ["/path/to/cryptoweather/main.py"]
    }
  }
}

For Developers

install from source:

git clone https://github.com/2051project/cryptoweather.git
cd cryptoweather
pip install -e .

Usage

Once installed, you can use the following tools in your Claude conversations:

Available Tools

  1. get_bitcoin_signal() - Get current Bitcoin prediction signal
  2. get_trading_recommendation() - Get detailed trading advice
  3. get_performance_metrics() - View AI performance statistics
  4. get_signal_history() - Learn about signal methodology

Example Usage

conversations

Signal Types

  • Sunny ☀️: Strong directional signal with high confidence
  • Cloudy ☁️: Mixed or uncertain market conditions

Position Types

  • Buy: AI predicts price increase
  • Sell: AI predicts price decrease
  • Hold: AI suggests maintaining current position

API Information

  • Update Frequency: Every hour
  • Response Format: JSON with signal, clarity, position, and profit data

Example Response

{
  "Clear": {
    "Clarity": "74%",
    "backtest": "24,510%",
    "pos": "hold",
    "profit": "538%",
    "sig": "C",
    "signal": "Cloudy ☁️"
  },
  "version": "2.0"
}

Disclaimer

⚠️ Important: CryptoWeather predictions are for informational purposes only. This is not financial advice. Always do your own research and consider your risk tolerance before making trading decisions. Past performance does not guarantee future results.

Support

License

MIT License - see LICENSE file for details.

Development

Running in Debug Mode

python main.py --debug

Requirements

  • Python 3.10+
  • fastmcp >= 0.1.0
  • requests >= 2.28.0

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

Made with ❤️ by the CryptoWeather Team

Server Config

{
  "mcpServers": {
    "cryptoweather": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "git+https://github.com/2051project/cryptoweather.git",
        "python",
        "-c",
        "import main; main.main()"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Satoshi
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Docwand

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

14 hours ago