Crypto Orderbook MCP

by kukapay

17 stars
464 downloads
Not rated
GitHub

About

An MCP server that analyzes order book depth and imbalance across major crypto exchanges.

Details

Author
kukapay
GitHub stars
17
Downloads
464
Categories
Finance

- Calculate bid depth, ask depth, and imbalance for a trading pair.
- Compare order book metrics across multiple exchanges in a Markdown table.
- Supports six major exchanges: Binance, Kraken, Coinbase, Bitfinex, Okx, Bybit.
- Real-time data via public exchange APIs.
- Simple integration with AI agents via MCP protocol.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Crypto Orderbook MCP
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Python 3.10+, clone the repository, and run uv sync to install dependencies. Configure the MCP client (e.g., Claude Desktop) with the command uv --directory <absolute_path> run main.py. Use the calculate_orderbook tool to get metrics for a single exchange or compare_orderbook to compare across multiple exchanges.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "crypto orderbook mcp": {
            "crypto-orderbook-mcp": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

McpServers

{
    "crypto-orderbook-mcp": {
        "command": "uv",
        "args": [
            "sync"
        ]
    }
}

Crypto Orderbook MCP

An MCP server that analyzes order book depth and imbalance across major crypto exchanges, empowering AI agents and trading systems with real-time market structure insights.

License
Python
Status

Features

- Order Book Metrics: Calculate bid/ask depth and imbalance for a specified trading pair on a given exchange.
- Cross-Exchange Comparison: Compare order book depth and imbalance across multiple exchanges in a unified Markdown table.
- Supported Exchanges: Binance, Kraken, Coinbase, Bitfinex, Okx, Bybit

Installation

Prerequisites

- Python 3.10 or higher
- uv (Python package and project manager)

Setup

1. Clone the Repository

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

2. Install Dependencies

Use uv to install the required packages:

   uv sync
   
3. Configure the MCP Client(Claude Desktop)
    "mcpServers": { 
      "crypto-orderbook-mcp": { 
        "command": "uv", 
        "args": [ "--directory", "/absolute/path/to/crypto-orderbook-mcp", "run", "main.py" ]
      } 
    }
    

Usage

The server provides two main tools:

1. calculate_orderbook: Computes bid depth, ask depth, and imbalance for a trading pair on a specified exchange.
2. compare_orderbook: Compares bid depth, ask depth, and imbalance across multiple exchanges, returning a Markdown table.

Example: Calculate Order Book Metrics

Prompt: "Calculate the order book metrics for BTC/USDT on Binance with a 1% depth range."

Expected Output (JSON object):

{
  "exchange": "binance",
  "symbol": "BTC/USDT",
  "bid_depth": 123.45,
  "ask_depth": 234.56,
  "imbalance": 0.1234,
  "mid_price": 50000.0,
  "timestamp": 1698765432000
}

Example: Compare Order Book Across Exchanges

Prompt: "Compare the order book metrics for BTC/USDT across Binance, Kraken, and OKX with a 1% depth range."

Expected Output (Markdown table):

| exchange | bid_depth | ask_depth | imbalance |
|----------|-----------|-----------|-----------|
| binance  |    123.45 |    234.56 |    0.1234 |
| kraken   |     89.12 |    178.34 |    0.0987 |
| okx      |    145.67 |    256.78 |    0.1345 |

License

This project is licensed under the MIT License. See the LICENSE file for details.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.