DEX K-line

An MCP server that streams K-line (candlestick) data from decentralized exchanges (DEXs) to power your AI agents and workflows.

python

4

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": {
    "kukapay-dex-kline-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/dex-kline-mcp",
        "run",
        "main.py"
      ]
    }
  }
}

You can run the DEX K-line MCP Server to stream K-line (OHLCV) data from decentralized exchanges and use it in AI agents, dashboards, or data workflows. It automatically selects the best liquidity pool and supports multiple timeframes for flexible analysis.

How to use

When you query data, you’ll use the single available tool to fetch K-line data for a specific token. You can choose the chain, token contract address, and the timeframe you need. You can also specify an end time in ISO 8601 format or rely on the current UTC time.

Practical usage pattern:

Pick a chain like eth, bsc, or solana
Provide the token’s contract address
Choose a timeframe from 1m, 5m, 15m, 1h, 4h, 12h, or 1d
Optionally set an end_time like 2025-07-03T02:14:00Z
Request up to 1000 data points for quick lookups or historical analysis Example prompt you can adapt for your workflow:

Fetch the 1-hour K-line data for the token with the contract address 0xf4b385849f2e817e92bffbfb9aeb48f950ff4444 on the Binance Smart Chain (BSC).```

## How to install

Prerequisites you need before you start:
- Python 3.10 or higher
- uv for dependency management (declared as the runtime tool)
Follow these concrete steps to set up the MCP server locally and run it with your client.

1) Clone the repository

git clone https://github.com/kukapay/dex-kline-mcp.git cd dex-kline-mcp

2) Install dependencies via uv (repository uses uv for dependency management)

uv sync

3) Install as an MCP server for Claude Desktop (or your MCP client)

uv run mcp install main.py --name "DEX K-line"

## Additional sections

Configuration and runtime details are provided below to help you run the server side by side with your MCP client.

{ "mcpServers": { "DEX K-line": { "command": "uv", "args": [ "--directory", "/path/to/dex-kline-mcp", "run", "main.py" ] } } }


## Available tools

### get\_kline

Retrieves K-line OHLCV data for a specified token, chain, and timeframe with optional end\_time and limit.