ETF Flow

An MCP server that delivers crypto ETF flow data to power AI agents' decision-making.

python

8

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-etf-flow-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/etf-flow-mcp",
        "run",
        "etf-flow-mcp"
      ],
      "env": {
        "COINGLASS_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You will run ETF Flow MCP to fetch and present historical ETF flow data for BTC and ETH, formatted for easy use by AI agents and prompts. This MCP delivers data tables and a ready-to-query prompt to streamline interactions with large language models.

How to use

You interact with the ETF Flow MCP through an MCP client. Start the local MCP server, then query it with natural language prompts to retrieve ETF flow history or the latest data in a table format. Expect outputs that show ETF tickers as columns, dates as rows, and a total column aggregating all flows.

Recommended usage patterns include asking for the latest BTC ETF flow data in a table, requesting historical ETH ETF flow data, or prompting for a combined view of BTC and ETH flows. Use clear, concise prompts to get well-formatted Markdown tables from the tool output.

How to install

Prerequisites you need before running the MCP server:

• Python 3.10 or higher
• uv package manager for Python (uvx) to run MCPs
• CoinGlass API key to access ETF flow data
• Claude Desktop (optional) for interactive querying
• Git for cloning the MCP source

Step 1: Clone the MCP source and navigate into the project directory

git clone https://github.com/kukapay/etf-flow-mcp.git
cd etf-flow-mcp

Continue installation and run

Step 2: Install dependencies and prepare the MCP runtime using uv

uv sync

Configure Claude Desktop (optional)

If you use Claude Desktop for interactive querying, add your ETF Flow MCP to Claude’s configuration with the following details. Replace the path with the absolute path to your etf-flow-mcp directory and insert your CoinGlass API key.

{
  "mcpServers": {
    "etf-flow-mcp": {
      "command": "uv",
      "args": ["--directory", "/absolute/path/to/etf-flow-mcp", "run", "etf-flow-mcp"],
      "env": { "COINGLASS_API_KEY": "your_coinglass_api_key_here" }
    }
  }
}

Restart Claude Desktop and test

After saving the configuration, restart Claude Desktop. Look for the hammer icon in the Claude Desktop UI to confirm the MCP is loaded and ready to respond to prompts.

Query examples you can try after setup:

Show me the ETH ETF flow history

Available tools

get_etf_flow

Dynamically fetches historical ETF flow data for BTC or ETH and returns a Markdown table with ETF tickers as columns, dates as rows, and a total column.

etf_flow_prompt

Prompt guidance to streamline LLM interactions for ETF flow questions and queries.