About ETF Flow MCP
ETF Flow MCP is an MCP server for retrieving historical BTC and ETH crypto ETF flows. It presents the data as Markdown tables with per-ETF figures and totals, and includes a prompt to guide queries.
Key features
- 01Fetch historical BTC and ETH ETF flows
- 02Format results as Markdown tables
- 03Show per-ETF and total flows
- 04Include an ETF query prompt
Use cases
- 01Review historical BTC ETF flows
- 02Compare ETH ETF flows by ticker
- 03Ask an LLM for ETF flow summaries
MCP support
The server exposes `get_etf_flow` for historical BTC or ETH ETF flow data and provides the `etf_flow_prompt` prompt to guide queries.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEETF Flow MCP
An MCP server that delivers crypto ETF flow data to power AI agents' decision-making.
Features
- Unified Tool: The
get_etf_flowtool dynamically fetches historical ETF flow data for BTC or ETH. - Markdown Table Output: Leverages pivot tables to present data with ETF tickers as columns, dates as rows, and a total column for summed flows.
- Prompt Guidance: Includes a prompt (
etf_flow_prompt) to streamline LLM interactions for user-friendly queries.
Prerequisites
- Python: Version 3.10 or higher.
- uv: A fast Python package and project manager (install instructions).
- CoinGlass API Key: Obtain a key from CoinGlass.
- Claude Desktop: Optional, for interactive querying.
- Git: For cloning the repository.
Installation
-
Clone the Repository:
git clone https://github.com/kukapay/etf-flow-mcp.git cd etf-flow-mcp -
Set Up with uv: Install dependencies using
uv:uv sync
Usage
Integrating with Claude Desktop
-
Configure Claude Desktop: Add the server to
claude_desktop_config.json(located in~/Library/Application Support/Claudeon macOS or%APPDATA%\Claudeon Windows):{ "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" } } } }Replace
/absolute/path/to/etf-flow-mcp/cli.pywith the full path tocli.py. -
Restart Claude Desktop: Verify the hammer icon appears in the Claude Desktop UI to confirm the server is loaded.
-
Query Examples:
- "Show me the latest BTC ETF flow data in a table"
- "Get the ETH ETF flow history"
Example Output
-
BTC ETF Flow:
| Date | GBTC | IBIT | FBTC | ARKB | BITB | BTCO | HODL | BRRR | EZBC | BTCW | Total | |------------|-----------|-----------|-----------|-----------|-----------|----------|----------|----------|----------|----------|-----------| | 2025-04-24 | 0 | 327300000 | 0 | 97700000 | 10200000 | 7750000 | 0 | 0 | 0 | 0 | 442200000 | | 2025-04-23 | 0 | 643200000 | 124400000 | 129500000 | -15200000 | 0 | 5300000 | 0 | 0 | 0 | 917700000 | | 2025-04-22 | 65100000 | 193500000 | 253800000 | 267100000 | 76700000 | 18300000 | 6500000 | 0 | 10600000 | 0 | 912700000 | | 2025-04-21 | 36600000 | 41600000 | 88100000 | 116100000 | 45100000 | 0 | 11700000 | 0 | 10100000 | 0 | 381300000 | | 2025-04-18 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | -
ETH ETF Flow:
| Date | ETHE | GETH | ETHA | ETHW | FETH | ETHV | EZET | CETH | QETH | Total | |------------|-----------|----------|-----------|----------|-----------|----------|----------|----------|----------|-----------| | 2025-04-24 | -6600000 | 18300000 | 40000000 | 5100000 | 0 | 2600000 | 0 | 4100000 | 0 | 63550000 | | 2025-04-23 | 0 | 6400000 | -30300000 | 0 | 0 | 0 | 0 | 0 | 0 | -23900000 | | 2025-04-22 | 0 | 0 | 0 | 6100000 | 32700000 | 0 | 0 | 0 | 0 | 38800000 | | 2025-04-21 | -25400000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | -25400000 | | 2025-04-18 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | | 2025-04-17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
License
This project is licensed under the MIT License.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.