Price Data MCP server

<!-- mcp-name: io.github.wesseltl/price-data-mcp -->

price-data-mcp

Give your AI agent live market prices. An MCP server that lets an agent look up the current price, the full symbol list, and recent price history for 200+ coins.

An LLM's knowledge is frozen at training time, so it can't answer "what's BTC trading at right now?". This closes that gap. It returns market data only. It never gives a trading signal or predicts direction.

What your agent can do with it

You: What's Bitcoin trading at, and how has it moved over the last few hours?

Agent (calls getprice("BTC") and getcandles("BTC", "1h", 6)):

Bitcoin is at $65,047. Over the last 6 hours it's held between $65,020 and $65,132 on rising volume.

The agent fetches real numbers instead of guessing from stale training data.

Quickstart

pip install "hyperliquid-price-mcp[mcp]"

Add it to your MCP client (e.g. Claude Desktop's config):

{
  "mcpServers": {
    "market-prices": { "command": "hyperliquid-price-mcp" }
  }
}

Restart your client. The agent now has four tools.

The tools

Example candle:

{"open_ms": 1786201200000, "open": 65104.0, "high": 65132.0,
 "low": 65020.0, "close": 65047.0, "volume": 409.43, "trades": 7014}

Also usable from plain Python

from price_data_mcp import prices

prices.get_price("BTC")                # {'symbol': 'BTC', 'price': 65047.5, 'as_of': ...}
prices.get_candles("ETH", "1h", 24)    # last 24 hourly candles
prices.list_symbols()                  # ['AAVE', 'ADA', 'APE', ...]

How it works

Prices come from the public Hyperliquid info API. The core fetching module (pricedatamcp/prices.py) uses the Python standard library only (no dependencies), so it's small and easy to audit. The mcp extra is only needed to run the server.

Tests

python -m unittest discover -s tests     # network is mocked, runs fully offline

Scope

A market-data source for agents. It reports prices and history. It does not give trading signals, predict where the price is going, or place orders.

License

MIT