crypto-price-mcp
Provides live cryptocurrency prices, price history, and symbol listing tools for AI agents via the Hyperliquid API.
README
<!-- 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
get_price("BTC")andget_candles("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
| Tool | Returns |
|---|---|
get_price("BTC") |
{"symbol": "BTC", "price": 65047.5, "as_of": 1786204330859} |
get_prices(["BTC","ETH"]) |
current price for each, missing ones flagged |
list_symbols() |
every symbol it can price (200+) |
get_candles("BTC","1h",100) |
recent OHLCV history (1m … 1d) |
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
(price_data_mcp/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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.