{
  "markdown": "<!-- mcp-name: io.github.wesseltl/price-data-mcp -->\n\n# price-data-mcp\n\n![PyPI](https://img.shields.io/pypi/v/hyperliquid-price-mcp)\n![Python](https://img.shields.io/badge/python-3.10%2B-blue)\n![MCP](https://img.shields.io/badge/MCP-server-6E56CF)\n![License](https://img.shields.io/badge/license-MIT-green)\n![Deps](https://img.shields.io/badge/core-zero%20dependencies-lightgrey)\n\n**Give your AI agent live market prices.** An [MCP](https://modelcontextprotocol.io) server that lets\nan agent look up the current price, the full symbol list, and recent price history for 200+ coins.\n\nAn LLM's knowledge is frozen at training time, so it can't answer *\"what's BTC trading at right now?\"*.\nThis closes that gap. It returns market data only. It never gives a trading signal or predicts direction.\n\n## What your agent can do with it\n\n> **You:** What's Bitcoin trading at, and how has it moved over the last few hours?\n>\n> **Agent** *(calls `get_price(\"BTC\")` and `get_candles(\"BTC\", \"1h\", 6)`)*:\n> Bitcoin is at **$65,047**. Over the last 6 hours it's held between $65,020 and $65,132 on rising volume.\n\nThe agent fetches real numbers instead of guessing from stale training data.\n\n## Quickstart\n\n```bash\npip install \"hyperliquid-price-mcp[mcp]\"\n```\n\nAdd it to your MCP client (e.g. Claude Desktop's config):\n\n```json\n{\n  \"mcpServers\": {\n    \"market-prices\": { \"command\": \"hyperliquid-price-mcp\" }\n  }\n}\n```\n\nRestart your client. The agent now has four tools.\n\n## The tools\n\n| Tool | Returns |\n|---|---|\n| `get_price(\"BTC\")` | `{\"symbol\": \"BTC\", \"price\": 65047.5, \"as_of\": 1786204330859}` |\n| `get_prices([\"BTC\",\"ETH\"])` | current price for each, missing ones flagged |\n| `list_symbols()` | every symbol it can price (200+) |\n| `get_candles(\"BTC\",\"1h\",100)` | recent OHLCV history (`1m` … `1d`) |\n\nExample candle:\n```json\n{\"open_ms\": 1786201200000, \"open\": 65104.0, \"high\": 65132.0,\n \"low\": 65020.0, \"close\": 65047.0, \"volume\": 409.43, \"trades\": 7014}\n```\n\n## Also usable from plain Python\n\n```python\nfrom price_data_mcp import prices\n\nprices.get_price(\"BTC\")                # {'symbol': 'BTC', 'price': 65047.5, 'as_of': ...}\nprices.get_candles(\"ETH\", \"1h\", 24)    # last 24 hourly candles\nprices.list_symbols()                  # ['AAVE', 'ADA', 'APE', ...]\n```\n\n## How it works\n\nPrices come from the public [Hyperliquid](https://hyperliquid.xyz) info API. The core fetching module\n(`price_data_mcp/prices.py`) uses the **Python standard library only** (no dependencies), so it's\nsmall and easy to audit. The `mcp` extra is only needed to run the server.\n\n## Tests\n\n```bash\npython -m unittest discover -s tests     # network is mocked, runs fully offline\n```\n\n## Scope\n\nA market-data source for agents. It reports prices and history. It does **not** give trading signals,\npredict where the price is going, or place orders.\n\n## License\n\nMIT\n",
  "bytes": 2837,
  "sha": "ea44adc54b9e422c253bab584b40de898e47864faa4ee644e2bafc8357624e0e",
  "repo_slug": "wesseltl/crypto-price-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_wesseltl_crypto_price_mcp_1d9007a2/readme"
}