Pyth Pro MCP Server
Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"mcp": {
"url": "https://mcp.pyth.network/mcp"
}
}
}远程端点
https://mcp.pyth.network/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢get_symbols(asset_type, limit, offset, query)
List available Pyth Pro price feeds. Use this FIRST to discover what feeds exist before calling get_latest_price, get_historical_price, or get_candlestick_data. Filter by asset_type (crypto, equity, fx, metal, rates, commodity, funding-rate) or search by name/symbol. Returns feed metadata including pyth_lazer_id (needed for get_historical_price), symbol, asset_type, and exponent.
输入模式
{
"type": "object",
"properties": {
"asset_type": {
"type": "string",
"enum": [
"crypto",
"fx",
"equity",
"metal",
"rates",
"commodity",
"funding-rate"
],
"description": "Filter by asset type: crypto, fx, equity, metal, rates, commodity, funding-rate"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"default": 50,
"description": "Results per page (default 50, max 200)"
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0,
"description": "Pagination offset (default 0)"
},
"query": {
"type": "string",
"description": "Text filter (e.g. 'BTC', 'gold', 'AAPL')"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢convert_date_to_timestamp(date_string)
Convert a date string to Unix timestamp for use with get_historical_price and get_candlestick_data. Use this tool when you need to compute timestamps — do not calculate Unix timestamps manually. Accepts ISO 8601 dates (e.g. '2026-01-01', '2026-01-01T12:00:00Z'). Returns seconds, microseconds, ISO 8601, and whether the date is within the available data range (April 2025 onward).
输入模式
{
"type": "object",
"properties": {
"date_string": {
"type": "string",
"minLength": 1,
"maxLength": 64,
"description": "Date to convert. Must be ISO 8601 / RFC 3339 with timezone (e.g. '2026-01-01T00:00:00Z', '2026-01-01'). Bare dates without timezone are interpreted as UTC."
}
},
"required": [
"date_string"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_candlestick_data(access_token, channel, from, resolution, symbol, ...)
Fetch OHLC candlestick data for a symbol. Pass your Pyth Pro `access_token` to authenticate the request. Use for charting, technical analysis, backtesting. IMPORTANT: The symbol must be the full name from get_symbols including the asset type prefix (e.g. 'Crypto.BTC/USD', 'Equity.US.AAPL', 'FX.EUR/USD') — never use bare names like 'BTC/USD'. Historical data is available from April 2025 onward — do not request timestamps before that. Resolutions: 1/5/15/30/60 minutes, 120/240/360/720 (multi-hour), D (daily), W (weekly), M (monthly). Timestamps are Unix seconds. Timestamp reference (Unix seconds): 2025-04-01 (earliest available) = 1743465600 2026-01-01 = 1767225600 2026-06-01 = 1780272000 Always double-check your timestamp math — year-boundary errors are common.
输入模式
{
"type": "object",
"properties": {
"access_token": {
"type": "string",
"minLength": 1,
"description": "Pyth Pro access token used to authenticate the request. Get one at https://docs.pyth.network/price-feeds/pro/acquire-access-token"
},
"channel": {
"type": "string",
"pattern": "^(real_time|fixed_rate@\\d+ms)$",
"description": "Override default channel (e.g. fixed_rate@200ms, real_time, fixed_rate@50ms, fixed_rate@1000ms)"
},
"from": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Start time (Unix seconds)"
},
"resolution": {
"type": "string",
"enum": [
"1",
"5",
"15",
"30",
"60",
"120",
"240",
"360",
"720",
"D",
"W",
"M"
],
"description": "Candle size: 1, 5, 15, 30, 60 (minutes), 120, 240, 360, 720 (hours), D (daily), W (weekly), M (monthly)"
},
"symbol": {
"type": "string",
"minLength": 1,
"description": "Full symbol from get_symbols including asset type prefix (e.g. 'Crypto.BTC/USD', not 'BTC/USD')"
},
"to": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "End time (Unix seconds)"
}
},
"required": [
"from",
"resolution",
"symbol",
"to"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_historical_price(access_token, channel, price_feed_ids, symbols, timestamp)
Get price data for specific feeds at a historical timestamp. Pass your Pyth Pro `access_token` to authenticate the request. Use get_symbols first to find feed IDs or symbols. If both price_feed_ids and symbols are provided, only price_feed_ids are used. Accepts Unix seconds, milliseconds, or microseconds (auto-detected). Historical data is available from April 2025 onward — do not request timestamps before that. The timestamp is internally converted to microseconds and aligned (rounded down) to the channel rate — e.g. for fixed_rate@200ms, it must be divisible by 200,000μs. Prices are integers with an exponent field — human-readable price = price * 10^exponent. Pre-computed display_price fields are included for convenience. Timestamp reference: 2025-04-01 (earliest available) = 1743465600 2026-01-01 = 1767225600 2026-06-01 = 1780272000 Always double-check your timestamp math — year-boundary errors are common.
输入模式
{
"type": "object",
"properties": {
"access_token": {
"type": "string",
"minLength": 1,
"description": "Pyth Pro access token used to authenticate the request. Get one at https://docs.pyth.network/price-feeds/pro/acquire-access-token"
},
"channel": {
"type": "string",
"pattern": "^(real_time|fixed_rate@\\d+ms)$",
"description": "Override default channel (e.g. fixed_rate@200ms, real_time, fixed_rate@50ms, fixed_rate@1000ms)"
},
"price_feed_ids": {
"type": "array",
"items": {
"type": "integer",
"exclusiveMinimum": 0
},
"maxItems": 50,
"description": "Numeric feed IDs from get_symbols"
},
"symbols": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50,
"description": "Full symbol names from get_symbols including asset type prefix (e.g. ['Crypto.BTC/USD', 'Equity.US.AAPL/USD'])"
},
"timestamp": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Unix timestamp — accepts seconds, milliseconds, or microseconds (auto-detected by magnitude)"
}
},
"required": [
"timestamp"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_latest_price(access_token, channel, price_feed_ids, properties, symbols)
Get the most recent real-time price for one or more feeds. Requires an `access_token` parameter (get one at https://docs.pyth.network/price-feeds/pro/acquire-access-token). Use get_symbols first to find symbols or feed IDs. IMPORTANT: symbols must be the full name including asset type prefix (e.g. 'Crypto.BTC/USD', not 'BTC/USD'). If both price_feed_ids and symbols are provided, only price_feed_ids are used. Prices are integers with an exponent field — human-readable price = price * 10^exponent. Pre-computed display_price fields are included for convenience.
输入模式
{
"type": "object",
"properties": {
"access_token": {
"type": "string",
"minLength": 1,
"description": "Pyth Pro access token. Get one at https://pyth.network/pricing"
},
"channel": {
"type": "string",
"pattern": "^(real_time|fixed_rate@\\d+ms)$",
"description": "Override default channel (e.g. fixed_rate@200ms, real_time, fixed_rate@50ms, fixed_rate@1000ms)"
},
"price_feed_ids": {
"type": "array",
"items": {
"type": "integer",
"exclusiveMinimum": 0
},
"maxItems": 100,
"description": "Numeric feed IDs from get_symbols"
},
"properties": {
"type": "array",
"items": {
"type": "string"
},
"description": "Properties to return. Default: price, bestBidPrice, bestAskPrice, confidence, exponent, publisherCount"
},
"symbols": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 100,
"description": "Full symbol names from get_symbols including asset type prefix (e.g. ['Crypto.BTC/USD', 'Equity.US.AAPL/USD'])"
}
},
"required": [
"access_token"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据