Pyth Pro MCP Server

Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.

    How to connect

    How to connect Pyth Pro MCP Server to Claude

    The server address to paste into Claude settings:

    https://mcp.pyth.network/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect Pyth Pro MCP Server to ChatGPT

    The server address to paste into ChatGPT settings:

    https://mcp.pyth.network/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect Pyth Pro MCP Server to Cursor

    The server address to paste into Cursor settings:

    https://mcp.pyth.network/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (5)

    Raw names from tools/list. Only developers need these.

    get_symbolsList 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.
    convert_date_to_timestampConvert 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).
    get_candlestick_dataFetch 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.
    get_historical_priceGet 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.
    get_latest_priceGet 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.