Aperiodic - Market Data for RWA & Crypto

Aperiodic is point-in-time market data for perpetual futures on Binance, OKX and Hyperliquid: crypto, and real-world assets such as tokenized stocks, ETFs, commodities and FX, including Hyperliquid HIP-3 markets.

It covers 19 metrics datasets (order flow, L1/L2 book liquidity, derivatives and OHLCV) and the raw data behind them: trades, top-of-book quotes, mark and index price, funding and open interest. With Aperiodic, your AI can: Find datasets and symbols, and see how far back each series goes.

MCP connector

Server URL: https://aperiodic.io/mcp
Login: API key
Protocol: MCP 2025-11-25
Instructions: Aperiodic serves point-in-time crypto market microstructure metrics (order flow, liquidity, L1/L2 book, derivatives) and the raw trades, quotes and derivatives data behind them, for Binance, OKX and Hyperliquid perpetuals, as Parquet. These tools are a control plane: they return small JSON (catalog, schema, statistics, handles). returns signed Parquet URLs, never the rows; load them in your own code (load_with has a Polars snippet) and do not paste data into the conversation. Without code execution, use summarize for statistics, correlations or a resampled series. Flow: , then , then if you need another symbol, then or summarize. gives your code the real-time WebSocket connection. search and fetch read the catalog as documents. Without an API key or sign-in, every metrics dataset is free for the Binance BTC-USDT perpetual, 5m, May 2025, and raw:trades for June 2025. A call beyond that with no credential is answered with HTTP 401, so the client can sign the user in and retry. Plans: https://aperiodic.io/pricing.

Tools

Reads data8

Skills

None in the store listings or on the server

MCP connector

Server URL

https://aperiodic.io/mcp

API key

Protocol

MCP 2025-11-25

Instructions

Aperiodic serves point-in-time crypto market microstructure metrics (order flow, liquidity, L1/L2 book, derivatives) and the raw trades, quotes and derivatives data behind them, for Binance, OKX and Hyperliquid perpetuals, as Parquet. These tools are a control plane: they return small JSON (catalog, schema, statistics, handles). returns signed Parquet URLs, never the rows; load them in your own code (load_with has a Polars snippet) and do not paste data into the conversation. Without code execution, use summarize for statistics, correlations or a resampled series. Flow: , then , then if you need another symbol, then or summarize. gives your code the real-time WebSocket connection. search and fetch read the catalog as documents. Without an API key or sign-in, every metrics dataset is free for the Binance BTC-USDT perpetual, 5m, May 2025, and raw:trades for June 2025. A call beyond that with no credential is answered with HTTP 401, so the client can sign the user in and retry. Plans: https://aperiodic.io/pricing.