Categories › Business & Finance › Market data, stocks & crypto
Crypto & RWA microstructure, liquidity, flow and raw data via Parquet; live metrics via WebSocket.
Remote server: your requests and data go to aperiodic.io. Claude Code: claude mcp add --transport http aperiodic-market-data https://aperiodic.io/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_datasets — Every Aperiodic dataset, metrics and raw: id, category, the plan that unlocks it, a one-line description, field count, and whether this calldescribe_dataset — Field definitions, intervals, exchanges with their start dates, the plan needed and the free preview window for one dataset.find_symbols — Symbol ids on one exchange matching every word of the query, at most 50: crypto and RWA perpetuals alike. Ids look like "perpetual-BTC-USDT:get_data — A handle to one slice of a dataset, not the data: signed Parquet URLs (valid one hour), schema, row counts, per-column min/max/nulls from thsummarize — Statistics worked out on our side, for when you can't run code: per-column count, mean, std, quantiles and range ("stats"), a correlation malive_feed — How your own code connects to the real-time WebSocket feed of metrics datasets (raw data is not streamed): its URL, the subscribe frame for search — Keyword search over every dataset, its fields, the categories and the plans guide. Returns ids, titles and URLs; read one with fetch.fetch — The full text of one search result: a dataset with all its fields, a category, or the plans guide.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.