AuraStream MCP

get_timeseries

Read-onlyIdempotent

Fetch historical time series data (OHLCV, funding, etc.) as CSV per ticker from multiple sources with configurable intervals and row limits for analysis and comparison.

Instructions

Fetch historical data from AuraStream and return it as a CSV table per ticker (timestamp,Open,High,Low,Close,Volume for market bars; source-specific fields otherwise, see list_sources). Long results are cut to the most recent max_rows rows per ticker, with the total row count noted. Each call uses one unit of the user's monthly AuraStream allowance. Provider credentials come from the server's environment; never ask the user to paste them.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`end`	Yes	End date, YYYY-MM-DD.
`feed`	No	alpaca only: iex (default) or sip (needs a paid Alpaca plan).
`mode`	No	gdelt search queries only: share of coverage (default), article count, or tone.
`as_of`	No	cftc only: stamp at Friday publication (release, default, no look-ahead) or Tuesday position date (report).
`dtype`	No	'bars' everywhere; binance also 'funding'/'orderbook'; oanda also 'orderbook'; alpaca also 'trades'/'quotes'; yahoo also 'earnings'.	bars
`start`	Yes	Start date, YYYY-MM-DD.
`period`	No	edgar financials only: quarter (default) or annual.
`report`	No	cftc only; default depends on the symbol.
`source`	Yes	Data source id, see list_sources.
`dataset`	No	finra: short_interest (default) or short_volume. edgar: insider (default) or financials. gdelt: themes.
`options`	No	cftc only: include options (futures-equivalent).
`tickers`	Yes	Tickers in the source's own format, e.g. ['BTCUSDT'] for binance, ['EUR_USD'] for oanda, ['SPY'] for yahoo, ['GC'] for cftc, ['gold:CH'] for hmrc. Batch several tickers in one call.
`category`	No	bybit only: linear (default) or inverse.
`concepts`	No	edgar financials only: XBRL concepts, e.g. ['Revenues'].
`interval`	No	Bar size: upper-case M is minutes, lower-case m is months (15M = 15 minutes, 1m = one month). Support varies by source (list_sources shows each source's intervals).	1d
`max_rows`	No	Max rows returned per ticker; the most recent rows are kept.
`reporter`	No	comext only: EU27_2020 (default) or a member state, e.g. DE.
`frequency`	No	fred and finnhub only: quarterly (default) or annual.
`assetclass`	No	alpaca only.
`instrument`	No	binance: spot (default) or perpetual (needed for dtype funding). kraken: futures (default) or spot.
`price_type`	No	oanda only: A ask (default), B bid, M mid.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations, it discloses CSV return shape, per-ticker structure, truncation to the most recent max_rows rows with total count noted, monthly allowance consumption, and environment-based credential handling. These are meaningful behavioral details that annotations alone do not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and return format, then covers truncation, cost, and credentials. Every sentence contributes operational information without excess.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema and 100% parameter description coverage, the description supplies the key missing operational context: CSV output, truncation behavior, allowance cost, and credential handling. An agent has enough information to call it correctly and route source-specific details to list_sources.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameter semantics are already largely handled by the schema. The description adds useful context for max_rows truncation and source-specific field discovery via list_sources, but it does not materially explain the many source-specific parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: fetch historical AuraStream data and return it as a CSV table per ticker. It also distinguishes the historical nature from the sibling get_latest and points to list_sources for source-specific fields.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly establishes this tool as the historical-data fetch path and references list_sources for source-specific fields. It does not explicitly contrast with get_latest, but the historical framing and sibling naming make the usage context clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server