Name: AuraStream
Author: UnbiasedAlpha

AuraStream MCP

Historical market, macro, positioning and alt data from 46 sources through one API.

Grade A Local · stdio API key 3 tools v0.1.7 MIT

No reviews yet by UnbiasedAlphaPyPI 2,284 Runs on your machine, nothing hosted

100/100

trust score

downloads a day

local

runs on your machine

163

downloads in 30d

What it does

AuraStream is a historical data API for quants. This server lets Claude, ChatGPT and other MCP clients pull data from 46 sources through one tool, so you can ask for the data in plain words instead of writing the requests.

Market data: OHLCV bars from Binance, Bybit, Kraken, Hyperliquid and other crypto exchanges, Yahoo Finance, and your own Oanda, Alpaca or Polygon account, plus funding rates, trades and order books where the source has them.

Data that is hard to find elsewhere: EU net short positions with the holder's name (France, Netherlands, Spain), every USDA WASDE report since 2010, FRED with every revision, SEC insider trades, 13F holdings and fails-to-deliver, CFTC Commitments of Traders, and trade, weather and travel data.

Try: "How have hedge funds positioned in gold futures since 2020?" or "Who is short Ubisoft, and by how much?"

All data is historical, not real-time. The free plan includes 500 calls a month with no credit card: get a key at aurastream.unbiased-alpha.com/sign-up

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'AURASTREAM_API_KEY=${AURASTREAM_API_KEY}' --transport stdio aurastream-mcp '--' uvx aurastream-mcp

# 2 — ask your agent for something these tools do
#   list_sources, get_timeseries, get_latest

It needs AURASTREAM_API_KEY: this reads it from your environment, so export it first.

AuraStream costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

UnbiasedAlpha1 server

1 category

All 1 server

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts AuraStream as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads AURASTREAM_API_KEY (Your AuraStream API key. A free plan (500 calls/month, no card) is at https://aurastream.unbiased-alpha.com) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx AURASTREAM_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'AURASTREAM_API_KEY=${AURASTREAM_API_KEY}' --transport stdio aurastream-mcp '--' uvx aurastream-mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: AURASTREAM_API_KEY — Your AuraStream API key. A free plan (500 calls/month, no card) is at https://aurastream.unbiased-alpha.com. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

3 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

List the AuraStream data sources: what each covers, ticker format, intervals, supported dtypes, optional source-specific parameters, the fields returned when they are not OHLCV, and whether provider credentials are needed and configured. Free to call (does not use the API allowance).

Takes no parameters.

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…

Parameter	Type	Required	Notes
source		yes	Data source id, see list_sources.
tickers	array	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; weather sources take 'latitude,longitude', e.g. ['48.
start	string	yes	Start date, YYYY-MM-DD.
end	string	yes	End date, YYYY-MM-DD.
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).
dtype		no	'bars' everywhere; binance also 'funding' (futures); oanda also 'orderbook'/'positionbook'; alpaca also 'trades'/'quotes'; yahoo also 'earnings'.
price_type	string	no	oanda: M mid (default), A ask, B bid. cityindex: MID (default), BID or ASK.
instrument	string	no	binance: spot (default) or futures (USD-M perpetuals). kraken: futures (default) or spot. firstrate: stock (default), etf, futures, fx, index, crypto or options. lyra: option (default) or perp.
continuous_contracts	boolean	no	firstrate futures only: true (default) for continuous series, false for one series per contract.
ticktype	string	no	kraken futures only: trade (default), mark or spot (index) price.
assetclass	string	no	alpaca only.
category	string	no	bybit only: linear (default) or inverse.
feed	string	no	alpaca stocks only: iex (default) or sip (consolidated tape).
adjustment	string	no	alpaca stock bars only: raw (default), split, dividend or all.
indicator	string	no	tradingeconomics (required): indicator name, e.g. 'gdp', 'inflation rate'.
metric	string	no	nemeton (required): signal name, e.g. cumulative-depth, orderbook-pressure, spread (list_sources has all).
level	integer	no	nemeton only: order book depth the metric is computed over (default 1000).
db	string	no	sdmx (required): provider ID, e.g. BIS, ECB, ESTAT, IMF, OECD.
filters	object	no	nasdaq only: column filters per table, e.g. {"QDL/FON": {"contract_code": "967654"}}.
assetcol	string	no	nasdaq only: one series per value of this column, e.g. contract_code.

Return the most recent N bars (OHLCV) per ticker, without having to pick dates.

Parameter	Type	Required	Notes
source		yes	Data source id, see list_sources.
tickers	array	yes	Tickers in the source's own format.
interval		no	Bar size, e.g. 1h or 1d.
bars	integer	no	How many of the most recent bars to return per ticker.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install AuraStream or to call it, at any volume.

ATrust score 100 / 100

Release 0.1.7 · scanned 28 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score100

Findings0 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationsource

Surface digestc0ff2ca954e0021ade0d4bf5a86ec670218e3ebc4bddfbeb5f8c032af2b850f7

Score vectorthreat 100 → client 100

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (3 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
list_sources	no tags
get_timeseries	untrusted-input	untrusted-input: keyword "fetch"
get_latest	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestc0ff2ca954e0021a

Scanned2026-10-28

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.