Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
NythosX Market Data is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
90/100
tool-list score
11
tools declared
remote
at its publisher
—
calls last 7d
What it does
Crypto/stock trade setups, signal bias, levels, regime, odds. Free track record. Pay per call, x402.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http nythosx-market-data-mcp https://market.nythosx.com/mcp
# 2 — ask your agent for something these tools do
# list_symbols, get_track_record, get_free_snapshot and 8 more
NythosX Market Data costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NYAll 2 servers
nythosx2 servers
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http nythosx-market-data-mcp https://market.nythosx.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
11 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.
List supported symbols, timeframes, the per-call USDC price of each paid tool (not asset prices — call get_signal_bias etc. for those), and the payment network (free, read-only, no auth required, no extra rate limit). Returns {symbols, timeframes, network, networks, asset, free: [tool names], tools: [{name, price}], docs}.
No parameter schema on file.
Graded accuracy of every published signal bias: hit rate by confidence, bias and symbol, Wilson intervals, Brier score, independent samples (free, cached 15 min, one full report per call — no pagination). Omit symbol for the all-symbols report; pass it to filter to one instrument. Check this before paying for get_signal_bias, to see whether its track record supports trusting the call. Returns 404
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | no | Instrument symbol |
Market regime (trend, volatility, RSI, ATR%) and nearest support/resistance for BTC and ETH only, refreshed every 15 minutes (free). Returns {price, regime, nearestSupport, nearestResistance}. Pick this over the paid siblings when you just need a quick read on BTC/ETH; use get_signal_bias ($0.01) for a trade direction, get_trade_plan ($0.03) for full setup levels and odds, or get_market_regime/get
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | — |
Status of a trigger armed with arm_price_trigger (free). Returns {id, status, symbol, direction, price, created_at, expires_at, fired_at, fired_price, delivered_at, cancelled_at, delivery_attempts, last_error}, where status is one of armed, fired_delivering, delivered, delivery_failed (after 5 webhook attempts), expired or cancelled (via disarm_price_trigger). Returns 404 if id is unknown or its p
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Trigger id returned by arm_price_trigger, format trg_<24 hex chars> |
Cancel a trigger armed with arm_price_trigger, before it fires (free). Requires both id and secret — the same token returned once at arm time and used to verify the webhook's HMAC signature — as proof of ownership. The $0.02 arm fee is not refunded; it paid for the monitoring already done. Returns 404 for an unknown id/secret pair, 409 if the trigger already fired or was already cancelled.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| secret | string | yes | — |
Complete trade setup in one call. Bundles signal bias, regime, levels, setup (entry, stop, target, R:R), odds of target-before-stop and of touching target within 7 days, time-to-target, invalidation, and track record. tf sets candle size and lookback (5m=1H to 1w=1Y); shorter is faster but noisier. Neutral bias returns odds of hitting resistance before support. For one piece only, call get_signal_
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Instrument symbol |
| tf | string | no | Candle timeframe |
Signal bias with setup levels and invalidation. Rules-based bias (bullish/lean_bullish/neutral/lean_bearish/bearish) with score, confidence, setup, weighted factors, invalidation. tf sets candle size and lookback (5m=1H to 1w=1Y): shorter is faster but noisier, longer is slower but higher-conviction. Accuracy free at /api/v1/track-record. Quick direction + one setup; get_trade_plan ($0.03) adds ta
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Instrument symbol |
| tf | string | no | Candle timeframe |
Support and resistance map. Up to five support and five resistance levels from clustered daily swing pivots, high-volume nodes and round numbers, each with kind, strength (1-5) and touch count, plus the nearest level on each side. Computed from the last 30 daily candles (cached 15 minutes). Use nearestSupport/nearestResistance as stop-loss/take-profit anchors for a position already open; higher st
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Instrument symbol |
Trend and volatility regime. Market regime from the last 24 hours of hourly candles (cached 5 minutes): trend (up / down / range, EMA50 vs EMA200), volatility bucket (low / normal / high / extreme by ATR%), RSI, EMAs. Use this for risk sizing or entry timing (e.g. avoid new entries while volatility is 'extreme') alongside get_signal_bias for direction and get_support_resistance for levels — on its
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Instrument symbol |
Probability of reaching a target price. Probability that the price closes beyond a target within 1, 7 and 30 days, and the approximate probability of touching it, from 14-day ATR volatility (normal approximation; touch ~ 2x close-beyond by the reflection principle). symbol must be one of the supported list (see list_symbols) and target must be a positive number, or the call returns 400 and is not
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Instrument symbol |
| target | number | yes | Target price in the quote currency |
Arm a price trigger with webhook delivery. Arms a single-fire price trigger. NythosX checks the price every minute and POSTs a JSON event to your HTTPS webhook on the first crossing: {event:"trigger.fired", id, symbol, direction, price, fired_price, fired_at}, signed with HMAC-SHA256 (header X-NythosX-Signature: sha256=<hex> over the raw body, key = returned secret). Retries up to 5 times (8s time
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Instrument symbol |
| direction | string | yes | — |
| price | number | yes | — |
| webhook_url | string | yes | Public HTTPS URL that receives the signed trigger.fired event |
| ttl_hours | integer | no | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install NythosX Market Data or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 90 / 100
Release 1.1.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
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 score90
Findings0 threat · 2 capability
Capabilityhigh
Coveragemanifest
Verificationnot in this report
Surface digest678ef13b8a43bedec806ed9a656a2b3d2198e119657d527ec41c483230311311
Score vectorthreat 100 → client 90
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_symbols | no tags | |
| get_track_record | no tags | |
| get_free_snapshot | no tags | |
| get_trigger_status | no tags | |
| disarm_price_trigger | sensitive-source | sensitive-source: parameter "secret" |
| get_trade_plan | no tags | |
| get_signal_bias | no tags | |
| get_support_resistance | no tags | |
| get_market_regime | no tags | |
| get_target_probability | no tags | |
| arm_price_trigger | external-sink | external-sink: keyword "webhook", parameter "webhook" |
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.
disarm_price_trigger → arm_price_trigger
A sensitive-source → external-sink chain exists: disarm_price_trigger → arm_price_trigger.
Supply chain and provenance
Integrityfirst-seen
Surface digest678ef13b8a43bede
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.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.0.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish NythosX Market Data can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.