MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Data access / search

NythosX Market Data

Crypto/stock trade setups, signal bias, levels, regime, odds. Free track record. Pay per call, x402.

Checks passed
11 / 22

3 failed · 8 not measured

Median response
287 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
11

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
220
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 287 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name nythosx-market-data.

  • Pass
    Lists tools

    tools/list returned 11 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 287 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 287 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Fail
    Parameters documented

    12 of 18 parameters have a description (67%). The bar is 80%.

  • Fail
    Safety hints

    11 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-10-20T15:13:17.466756Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using NythosX Market Data

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http nythosx-market-data https://market.nythosx.com/mcp

Capabilities

Tools 11

arm_price_trigger

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 timeout per attempt, until your endpoint returns 2xx); after 5 failed attempts delivery is marked failed — check status free with get_trigger_status (REST: GET /api/v1/triggers/status?id=) to see delivery_attempts/last_error. Expires after ttl_hours (default 168, max 720); cancel any time before it fires, free, with disarm_price_trigger (REST: POST /api/v1/triggers/cancel with {id, secret}) — the arm fee is not refunded, it paid for the monitoring already done. Costs $0.02 USDC per call (x402).

Discovered
disarm_price_trigger

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.

Discovered
get_free_snapshot

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_support_resistance ($0.005 each) for other symbols or deeper history.

Discovered
get_market_regime

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 own it gives context, not a trade direction. symbol uses the same trend/volatility thresholds for every instrument, so regime readings are directly comparable across symbols (e.g. BTC 'high' and SOL 'high' mean the same ATR% bucket). Costs $0.005 USDC per call (x402).

Discovered
get_signal_bias

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 target-before-stop odds, get_market_regime ($0.005) is trend/volatility only. Costs $0.01 USDC per call (x402).

Discovered
get_support_resistance

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 strength and touch count mean a more reliable level. Costs $0.005 USDC per call (x402).

Discovered
get_target_probability

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 charged; if volatility can't be computed from recent candles it returns 502 and is not charged. Costs $0.005 USDC per call (x402).

Discovered
get_track_record

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 if nothing has been graded yet for that filter.

Discovered
get_trade_plan

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_bias ($0.01) or get_market_regime ($0.005) — cheaper. Costs $0.03 USDC per call (x402).

Discovered
get_trigger_status

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 payment never settled.

Discovered
list_symbols

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}.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected287 ms11