"Pearson" matching MCP tools:

• GetCorrelatedStocksA

  equiblesA

  Get the stocks whose daily price returns are most (or least) correlated with one stock — Pearson correlation of daily log returns on comparable raw closes (dividends excluded), computed over the trading days both stocks priced, never on raw price levels. Scope picks the candidate universe: Industry (default) ranks the subject's direct industry peers; Sector widens to sibling industries; Market ranges across the ~1,500 largest listed names and surfaces cross-industry relationships the classification misses (suppliers, commodity proxies). direction=Negative flips the ranking to the strongest inverse movers (hedge candidates). Candidates need a $100M market cap and enough overlapping trading days with the subject; each row reports the observation count behind its coefficient. Use GetStockPrices for the underlying series and the screener for fundamentals-based peer sets.

  ConnectorNo auth

• test_formulaA

  ensotradeA

  Invent a formula over EnsoTrade's data, and get back whether it actually predicts forward returns — validated on a holdout split, not just fit to the whole window. `formula` is a math expression combining any of the fields listed in fetch_series' docstring (for the same `timeframe`) with +, -, *, /, **, %, unary +/-, and abs/min/max/ sqrt/log/log1p/exp/sign/clip/mean/std, e.g. "ofi1 * vpin - dofi / 2" or "sign(qi) * sqrt(abs(obi))". No other Python is executed — this runs through a restricted, default-deny expression evaluator, not eval(). `timeframe="scalp"` (default, WDE order-flow, second-scale): `horizon` is which forward return to correlate against — ret_1s_bp, ret_5s_bp, ret_30s_bp, or ret_60s_bp. `hours` max 720 (30 days). `timeframe` = "15m"/"1h"/"4h"/"1d" for day/swing strategies (real OKX candles, always available): use `horizon_bars` instead of `horizon` — the forward % return N candles ahead (e.g. horizon_bars=4 on timeframe="1h" = predicting the move 4 hours out). `hours` max ~1500 bars worth; a small `hours` still fetches at least 150 bars (the minimum needed for a meaningful 70/30 split) rather than failing outright, so the actual window tested can be wider than requested for a small `hours` value. Either mode needs enough rows that a 70/30 split leaves >=150 total. Returns train (first 70% chronologically) and holdout (untouched final 30%) Spearman/Pearson correlations plus a verdict: 'validated' only if holdout |spearman| >= 0.15 AND same-signed as train — this guards against keeping a formula that only looked good by chance on one slice of data. ALSO returns, computed on the holdout portion only: - `net`: risk-adjusted performance AFTER trading costs — sharpe, sortino, max_drawdown_pct, calmar, ann_return_pct, ann_volatility_pct, win_rate_pct, profit_factor. Sharpe is annualized and corrected for overlapping horizons (a horizon spanning N bars sampled every bar is subsampled to non-overlapping periods first, which removes the ~sqrt(N) inflation naive Sharpe would show). - `gross`: the same metrics before costs, so the cost drag is visible. - `costs`: fee/slippage assumptions, position_changes (turnover), total_cost_pct. Costs are charged on position CHANGES only, not per bar — holding one side is cheap, flipping every bar is not. - `cost_verdict`: survives_costs / marginal_after_costs / killed_by_costs / unknown. IMPORTANT: `verdict` is a correlation test and says nothing about profitability; a formula can be 'validated' and still be killed_by_costs. Check both. - `walk_forward`: the same formula re-scored on 5 consecutive time blocks, with consistency_pct (share of blocks agreeing on direction) and a `stable` flag. An edge that passes one holdout but flips sign between blocks is usually noise. `fee_bp`/`slippage_bp` are per side, defaulting to 5bp taker + 2bp slippage; raise them for illiquid coins or a worse fee tier. Iterate: call this repeatedly with different formulas, keep what validates AND survives costs, discard what doesn't. Requires an EnsoTrade Pro API key.

  ConnectorNo auth

• bcb_correlacaoA

  Banco Central do Brasil (BCB) — SGS Time Series MCP ServerA

  Calcula a correlação estatística entre 2 a 5 séries temporais do BCB no MESMO período (dataInicial e dataFinal obrigatórias), par a par. Quando usar: para medir se dois indicadores se movem juntos (ex.: dólar e Selic, IPCA e IGP-M). Quando NÃO usar: para comparar a variação de cada série lado a lado use bcb_comparar; para uma série só use bcb_variacao. Métodos: `pearson` (padrão) mede relação LINEAR entre os valores; `spearman` mede relação MONÓTONA entre os postos e é o adequado quando a relação não é reta ou quando uma série fica parada em platôs (taxa de juros entre reuniões do Copom). Base: `nivel` (padrão) correlaciona os valores; `variacao` correlaciona a mudança percentual de um ponto para o outro — prefira `variacao` quando as duas séries têm tendência (preço, índice, estoque), porque o nível de duas séries crescentes tem correlação alta só porque ambas crescem com o tempo. Retorna: `periodo`, `metodo`, `base`, `series`, `alinhamento` (datas cruzadas, completas e parciais), `pares` (cada um com codigoA/codigoB, `coeficiente` entre -1 e 1, `n`, `descartados` e `interpretacao` em prosa), `erros` e `derivacao`. Coeficiente que não pode ser calculado vem `null` com `motivo` — nunca 0, que significaria ausência medida de relação. Periodicidades diferentes são RECUSADAS, não avisadas: cruzar uma série diária com uma mensal por data casa só as datas coincidentes (cerca de 7 por ano) e produziria um coeficiente sobre esse punhado; informe `frequencia` para harmonizar todas na mesma grade antes de correlacionar. Correlação não estabelece causalidade. Comportamento: consome a API pública SGS do Banco Central do Brasil — sem autenticação, chave de API ou cadastro, e sem limite de requisições divulgado (uso é best-effort). Em falha transitória ou timeout a chamada é repetida automaticamente (até 3 tentativas, backoff exponencial); persistindo o erro, retorna `isError: true` com mensagem em português (HTTP 404 = série inexistente ou sem dados no período solicitado). O resultado vem como JSON tanto em texto quanto em `structuredContent` (conforme o outputSchema); datas no formato dd/MM/yyyy e valores numéricos (ponto decimal).

  ConnectorNo auth

• tf_premium_correlation_matrixA

  terminalfeedA

  Pre-computed macro correlation matrix for AI trading and portfolio agents. Returns 30-day Pearson correlations on daily simple returns for 4 FRED series (US gov, public domain): 10Y treasury yield, 2Y treasury yield, trade-weighted USD index, and WTI crude oil. Output includes both a pairs array (sorted by absolute r descending) and an NxN matrix object for easy lookup. Each pair tagged with relationship strength (negligible / weak / moderate / strong) and direction (positive / negative). Costs 2 credits ($0.04 USDC). 30-min cache. Bearer auth required. Note: crypto and equity legs were removed 2026-07-23 for market-data licensing compliance.

  ConnectorNo auth

• compute_correlation_matrixA

  kwantA

  Compute the pairwise return-correlation matrix for a list of tickers. Fetches each ticker's daily history over range, converts it to daily returns, and computes the pairwise Pearson correlation (aligned on shared dates). Requires at least two tickers; tickers that cannot be fetched are dropped and noted in warnings (at least two must survive). Returns the standard envelope; values holds range, the tickers used, and matrix — a nested dict {rowTicker: {colTicker: correlation}} with a 1.0 diagonal. (paid: $0.0100/call)

  ConnectorNo auth

• post_calc_statsA

  webbersites-x402-data-apiA

  Exact descriptive statistics — LLMs cannot reliably sum 200 numbers; this can. POST {values:[…]} for count/sum/mean/median/stddev/percentiles; {x:[],y:[]} for Pearson correlation + linear regression; {rows:[…], field} for object arrays — or {collection, field?} to run stats DIRECTLY ON YOUR DATASTORE collection (the paying wallet is the identity; reading extends its life 30 days). Up to 100k values, Kahan-summed. ($0.005 per call, paid via x402)

  ConnectorNo auth

• get_correlation_mapA

  mcpA

  Get the cross-ticker ENTANGLEMENT map — which S&P 500 names the quantum model expects to co-move. "Entanglement" here is the Pearson correlation of the quantum model's own FORECAST return paths (mode="forecast", the default) — a forward-looking, model-implied co-movement signal. It is NOT a claim about realised market correlation, and you must not present it as one. mode="realized" instead correlates trailing daily returns (the consensus baseline) for comparison. Two ways to read it: • Diversification / risk lens — high entanglement means two names are effectively one trade. Stacking five mutually-entangled longs is one position with 5x the size, not a diversified book. • Pairs / divergence lens — strongly NEGATIVE entanglement flags names the model expects to move oppositely (hedge or pairs candidates). Honesty: every number is computed from real persisted scan output. Tickers with no usable forecast curve are listed in `missing`, never imputed. The universe is the top_n names ranked by 3mo forecast growth. Args: ticker: Optional. When set, returns only that ticker's row (correlations + most_entangled + most_divergent), not the full matrix. Case-insensitive. top_n: Universe size — top-N tickers by 3mo forecast growth (2–100, default 25). Smaller = tighter LLM payload. horizon: Forecast horizon to correlate — "1mo", "3mo", "6mo", or "1y" (default "3mo"). mode: "forecast" (model-implied, default) or "realized" (trailing-returns baseline). basis: Forecast-mode correlation basis. "mean" (default) correlates the single mean forecast curve. "ensemble" correlates across the full forecast band envelope (q05/q25/mean/q75/q95) and averages the per-band correlations — this surfaces TAIL co-movement (two names whose stress/downside paths move together) that the mean curve understates, which is exactly when diversification matters most. Ignored in realized mode. The method label becomes "quantum_forecast_ensemble" so you never conflate the two. Returns the full-matrix shape (tickers / matrix / top_pairs / missing) by default, or the single-ticker shape when `ticker` is given. Carries method, basis, generated_at, scan_date, and disclaimer in the payload.

  ConnectorNo auth

• correlationA

  Moltline Data DeskA

  Compute the Pearson correlation between two numeric series. FREE. Typical input {"x": [1, 2, 3, 4], "y": [2.1, 3.9, 6.2, 8.1]} returns {"pearson_r": 0.999, "r_squared": 0.998, "interpretation": "very strong positive correlation", "caution": "..."}. Use when two equal-length numeric series may move together. Reports association only, never causation. Not for a single series over time (growth_rates). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need two equal-length series of 3+ values"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• correlationA

  Moltline Data DeskA

  Compute the Pearson correlation between two numeric series. FREE. Typical input {"x": [1, 2, 3, 4], "y": [2.1, 3.9, 6.2, 8.1]} returns {"pearson_r": 0.999, "r_squared": 0.998, "interpretation": "very strong positive correlation", "caution": "..."}. Use when two equal-length numeric series may move together. Reports association only, never causation. Not for a single series over time (growth_rates). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need two equal-length series of 3+ values"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• get-person-activity-toolA

  CoderbudsA

  What one person on the team has actually been doing, over a recent window (default 8 weeks). Answers "is Dave still shipping?" or "what has Sam been working on?" with three counts read together rather than one in isolation: pull requests opened and merged, reviews given to other people, and production deploys triggered — plus a week-by-week rollup, the busiest days, and the longest quiet run. Lead with the `headline`. A pull request count on its own supports the wrong conclusion: someone who opened 5 pull requests and gave 70 reviews is carrying the team's review load, not coasting. The headline says which of those it is. Identify the person by name or provider login ("dave", "Dave Smith", "@dsmith"). When the reference is ambiguous or unknown the tool returns the team's member names in `candidates` instead of guessing — ask which one rather than reporting activity for the wrong person. `not_captured` lists what this data cannot see (commits, review comment volume, ticket assignment, anything outside git). Repeat those limits when the answer is "this person looks quiet" — never present an absence of pull requests as an absence of work.

  ConnectorOAuth

• cross_signal_correlateA

  Trillboards DOOH AdvertisingB

  Discover correlations between different signal types. Example: relationship between ad fill rate and audience attention for QSR venues. Queries the cross_signal_insights table for pre-computed correlations, or computes ad-hoc correlations from the observation_stream when no pre-computed insight exists. WHEN TO USE: - Understanding relationships between different sensing signals - Finding which audience behaviors correlate with business outcomes - Discovering hidden patterns (e.g., crowd_energy vs purchase_intent) - Validating hypotheses about audience-venue-time relationships RETURNS: - data: Correlation analysis with: - signal_a, signal_b: The two signals being correlated - correlation_r: Pearson correlation coefficient (-1 to +1) - correlation_r2: R-squared (proportion of variance explained) - p_value: Statistical significance - sample_count: Number of data points used - effect_size: Cohen's d effect size - confidence_interval_lower, confidence_interval_upper: 95% CI bounds - insight_summary: Human-readable interpretation - metadata: { computation_method, window, filters_applied } - suggested_next_queries: Related correlation analyses to explore EXAMPLE: User: "Is there a correlation between audience attention and ad fill rate at QSR venues?" cross_signal_correlate({ signal_a: "attention_score", signal_b: "ad_fill_rate", filters: { venue_type: "restaurant_qsr" } }) User: "How does crowd energy relate to purchase intent during lunch hours?" cross_signal_correlate({ signal_a: "crowd_energy", signal_b: "purchase_intent", filters: { daypart: "lunch" } })

  ConnectorNo auth

• cross_assetA

  Bitget MCP — Crypto, DeFi & Macro Market IntelligenceB

  Rolling cross-asset correlation: BTC vs Gold, DXY, Nasdaq, S&P500, 10Y Treasury yield, EUR/USD, oil, VIX, and any other Yahoo Finance symbol. Returns Pearson correlation (full period + rolling window) with trend and interpretation. No API key required.

  ConnectorNo auth

• get_correlationsA

  mcpA

  Call this when the user asks how correlated two coins are, for decorrelated pairs, or how tightly alts track BTC. Returns the 30-day rolling Pearson correlation matrix of daily returns across the top perpetuals.

  ConnectorNo auth

• get_correlationA

  SentimentFXA

  180-day Pearson correlation between daily sentiment shifts and next-day price returns for `ticker`. Returns Pearson `r`, `p_value`, `n_days` overlapping, a 95% confidence interval (Fisher z), and a categorical `strength` (strong / weak / inconclusive). Costs 1 API credit — same as GET /v1/correlation/{ticker}. Requires ≥30 overlapping day-pairs. Under that, returns a `note` field explaining what's missing so a caller can suggest waiting or switching to a higher-coverage ticker.

  ConnectorNo auth

• correlate_layersA

  ShowMeOnMapA

  Spatially join two existing workspace layers and return the Pearson correlation coefficient r, sample size n, two-sided p-value approximation, plus human-readable strength and direction labels. Pure read — no layer is added, no op is committed, no credit charge. Use this when you want a numeric answer without rendering; use add_fusion_layer when the user wants the visualization. Required: map_id, layer_a_id, layer_b_id, rationale.

  ConnectorNo auth

• personA

  Ietf DatatrackerB

  Fetch an IETF Datatracker person record by numeric ID; returns name, email addresses, and affiliated organizations.

  ConnectorNo auth

• indicator_correlationsA

  The Cracks IndexA

  Return pairwise correlations between the six indicators across areas. Computes the Pearson correlation coefficient between every pair of the six Cracks Index indicators, using each area's direction-corrected normalised score. Adds a short plain-language note naming the strongest relationship. A coefficient near +1 means areas that do well on one indicator tend to do well on the other; near -1 means the opposite. Read-only, area-level aggregates only, no personal data.

  ConnectorNo auth

• get_spot_vol_correlationA

  FlashAlphaA

  20-day and 60-day Pearson correlation between spot log-returns and ATM IV first-differences. Equity indices typically run strongly negative (vol spikes on spot down). Use to assess leverage effect strength, calibrate vanna/vol-of-vol hedges, or classify correlation regime.

  ConnectorNo auth

• arena_get_btc_macro_correlationsA

  Backtesting ArenaA

  What does Bitcoin actually move with? Pre-aggregated weekly correlations between Bitcoin and 13 macro components (Fed Net Liquidity, VIX, DXY, Real Yield 10Y, NFCI, Yield Curve, etc.). Returns quadrant_performance (BTC return stats per 2D-matrix quadrant — annualized return, vol, max drawdown, positive-period%), component_correlations (Pearson 90d/1y/5y — a window is null when the joined daily sample does not reach its start; sample_size_days is the actual basis per macro component + quartile-performance), asset_correlations (Pearson per window + per quadrant; assets: dxy plus tokenized on-venue proxies paxg = PAX Gold, spyb = S&P 500 ETF proxy, qqqb = Nasdaq-100 ETF proxy — proxies carry tracking noise vs. the underlying, and windows the vehicle history does not cover are null with data_start_date telling you why: the ETF proxies listed on Binance mid-2026, so their windows fill in over time — 90d first, ~2 months after listing), current_quadrant. Window labels are upper bounds — sample_size_days / data_start_date carry the actual basis. Historical analysis over the windows named above. [Free tier]

  ConnectorNo auth

• get_macro_causality_graph_toolA

  OneQAZ Trading IntelligenceA

  Purpose: Lag-aware causal graph between macro categories (bonds / vix / forex / credit / inflation / liquidity / commodities). Returns only statistically significant lead-lag pairs (e.g. forex -> vix 7d rho=-0.41). Triggers (casual questions too): "what happens to VIX when bonds move?", "금리 오르면 뭐가 움직여?", "which macro leads which?", "거시 지표끼리 인과관계 있어?", "does the dollar lead volatility?". When to call: assess pre-emptive cross-category impact after a macro event. Prerequisites: none. Next steps: get_macro_influence_map for category -> market impact. Caveats: Pearson-based; requires >= 30 samples; p < 0.05 filter.

  ConnectorNo auth

• get-person-toolA

  ClearPolicyA

  Get a person's profile and see which documents they have or haven't signed.

  ConnectorOAuth