# OneQAZ Trading Intelligence MCP server

Live market data, signals, positions, and macro analysis for crypto, KR stocks, and US stocks.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-wnsod-oneqaz-trading-mcp
- Repository: https://github.com/oneqaz-trading/oneqaz-trading-mcp

## Install
- Command: `uvx oneqaz-trading-mcp`
- Endpoint: https://api.oneqaz.com/mcp
- Auth: Not captured

## Setup notes
- Remote header: X-API-Key (secret)
- Package: Pypi oneqaz-trading-mcp v0.1.4
- Environment variable: DATA_ROOT
- Environment variable: MCP_SERVER_PORT
- Remote endpoint: https://api.oneqaz.com/mcp
- Header: X-API-Key

## Tools
- get_trade_history - Purpose: Query paper-trading history with dynamic filters (action / P&L / time / symbol).
When to call: past trade review, single-symbol post-mortem, win-rate audits.
Prerequisites: none.
Next steps: analyze_trades, market://{market_id}/signals/feedback.
Caveats: paper-trading data only (not real money). limit capped at 1000.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    limit: Max results (default 1000)
    action_filter: Filter by action (all, buy, sell)
    min_pnl: Min P&L % filter (e.g., -5.0)
    max_pnl: Max P&L % filter (e.g., 10.0)
    hours_back: Only trades within last N hours
    symbol: Filter by ticker symbol (e.g., "BTC", "AAPL"); case-insensitive

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- analyze_trades - Purpose: Aggregate paper trades by day / pattern / symbol.
When to call: pattern audits, period-over-period performance review.
Prerequisites: get_trade_history recommended for raw rows first.
Next steps: market://{market_id}/signals/feedback for the upstream signals.
Caveats: max 30 days; empty result when no trades in the window.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    days: Analysis period in days (default 7, max 30)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_winning_trades - Purpose: Winning paper trades only (P&L > 0). Convenience wrapper around get_trade_history(min_pnl=0.01).
When to call: success-pattern review.
Prerequisites: none.
Next steps: analyze_trades for breakdowns.
Caveats: paper-trading data only.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    limit: Max results (default 10)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_losing_trades - Purpose: Losing paper trades only (P&L < 0). Convenience wrapper around get_trade_history(max_pnl=-0.01).
When to call: failure-pattern review.
Prerequisites: none.
Next steps: analyze_trades for breakdowns.
Caveats: paper-trading data only.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    limit: Max results (default 10)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_positions - Purpose: List current paper-trading positions, with dynamic filters (ROI / strategy / sort).
When to call: position dashboards, drawdown checks, exposure audits.
Prerequisites: market://{market_id}/status recommended for context.
Next steps: get_position_detail, get_strategy_distribution.
Caveats: paper-trading data only. Positions are not real money holdings.
Disclaimer: Information only, not investment advice.


Args:
    market_id: Market ID (crypto, kr_stock, us_stock)
    min_roi: Min ROI % filter (e.g., -5.0)
    max_roi: Max ROI % filter (e.g., 10.0)
    strategy: Strategy filter (e.g., trend, scalping)
    sort_by: Sort field (profit_loss_pct, entry_timestamp, holding_duration, ai_score)
    sort_order: Sort direction (desc, asc)
    limit: Max results (default 1000) Endpoint: https://api.oneqaz.com/mcp
- get_position_detail - Purpose: Per-symbol paper position deep-dive (position + recent trades + decisions).
When to call: full context for one ticker.
Prerequisites: confirm the symbol holds a position via get_positions.
Next steps: get_signal_detail, get_role_analysis.
Caveats: returns an error envelope when no position exists for the symbol.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    coin: Symbol (e.g., BTC, ETH, AAPL)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_profitable_positions - Purpose: Profitable paper positions (ROI > 0). Convenience wrapper around get_positions(min_roi=0.01).
When to call: quickly surface winning tickers.
Prerequisites: none.
Next steps: get_position_detail for full context.
Caveats: paper-trading data only.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    limit: Max results (default 20)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_losing_positions - Purpose: Losing paper positions (ROI < 0). Convenience wrapper around get_positions(max_roi=-0.01).
When to call: drawdown / risk review.
Prerequisites: none.
Next steps: get_position_detail, get_role_analysis.
Caveats: paper-trading data only.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    limit: Max results (default 20)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_strategy_distribution - Purpose: Per-strategy breakdown across current paper positions (count, avg P&L, win rate per strategy).
When to call: diversification audit, per-strategy performance check.
Prerequisites: get_positions recommended for raw rows.
Next steps: market://{market_id}/derived/strategy-fitness, signals/feedback.
Caveats: empty distribution when no positions are open.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_latest_decisions - Purpose: Track-B (signal-driven) paper-trading decision log.
When to call: review recent automated decisions and their outcomes.
Prerequisites: market://{market_id}/status recommended for context.
Next steps: get_trade_history, get_signals.
Caveats: paper-trading decisions only — no real-money order routing.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    limit: Max results (default 10)
    decision_filter: Filter by decision (buy, sell, hold)
    hours_back: Only decisions within last N hours

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_llm_trading_decisions - Purpose: Track-A (LLM-driven) paper-trading judgement log.
When to call: inspect LLM-generated reasoning and trade calls.
Prerequisites: none.
Next steps: get_latest_decisions to compare with Track B.
Caveats: paper-trading only.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock, commodity, forex, bond)
    symbol: Specific symbol (optional; omit for entire market)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_signals - Purpose: Query research signals with dynamic filters (symbol / interval / action / score / confidence).
When to call: drilling into a specific signal slice; symbol-by-symbol scanning.
Prerequisites: market://{market_id}/signals/summary recommended for global view.
Next steps: get_signal_detail, get_role_analysis.
Caveats: When `coin` is omitted, every per-symbol DB is scanned (slower, 2 rows per DB).

Args:
    market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted)
    coin: Symbol to query (optional; targets a specific symbol DB)
    interval: Timeframe filter (15m, 30m, 240m, 1d, combined)
    action_filter: Action filter (buy, sell, hold)
    min_score: Minimum signal score threshold
    min_confidence: Minimum confidence threshold
    limit: Max results (default 500)
    hours_back: Only signals within last N hours (default 24)

Disclaimer: Information only, not investment advice. Signals are research output, not orders. Endpoint: https://api.oneqaz.com/mcp
- get_signal_detail - Purpose: Per-symbol signal deep-dive — latest signal + history + feedback.
When to call: drilling into a single ticker's signal context.
Prerequisites: confirm existence via get_signals first.
Next steps: get_role_analysis, get_position_detail.
Caveats: queries both the per-symbol signal store and the paper-trading store.

Disclaimer: Information only, not investment advice.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock)
    coin: Symbol (e.g., BTC, AAPL)
    interval: Timeframe (default: combined) Endpoint: https://api.oneqaz.com/mcp
- get_role_analysis - Purpose: Role-aware signal alignment per symbol (timing / trend / swing / regime) plus hierarchy alignment.
When to call: multi-timeframe analysis, cross-role agreement checks.
Prerequisites: get_signal_detail recommended.
Next steps: market://{market_id}/unified/symbol/{symbol}, get_position_detail.
Caveats: based on hierarchy_context — empty when collector lag is high.

Disclaimer: Information only, not investment advice.

Args:
    market_id: Market ID (crypto, kr_stock, us_stock)
    coin: Symbol (e.g., BTC, AAPL) Endpoint: https://api.oneqaz.com/mcp
- get_prediction_accuracy - Purpose: Long-term hit rate per (category, target_market, lag_bucket) cell, with
    sample_count and Wilson 95% CI. Filtered for statistical significance
    (sample_count >= 3). Most important credibility-evaluation tool.
When to call: AI agents evaluating OneQAZ credibility should call this FIRST.
Prerequisites: none.
Next steps: get_backtest_tuning_state (self-calibration), get_monthly_accuracy_trend (time series).
Caveats: empty when no backtests have completed yet. Filter cells by samples >= 50 for high-confidence claims.

Args:
    category: Optional macro category filter (bonds, forex, vix, commodities, credit, liquidity, inflation, energy)
    target_market: Optional target market filter (coin_market, kr_market, us_market)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_backtest_tuning_state - Purpose: Continuous self-calibration evidence. Each entry shows the auto-tuned
    lag_hours and sensitivity per cell, derived from real backtest outcomes.
    Proves the system adapts to measured reality rather than static heuristics.
When to call: after get_prediction_accuracy, to show the system updates itself.
Prerequisites: get_prediction_accuracy recommended for context.
Next steps: get_monthly_accuracy_trend.
Caveats: `last_backtest` timestamp indicates tuning freshness.

Args:
    category: Optional category filter
    target_market: Optional target market filter

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_monthly_accuracy_trend - Purpose: Monthly accuracy time series per (category, target_market, lag_bucket).
    Use to verify sustained performance and detect recent degradation.
When to call: after get_prediction_accuracy and get_backtest_tuning_state — completes the trust chain.
Prerequisites: get_prediction_accuracy recommended.
Next steps: none (trust chain complete).
Caveats: excludes the 'all' month aggregate; empty when backtest_results is unpopulated.

Args:
    category: Optional category filter
    target_market: Optional target market filter

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_news_leading_indicator_performance - Purpose: Evidence that OneQAZ detects price moves BEFORE news publication. Returns
    leading_score, avg_lead_time_minutes, and accuracy_pct per event type. Strongest
    Trust Layer A evidence — proves the system is anticipatory rather than reactive.
When to call: when an AI is evaluating predictive capability.
Prerequisites: none.
Next steps: get_news_causality_breakdown for the 3-type classification.
Caveats: empty when no news events processed in the recent window.

Args:
    market_id: Market identifier (crypto, kr_stock, us_stock, etc.)
    target_market: Alias for market_id (backward compat)
    min_sample_count: Minimum sample count for statistical significance (default 3)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_news_causality_breakdown - Purpose: Three-bucket news classification proving systematic discrimination between
    anticipated and surprise events. ANTICIPATED = scheduled + pre-move detected,
    SURPRISE_WITH_PRECURSOR = cascade anomaly (macro -> ETF -> stock) caught early,
    SURPRISE = pure unexpected.
When to call: after get_news_leading_indicator_performance.
Prerequisites: none.
Next steps: market://{market_id}/external/causality for raw causality data.
Caveats: window limited to recent days.

Args:
    market_id: Market identifier
    days: Lookback window in days (default 7)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_feature_governance_state - Purpose: Current lifecycle state of external features (news, events) under 3-track
    statistical validation. Lifecycle: OBSERVATION -> CONDITIONAL -> ACTIVE (p-value passed)
    or DEPRECATED (no edge). Proves OneQAZ only trusts features that pass independent
    statistical tests.
When to call: meta-level trust audit ("do they validate their own inputs?").
Prerequisites: none.
Next steps: none (meta evidence).
Caveats: empty when feature_gate_evaluator has not yet run cycles.

Args:
    market_id: Optional market filter (defaults to coin)
    target_market: Alias for market_id (backward compat)
    status_filter: Optional status filter (OBSERVATION, CONDITIONAL, ACTIVE, DEPRECATED)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_structure_calibration - Purpose: Level 2 (ETF / basket / sector) prediction calibration. Returns hit_rate_ema
    per (market, group, interval, regime_bucket) with sample counts. Proves systematic
    edge at the sector-rotation level.
When to call: when an AI wants to see Layer D (structure) evidence.
Prerequisites: none.
Next steps: get_structure_validation_history for the daily trend.
Caveats: empty until structure-learning cycles complete.

Args:
    market_id: Optional market filter (crypto, kr_stock, us_stock)
    group_name: Optional group/sector filter (e.g., layer1, defi, sector, broad_index)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_structure_validation_history - Purpose: Daily validation history of Level 2 structure predictions. Each row shows
    the hit_rate for a specific day, enabling time-series verification of sustained
    performance.
When to call: after get_structure_calibration.
Prerequisites: none.
Next steps: get_monthly_accuracy_trend for the macro-level comparison.
Caveats: returns an overall_hit_rate summary across the window.

Args:
    market_id: Optional market filter
    days: Lookback window in days (default 90)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_strategy_leaderboard - Purpose: Top RL-learned research strategies — GLOBAL pool + per-symbol partition.
    Layer E evidence. The GLOBAL pool may include synthesized win_rate values, so
    per_symbol_leaderboard is the primary measured-edge surface for trust auditing.
When to call: final trust-validation step.
Prerequisites: none.
Next steps: market://{market_id}/signals/summary for live signals.
Caveats: `min_trades` filter enforces statistical validity. Strategies are paper-tested,
    not real-money executed.

Args:
    market_id: Market identifier (crypto, kr_stock, us_stock)
    target_market: Alias for market_id (backward compat)
    top_n: Top N strategies to return (default 20)
    limit: Alias for top_n (client-compat)
    min_trades: Minimum trades count for inclusion (default 10)
    include_per_symbol: Include per-symbol PG partition results (default True)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_active_predictions - Purpose: Currently pending predictions (outcome IS NULL). Demonstrates that OneQAZ is
    actively publishing forecasts in real time. Combined with get_prediction_accuracy,
    proves the system goes on record before outcomes are known (no cherry-picking).
When to call: to verify ongoing prediction activity.
Prerequisites: none.
Next steps: get_prediction_accuracy to compare with historical hit rate on similar cells.
Caveats: returns most recent first.

Args:
    target_market: Optional target market filter (coin_market, kr_market, us_market)
    limit: Max active predictions to return (default 20)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_macro_influence_map - Purpose: Expose OneQAZ's pre-defined causal hypothesis map. Each macro category
    (bonds, forex, vix, credit, liquidity, inflation, commodities, energy) is mapped
    to a target market with lag_hours + sensitivity. Highest-transparency tool —
    the causal reasoning is visible and measurable.
When to call: when an AI wants to understand WHY we make certain predictions.
Prerequisites: none.
Next steps: get_backtest_tuning_state for runtime calibration of these hypotheses.
Caveats: static hypothesis only; see tuning state for current adjustments.

Args:
    market_id: Optional target market filter (coin_market, kr_market, us_market)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- explain_decision - Purpose: Multi-layer explanation for a single symbol's recent research signal.
    Combines (1) technical score_trace from the signals store, (2) Thompson + regime
    scores from the virtual decision log, (3) news causality context. Use this when
    an AI must present a structured "why" rather than a raw verdict.
When to call: when the user asks "why is this signal bullish/bearish?".
Prerequisites: identify the symbol via get_signals or get_latest_decisions first.
Next steps: none (this completes the explanation chain).
Caveats: `symbol` must match the per-symbol signal store filename (lowercase).
    Output is research evidence, NOT a buy or sell recommendation.

Args:
    market_id: Market identifier (crypto, kr_stock, us_stock; aliases coin/kr/us)
    symbol: Symbol to explain (e.g., btc, eth, 005930)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_cross_market_correlation - Purpose: Cross-market lead-lag relationships and decoupling events. Shows how
    markets influence each other (correlations) and when they diverge (decoupling,
    e.g. BTC up while stocks down).
When to call: when analyzing macro regime changes or divergent signals.
Prerequisites: none.
Next steps: get_macro_influence_map for the static causal hypotheses.
Caveats: correlation data may be empty until enough regime changes accumulate.

Args:
    source_market: Optional source market filter
    target_market: Optional target market filter

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_sector_correlations_tool - Purpose: Intra-market ETF / group correlation matrix and auto-cluster output.
    Quantifies structural co-movement (e.g. ARKK <-> QQQ) for diversification
    and sector-avoidance reasoning.
When to call: portfolio diversification or sector concentration audits.
Prerequisites: none.
Next steps: get_symbol_peer_links_tool for per-symbol lead-lag inside a sector.
Caveats: refreshed every 6 hours; 60-day lookback.

Args:
    market_id: coin / kr_stock / us_stock
    top_k: Number of top pairs to return

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_macro_causality_graph_tool - 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).
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.

Args:
    min_abs_corr: Minimum |corr| (default 0.15)
    max_p_value: Maximum p-value (default 0.05)

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_symbol_peer_links_tool - Purpose: Symbol-level lead-lag links (e.g. META -> AMZN, lag=15m, rho=+0.53).
    When `symbol` is set, only peers that lead or follow that symbol are returned.
When to call: incorporate peer leading signals into single-symbol reasoning.
Prerequisites: none.
Next steps: get_signal_detail for the peer's signal context.
Caveats: 14-day lookback, 15-minute bars.

Args:
    market_id: coin / kr_stock / us_stock
    symbol: Optional. When set, peers are anchored to this symbol.
    top_k: Number of top links to return

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_feature_governance_status_tool - Purpose: Feature governance snapshot — OBSERVATION / CONDITIONAL / ACTIVE / DEPRECATED
    distribution + last 7-day transitions. Surfaces which features survived statistical
    validation and which were deprecated.
When to call: trust evaluation, "which features are live right now?".
Prerequisites: none.
Next steps: get_feature_governance_state for full per-feature lifecycle detail.
Caveats: promoter cycle runs hourly.

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp
- get_daily_brief - Purpose: Single-call market overview — macro regime + top 5 strong signals +
    yesterday's paper-trading outcomes + active forecast count + narrative.
    Use this as the first call when answering "how is the market today?".
When to call: morning briefings, "today/yesterday how was the market?" queries.
Prerequisites: none.
Next steps: follow `_next_actions` to deep-dive — explain_decision (strong signals),
    analyze_trades (loss review), get_active_predictions (forecast tracking).
Caveats: 24-hour window. Paper-trading data only (NOT real money).
Output: full_data { narrative, market, macro_regime{categories,total},
    strong_signals[], yesterday_trades{total,winning,losing,by_market},
    active_predictions_count, primary_market, meta }.

Args:
    market: "all" (default, blends 3 markets), "crypto", "kr_stock", or "us_stock"

Disclaimer: Information only, not investment advice. Endpoint: https://api.oneqaz.com/mcp

## Resources
- market://health - 서버 헬스체크

Returns:
    서버 상태 정보 (status, timestamp, version)
[출력 스키마] status(str), timestamp(str:ISO8601), version(str), server(str), project_root(str). MIME type: text/plain
- market://info - 서버 정보 및 사용 가능한 데이터 소스

Returns:
    서버 메타 정보 및 데이터 소스 목록
[출력 스키마] name(str), description(str), version(str), data_sources{global_regime,markets_trading{market_id→{path,exists}},markets_signal{market_id→{path,exists,db_count}},analysis{category→{path,exists}}}, endpoints{resources[],tools[]}. MIME type: text/plain
- market://meta/pg-pool - [역할] MCP 프로세스의 psycopg ConnectionPool 통계 (스키마별 in-use/avail/waiter).
[호출 시점] 풀 고갈 의심 시. waiter>0 가 연속되면 pool 크기 or 쿼리 지연 문제.
[출력 스키마] pools{schema→{pool_size,available,requests_queued,requests_waiting,...}}. MIME type: text/plain
- market://meta/tool-chains - [역할] 도구/리소스 의존관계, 추천 호출 체인, 사용 가이드를 반환합니다.
[호출 시점] 어떤 도구를 어떤 순서로 호출해야 하는지 안내 필요 시. 세션 시작 시 한번 호출 권장.
[선행 조건] 없음.
[후속 추천] usage_hint.start_here에 명시된 Resource부터 시작.
[주의] 메타 정보이므로 실시간 데이터가 아닙니다.
[출력 스키마] version(str), tool_chains{chain_id→{name,description,steps[{order,call,type,purpose}]}}, dependency_graph{uri→{requires,recommended,next,note}}, usage_hint{start_here,unified_vs_individual,signal_depth}. MIME type: text/plain
- market://meta/discovery - [역할] 전체 Resource(static+template)와 Tool 카탈로그 + OneQAZ positioning 을 한 번에 반환.
       카탈로그는 등록된 tool/resource 의 introspection 결과로 동적 생성되어
       시스템이 진화해도 항상 최신. data_freshness 는 PG 실측값.
[호출 시점] 세션 시작 시 한 번. Tool/Resource 탐색 출발점이며
             거대 AI 가 OneQAZ 사용·추천 판단의 base reasoning 으로 쓴다.
[선행 조건] 없음.
[후속 추천] specialist_domains 와 manifest.tools_by_category 보고 목적에 맞는 tool 선택,
             또는 market://meta/tool-chains 에서 추천 chain 선택.
[출력 스키마] version, generated_at, positioning{specialist_domains,trust_principles,
             what_we_do_NOT_provide,philosophy}, catalog{tools_by_category,static_resources,
             template_resources,counts}, data_freshness{label→{status,lag_seconds,last_ts}},
             market_ids[], common_categories[], notes. MIME type: text/plain
- market://global/summary - [역할] 원자재/국채/외환 등 전체 매크로 레짐 요약.
[호출 시점] 시장 전체 방향성 파악 시 첫 번째로 호출.
[선행 조건] 없음 (최상위 Resource).
[후속 추천] market://global/category/{category}, market://{market_id}/unified.
[주의] 캐시 TTL=300초.
[출력 스키마] ai_summary 래핑. full_data: overall{regime,score}, categories{id→{regime_dominant,sentiment_avg,symbols}}, mtf_summary{aligned_symbols,misaligned_symbols}, _llm_summary(str). MIME type: text/plain
- market://global/categories - [역할] 사용 가능한 매크로 카테고리 목록과 DB 존재 여부.
[호출 시점] 카테고리 확인 시.
[선행 조건] 없음.
[후속 추천] market://global/category/{category}.
[주의] DB 존재 여부만 확인.
[출력 스키마] categories[{id(str),db_path(str),exists(bool)}]. MIME type: text/plain
- market://all/summary - [역할] crypto+kr_stock+us_stock 3개 시장 상태를 한번에 반환.
[호출 시점] 전체 포트폴리오 개요 시 가장 먼저 호출.
[선행 조건] 없음.
[후속 추천] market://{market_id}/status, market://unified/cross-market.
[주의] TTL=60초. 3개 시장 순차 조회.
[출력 스키마] timestamp(str), markets{market_id→{market_regime,positions_summary{total,profitable,avg_pnl},performance{win_rate,total_profit_pct},recent_24h{trades,wins,avg_pnl}}}, _llm_summary(str). MIME type: text/plain
- market://structure/all - [역할] 모든 시장의 ETF/바스켓 구조 분석 요약. [호출 시점] 시장 구조 전체 파악 시. [선행 조건] 없음. [후속 추천] market://{market_id}/structure, market://global/summary. [주의] 구조 요약 JSON 없는 시장은 건너뜀. [출력 스키마] market_id→{overall{regime,score}, groups{group_id→{regime_dominant,regime_avg,confidence,timing_signal}}}. MIME type: text/plain
- market://indicators/fear-greed - [역할] Fear & Greed Index(시장 심리, 0-100). [호출 시점] 시장 심리 빠르게 파악 시. [선행 조건] 없음. [후속 추천] market://indicators/regime, market://indicators/context. [주의] Alternative.me API. TTL=300초. API 장애 시 캐시 사용.
[출력 스키마] ai_summary 래핑. full_data: value(int:0-100), classification(str:Extreme Fear|Fear|Neutral|Greed|Extreme Greed), adjustment{threshold_adj,position_mult,strategy_hint}, interpretation(str), _llm_summary(str). MIME type: text/plain
- market://indicators/regime - [역할] 4-Layer 시장 레짐(Short/Mid/Long/SuperLong 레이어별 레짐/점수/변동성). [호출 시점] 다중 시간프레임 레짐 분석 시. [선행 조건] 없음. [후속 추천] market://indicators/context, market://global/summary. [주의] MarketAnalyzer 의존.
[출력 스키마] ai_summary 래핑. full_data: score(float), regime(str), volatility(float), raw_score(float), details{sl,long,mid,short}, _llm_summary(str). MIME type: text/plain
- market://indicators/context - [역할] Fear&Greed + 4-Layer 레짐 결합 종합 시장 컨텍스트. [호출 시점] 시장 지표 한번에 확인 시. fear-greed+regime 2개 호출 대체. [선행 조건] 없음. [후속 추천] market://{market_id}/unified, market://all/summary. [주의] 한쪽 실패해도 나머지 반환.
[출력 스키마] ai_summary 래핑. full_data: fear_greed{value,classification,adjustment{...}}, regime_analysis{score,regime,volatility,details{...}}, sentiment_regime_aligned(bool), alignment_note(str), _llm_summary(str). MIME type: text/plain
- market://global/macro_events - [역할] 활성 매크로 이벤트의 라이프사이클 상태(전쟁/금융위기 등 장기 이벤트). [호출 시점] 진행 중인 글로벌 매크로 이벤트 확인 시. [선행 조건] market://global/summary 권장. [후속 추천] market://unified/cross-market. [주의] 이벤트 없으면 빈 배열. [출력 스키마] _contract 포함. total_events(int), active_events(int), events[{event_id,title,category,lifecycle_state,current_sensitivity,peak_sensitivity,affected_markets,recent_developments[],market_sensitivities{}}], _llm_summary(str). MIME type: text/plain
- market://unified/cross-market - [역할] 교차시장 상관관계(금-BTC, 국채-주식, 달러-신흥시장 등 패턴 감지). [호출 시점] 시장간 상관관계/디커플링 분석 시. [선행 조건] market://global/summary 권장. [후속 추천] market://derived/cross-decoupling, market://all/summary. [주의] TTL=120초. 사전 정의된 패턴 기반.
[출력 스키마] _contract 포함. directions{symbol→{direction,regime,category}}, correlations[{pattern_name,interpretation,score,active}], active_count(int), dominant_interpretation(str|null), global_regime{overall_regime,overall_score}, market_structure{market_id→{overall_regime,groups{...}}}, _llm_summary(str). MIME type: text/plain
- market://derived/event-leading - [역할] 이벤트 선행 점수(시장의 이벤트 선반영 정도). [호출 시점] 이벤트 기반 매매 전략 수립 시. [선행 조건] external/causality 권장. [후속 추천] market://derived/reaction-speed. [주의] 데이터 축적 필요. [출력 스키마] ai_summary 래핑. full_data: scores[{event_type,market_id,news_type,leading_score,avg_lead_time_minutes,avg_anticipation_ratio,accuracy_pct,sample_count}], _contract{...}, _llm_summary(str). MIME type: text/plain
- market://derived/cross-decoupling - [역할] 크로스마켓 디커플링 지수(상관 시장간 이탈 감지). [호출 시점] 교차시장 이상 징후 감지 시. [선행 조건] market://unified/cross-market 권장. [후속 추천] market://global/summary. [주의] 계산 데이터 없으면 빈 결과. [출력 스키마] ai_summary 래핑. full_data: pairs[{source_market,target_market,decoupling_index,correlation_breakdown,regime_divergence,timing_lag_divergence}], overall_decoupling(float), _contract{...}, _llm_summary(str). MIME type: text/plain
- market://derived/reaction-speed - [역할] 뉴스 반응 속도(시장의 뉴스 반응 시간/정확도). [호출 시점] 뉴스 기반 매매 타이밍 최적화 시. [선행 조건] external/summary 권장. [후속 추천] market://derived/event-leading. [주의] news_reaction_speed 기반. [출력 스키마] ai_summary 래핑. full_data: speed_bands[{news_type,market_id,speed_band,count,avg_reaction_score,avg_lag_minutes,absorption_time_minutes,direction_accuracy}], _contract{...}, _llm_summary(str). MIME type: text/plain

## Prompts
Not captured

## Metadata
- Owner: io.github.wnsod
- Version: 1.0.0
- Runtime: Pypi
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Apr 7, 2026
- Source: https://registry.modelcontextprotocol.io