Universal Quant Tournament MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ALPACA_PAPER | No | Whether to use Alpaca Paper trading ("true") or live trading ("false"). | true |
| RAPIDAPI_KEY | Yes | Your RapidAPI key used to authenticate requests to the Universal Quant Strategy Tournament API. | |
| ALPACA_KEY_ID | No | Alpaca Paper/Live API key ID used for Alpaca order execution. | |
| RAPIDAPI_HOST | Yes | The RapidAPI host for the tournament API, e.g. universal-quant-strategy-tournament.p.rapidapi.com. | |
| ALPACA_SECRET_KEY | No | Alpaca Paper/Live API secret key used for Alpaca order execution. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_multi_strategy_tournamentC | Performs a top-down institutional market evaluation: (1) Pulls live ForexFactory high/medium impact macro events (forex_factory_macro_calendar) and checks forexfactory.com/calendar for scheduled news risk, (2) Classifies Higher-Timeframe (HTF) structure and market regime, (3) Filters historical and live signals by user-definable session liquidity hours using bar timestamps, (4) Requires price-action candle confirmation (Engulfing, Rejection Pinbar, or Displacement close) on the entry bar, and (5) Evaluates 8 quantitative strategies via a two-stage Out-of-Sample walk-forward backtest. |
| run_monte_carlo_stress_testB | Runs a 1,000-path Bayesian Out-of-Sample Monte Carlo simulation and Half-Kelly risk assessment on a strategy's entry, stop-loss, take-profit, and validated win rate. |
| build_universal_bracket_orderB | Generates risk-sized, leverage-aware bracket order payloads for Alpaca (Equities/Crypto), MetaTrader 5 (Forex/CFD/Metals with 100 oz Gold lot sizing and USD/JPY cross-rate conversion), and Tradovate/TradingView Webhooks (Futures). |
| sync_or_execute_local_mt5A | Connects directly to the user's open Windows MetaTrader 5 desktop terminal to either (1) pull live broker OHLCV candles and account equity/leverage, or (2) execute an approved mt5_mql5_order_send bracket order after explicit user confirmation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool maps to a distinct stage: tournament evaluation, Monte Carlo stress testing, bracket payload construction, and MT5 sync/execution. The only potential overlap is between building an order and executing it, but the descriptions clarify the boundary; the tournament tool is broad but still a single evaluation operation.
All names are snake_case and verb-led, mostly following a predictable verb_noun pattern. The compound verb 'sync_or_execute' and very long descriptive names are minor deviations, but the convention remains readable and consistent.
Four tools is compact and each maps to a real workflow stage. It is slightly thin for a 'universal' quant server because several capabilities are bundled into the tournament tool, but the count is reasonable and not excessive.
The core workflow of evaluate, stress-test, construct bracket order, and execute is covered, including multi-broker payload generation and local MT5 access. Gaps remain around order lifecycle management such as modify/cancel/close/status and strategy/result management, but core workflows are present.