Skip to main content
Glama

NexusTrade Financial MCP

by io.github.austin-starks
OverviewDiscussionsAdmin

backtest_portfolio

Submit an asynchronous historical backtest for a portfolio over a date range. Minute interval: first-look default is the last 90 inclusive calendar days; the selected range plus minute-indicator warmup cannot exceed 730 days of minute data, so a multi-year Minute window up to that span is allowed — do not emit 2010, and never split a longer span into yearly Minute jobs. Daily equity may use a long window. Set baseline_symbol to match the book — underlying ticker for single-name options (AAPL→AAPL), per-underlying baselines or equal-weight universe B&H for multi-name options; SPY only for broad equity. Returns a backtest ID immediately; poll query_backtest_status, then query_backtest_history (zero-LLM). Aurora may also use Read Backtest for an LLM narrative once complete.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
end_dateYesBacktest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs.
intervalNoTime interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation.
fee_configNoOptional fee contract keyed by AssetTypeEnum (Stock/Cryptocurrency/Option) with {amount, type: percent|dollars}. Omit for shared defaults (Option $0.65/contract). For replay of an optimizer/walk-forward study, pass that study's persisted feeConfig. Option fill slippage (OptionSlippageFraction) is not set here — engine default 0.5 applies.
start_dateYesBacktest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute.
portfolio_idNoPortfolio ID (live, paper, or chat — from fetch_portfolios or create_portfolio). Server resolves the collection automatically.
initial_valueNoStarting portfolio value (default 10000)
baseline_symbolNoBenchmark for comparisonValue (buy-and-hold of this ticker). Defaults to SPY if omitted — use SPY only for broad equity/market strategies. For single-name options, set to that underlying (AAPL options → AAPL). For multi-name options books, run separate backtests with each material underlying as baseline (AAPL for AAPL sleeve, MSFT for MSFT), or equal-weight B&H of the traded universe — do not default to SPY.
generate_eventsNoGenerate detailed event data (signals, orders, audits) during backtest. Costs 5x research tokens. Events are Mongo hot-store traces retained for 3 days. Use query_backtest_events to explore them while retained.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / end_date / description
      Previous value: -"Backtest end date (ISO format, e.g. 2024-12-31). Minute hard max is 365 days from start_date; extend a survivor in a later run instead of splitting into yearly Minute jobs."New value: +"Backtest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs."
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation."
    • changedInput schema / properties / start_date / description
      Previous value: -"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range cannot exceed 365 days. Do not use 2010-01-01 or a multi-year span on Minute."New value: +"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute."
  2. Changed3 schema fields changed
    • changedInput schema / properties / end_date / description
      Previous value: -"Backtest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs."New value: +"Backtest end date (ISO format, e.g. 2024-12-31). Minute hard max is 365 days from start_date; extend a survivor in a later run instead of splitting into yearly Minute jobs."
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."
    • changedInput schema / properties / start_date / description
      Previous value: -"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute."New value: +"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range cannot exceed 365 days. Do not use 2010-01-01 or a multi-year span on Minute."
  3. Changed3 schema fields changed
    • changedInput schema / properties / end_date / description
      Previous value: -"Backtest end date (ISO format, e.g. 2024-12-31). Minute hard max is 365 days from start_date; extend a survivor in a later run instead of splitting into yearly Minute jobs."New value: +"Backtest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs."
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation."
    • changedInput schema / properties / start_date / description
      Previous value: -"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range cannot exceed 365 days. Do not use 2010-01-01 or a multi-year span on Minute."New value: +"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute."
  4. Changed3 schema fields changed
    • changedInput schema / properties / end_date / description
      Previous value: -"Backtest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs."New value: +"Backtest end date (ISO format, e.g. 2024-12-31). Minute hard max is 365 days from start_date; extend a survivor in a later run instead of splitting into yearly Minute jobs."
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."
    • changedInput schema / properties / start_date / description
      Previous value: -"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute."New value: +"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range cannot exceed 365 days. Do not use 2010-01-01 or a multi-year span on Minute."
  5. Changed3 schema fields changed
    • changedInput schema / properties / end_date / description
      Previous value: -"Backtest end date (ISO format, e.g. 2024-12-31). Minute hard max is 365 days from start_date; extend a survivor in a later run instead of splitting into yearly Minute jobs."New value: +"Backtest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs."
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation."
    • changedInput schema / properties / start_date / description
      Previous value: -"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range cannot exceed 365 days. Do not use 2010-01-01 or a multi-year span on Minute."New value: +"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute."
  6. Changed3 schema fields changed
    • changedInput schema / properties / end_date / description
      Previous value: -"Backtest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs."New value: +"Backtest end date (ISO format, e.g. 2024-12-31). Minute hard max is 365 days from start_date; extend a survivor in a later run instead of splitting into yearly Minute jobs."
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."
    • changedInput schema / properties / start_date / description
      Previous value: -"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute."New value: +"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range cannot exceed 365 days. Do not use 2010-01-01 or a multi-year span on Minute."
  7. Changed3 schema fields changed
    • changedInput schema / properties / end_date / description
      Previous value: -"Backtest end date (ISO format, e.g. 2024-12-31). Minute hard max is 365 days from start_date; extend a survivor in a later run instead of splitting into yearly Minute jobs."New value: +"Backtest end date (ISO format, e.g. 2024-12-31). Minute allows up to 730 days of minute data from start_date, counting minute-indicator warmup; never split a longer span into yearly Minute jobs."
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 730 days of minute data (selected range plus warmup) is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year or two is a normal second backtest, not an escalation."
    • changedInput schema / properties / start_date / description
      Previous value: -"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range cannot exceed 365 days. Do not use 2010-01-01 or a multi-year span on Minute."New value: +"Backtest start date (ISO format, e.g. 2024-01-01). For interval=Minute, default first-look is the last 90 inclusive calendar days and the selected range plus minute-indicator warmup cannot exceed 730 days of minute data. Do not use 2010-01-01 on Minute."
  8. Changed1 schema field changed
    • changedInput schema / properties / interval / description
      Previous value: -"Time interval: Day or Minute (default Day). Minute is a daytrade tape — first-look 90 days, hard max 365 days."New value: +"Time interval: Day or Minute (default Day). Minute is a daytrade tape. 365 days is the HARD CAP; 90 days is only the DEFAULT when you name no dates. Name the dates you actually want — certifying a candidate on a full year is a normal second backtest, not an escalation."
  9. First observed

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral load and does well: it discloses async submission, that a backtest ID is returned immediately, the polling workflow, the 5x research-token cost of generate_events, and the 3-day Mongo hot-store retention. It does not state permission/auth requirements or failure behavior, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and the critical constraint, and most sentences earn their place by covering distinct rules. However, the 90-day default and 730-day cap are repeated from the parameter schema, adding avoidable length to an already dense paragraph.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, nested-object, no-annotation, no-output-schema tool, the description covers the call path: constraints, baseline selection, cost, retention, and the ID-plus-polling return workflow. Permission requirements and error handling are absent, keeping it just short of fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine decision logic beyond the schema: baseline_symbol should mirror the book (AAPL options → AAPL, per-underlying or equal-weight B&H for multi-name, SPY only for broad equity) and fee_config can be replayed from a study. It partly restates schema text (the 90/730-day rules), which caps this at 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Submit an asynchronous historical backtest for a portfolio over a date range.' It also names the sibling tools it hands off to (query_backtest_status, query_backtest_history, Read Backtest), so an agent can distinguish submission from polling and reporting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use guidance for interval (Day vs Minute), date spans, and baseline_symbol selection, with clear exclusions ('do not emit 2010', 'never split a longer span into yearly Minute jobs', 'do not default to SPY'). It also names the downstream alternatives and their order, leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All NexusTrade Financial MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources