Backtest360

Run several strategies on the same data and compare side by side. One quota-counted call, but compute scales with the number of strategies. If the wall-clock compute budget is exceeded, the call fails with a tool error (504) instead of returning partial results — narrow the request (fewer strategies, shorter date range, coarser frequency) and retry. Args: data_source: Shared data source (same shape as run_backtest). strategies: List of {"label": str, "strategy": {...}, "execution": {...}?} entries. Labels need not be unique or id-safe — they are echoed back verbatim in the result. include_benchmark: Add a buy-and-hold benchmark to the comparison. response_detail: Shaping level applied to each strategy's result. trades_limit: Max trades per strategy when detail is 'full'. Returns: {"strategies": [{"label", "result"}, ...], "equity_curves": {...}, "alignment"?}, each result shaped at the requested detail. When a benchmark is included, non-benchmark entries also carry "relative" (beta, alpha, information ratio, etc.). A 400/422 rejection returns {"accepted": false, "error": ...}; capacity/timeout/permission failures raise a tool error.

Compute the engine's performance metrics from a returns series. Use when the returns came from somewhere other than run_backtest (an external system, a portfolio) — backtest results already include these statistics. Args: returns: Per-bar log returns as {"dates": [...], "values": [...]} parallel arrays (ISO-8601 dates). trading_days_per_year: Required annualization factor — 252 for a daily equities calendar, 365 for 24/7 crypto. Must match the bar calendar of the returns series; a wrong value silently mis-annualizes Sharpe, volatility, and CAGR. benchmark_returns: Optional benchmark series, same shape — adds alpha/beta/capture metrics. trades: Optional trade records (entry_date, exit_date, direction, return_net, ...) — adds trade-level metrics. risk_free_rate: Annual risk-free rate as a decimal. Returns: {"stats": {...}} — the metric set the API key's plan allows. See get_catalog('sections') for every metric's id and description.

Engine version, API contract number, and health. Free (not quota-counted). Call once at the start of a session to confirm the engine is reachable and which contract it serves.

Export a multi-strategy comparison as an Excel workbook. Quota-counted; needs a key whose plan includes full-metrics export (a 403 means the configured key's plan does not — do not retry). Returns the workbook base64-encoded — decode and write it to a ``.xlsx`` file. Args: data_source: Shared data source (same shape as run_backtest). strategies: Same shape as compare_backtests' ``strategies``. include_benchmark: Add a buy-and-hold benchmark to the export. Returns: {"filename", "content_type", "size_bytes", "content_base64"}. A 400/422 rejection returns {"accepted": false, "error": ...}; capacity/timeout/permission failures raise a tool error. If the encoded workbook would exceed the output size limit, raises a tool error — narrow the request (shorter date range, fewer strategies, coarser frequency) and retry.

Fetch one engine reference catalog. Catalogs (cheap, cacheable per session): - 'operators' — comparison operators for condition expressions - 'execution-modes' — entry/exit anchors and fill algorithms, with the validity matrix by market type - 'stop-types' — stop-loss types, re-entry modes, and their parameters - 'sizing-methods' — position-sizing methods and their parameters - 'bar-frequencies' — supported bar frequencies and the signal x execution validity matrix (which combinations are allowed) - 'sections' — the full metric catalog: every statistic's stable id, display label, section, and description - 'sampling-modes' — Monte-Carlo resampling modes, each with its status and parameters Fetch the relevant catalog BEFORE building a strategy or config; build only from values it lists — never guess parameter names or frequencies.

Available date range and estimated bar count for a symbol/frequency. Available on paid plans. Call before a server-side fetch so the requested start/end stay inside what the provider can deliver and the bar count stays inside the key's per-run limit.

Evaluate the strategy on the most recent bar only — no P&L, no stats. Returns the latest signal (-1/0/1), which condition slots fired, and the bar timestamp. Use for "what would this strategy do right now" questions; use run_backtest for performance.

Observations for one macroeconomic series over an optional date range. Free — no special plan. ``series`` is an ``id`` from list_macro_series (e.g. treasury_10y, cpi, unemployment_rate); arbitrary external ids are not accepted. ``start``/``end`` are ``YYYY-MM-DD``, inclusive, both optional (full history when omitted). Returns the value series at its native reporting frequency, with the series descriptor and an ``as_of`` date. A long history is downsampled by the MCP server to a bounded number of points (first and last kept), marked with ``downsampled_from_bars`` and ``points_returned`` on the ``observations`` block. Note: values are the latest revised figures stamped by reference period, not point-in-time as-first-reported data — do not treat them as the values that were known at a past date.

The configured API key's permissions, limits, and current usage. Cheap. Call early in a session — before planning work — to learn what this key can do instead of discovering limits through failed calls. Returns: ``scopes``: the permission scopes the key carries. ``limits``: requests per minute and per day, max concurrent requests, and the per-run bar cap (null when uncapped). ``usage``: current consumption against those limits, with reset countdowns in seconds. ``capabilities``: feature flags such as server-side data fetch and the full metric set. A small fixed-shape record, returned as the engine sent it.

OHLCV price history for a symbol over a date range. Requires a paid plan (managed market data). ``start`` is required (``YYYY-MM-DD``); ``end`` defaults to today. Returns a summary (symbol, resolved date range, total bar count, price range, gap flags), market-hours detection, and the OHLCV arrays. A long history is downsampled by the MCP server to a bounded number of points — first and last bar always kept, every column thinned on the same dates — with ``downsampled_from_bars`` and ``points_returned`` recorded on the ``ohlcv`` block; the untouched ``summary.total_bars`` still reports the true bar count. The window is bounded by the plan's per-request bar cap — call get_data_range first to size a request.

Latest available price for a symbol. Requires a paid plan (managed market data). Returns the most recent *available* bar for the given frequency — the end-of-day close for daily, the last completed bar otherwise — as open/high/low/close/volume plus an ``as_of`` timestamp for that bar. This is a last-known price, not a live tick; read ``as_of`` to judge how stale it is.

JSON Schema for the strategy document (condition_tree + indicators). Fetch this before composing a strategy by hand; the validate_strategy tool checks against the same rules.

Identity and data coverage for one symbol, in a single call. Metadata only — no market data, so no paid plan is needed. Returns the asset's identity (name, asset class, exchange, currency, and whether it is still active) together with a coverage summary for the given frequency: the available date range and an estimated bar count. Use it to confirm a symbol resolves and that the history you need exists before requesting a quote or a price fetch. For the precise per-frequency range use get_data_range.

List indicators, or fetch one indicator's full schema. Cheap, cacheable per session. With no arguments: a compact catalog — ``{"indicators": [...], "count": N}`` — where each entry carries id, name, category, kind, and value_dtype (no description, to keep the discovery scan small). Use it to discover what exists. Pass name='rsi' (id or name, case-insensitive) to get that single indicator's complete entry including its description and params_schema — do this before adding an indicator to a strategy so its parameters are exactly right. Pass compact=False for full entries for everything (large; the MCP server may cap it and set ``truncated_by_mcp`` — prefer compact or name=). Wire optimization: the compact discovery path asks the engine to omit per-entry descriptions (``descriptions=false``) since they are stripped locally anyway; the name= and compact=False paths request them. This is a pure saving — if the engine ignores the param it returns full entries and the local compact strip still yields a lean result.

List the available macroeconomic series (the catalog). Free — no special plan. Returns the set of macro series you can fetch with get_macro_series, each with its stable ``id`` (the value get_macro_series takes), title, category, native reporting frequency, and units, plus the list of categories. Optionally filter to one ``category`` (e.g. rates, yield_curve, inflation, employment, recession, growth). Call this first to find the ``id`` for the series you want.

List predesigned strategy templates, or fetch one in full. Cheap, cacheable per session. The engine returns the templates available to the calling key. With no arguments: a compact catalog — ``{"templates": [...], "count": N}`` — where each entry carries id, origin, name, and description. Use it to discover what exists. Pass name='sma-cross' (id or name, case-insensitive) to get that single template's complete entry: its strategy logic (``condition_tree`` + ``indicators``, the same shape validate_strategy and run_backtest accept) plus parameter metadata — ``defaults`` (starting parameter values), ``requires``, and ``locked_params`` (parameters that must keep their template values). Pass compact=False for complete entries for everything (large; the MCP server may cap it and set ``truncated_by_mcp`` — prefer compact or name=).

List available tickers, optionally filtered by asset class. The full universe is very large, so the MCP server caps the returned list and marks it ``truncated_by_mcp`` — pass asset_class to narrow it, or use search_tickers to resolve a specific asset by name.

Run a historical backtest against the engine. Quota-counted and compute-bound. Validate the strategy first (validate_strategy is far cheaper). On a 504 compute timeout, do NOT retry the same request — reduce the date range, use a coarser frequency, or simplify the strategy. On 429/503, wait for the advertised Retry-After before retrying. Args: data_source: Either inline OHLCV ({"ohlcv": {dates, open, high, low, close, volume?}} as parallel arrays, ISO-8601 dates) or a server-side fetch ({"symbol", "start", "end", "frequency"} — requires a paid plan). strategy: Strategy document (indicators[] + condition_tree). Mutually exclusive with signals. signals: Precomputed signal series ({"dates": [...], "values": [-1|0|1, ...]}). Mutually exclusive with strategy. execution: Execution/cost/risk/sizing settings. Use values from get_catalog('execution-modes'/'stop-types'/'sizing-methods'); omit for engine defaults. benchmark: Optional benchmark data source (same shape as data_source) — when given, the result also carries benchmark-relative metrics (beta, alpha, information ratio, tracking error, up/down capture) and bar-alignment info. data_inputs: Optional custom time-series the strategy references (name -> {dates, values}). response_detail: 'summary' (default — headline metrics, smallest), 'stats' (every metric), 'full' (plus trades and series downsampled to a fixed, server-controlled number of points). include: Optional add-on blocks at any detail level: 'trades', 'equity_curve', 'monthly_returns', 'yearly_returns', 'signal_diagnostics' (which per-bar entry/exit conditions fired,…

Search available assets by ticker or name (relevance-ranked). Use to resolve a user's asset mention ("bitcoin", "S&P") to the exact ticker before requesting a server-side data fetch. asset_class filters to 'stocks', 'crypto', 'forex', or 'indices'.

Validate a strategy document without running a backtest. A cheap quota separate from backtest runs, so validate freely and ALWAYS before run_backtest. Args: strategy: The strategy document — name, indicators[], and condition_tree (see get_strategy_schema for the exact shape). injected_indicators: Names of custom time-series columns the caller will supply via data_inputs at run time, so conditions referencing them validate. Returns: On success: {"valid": true, "warmup_bars": ..., referenced indicators/columns}. On failure: {"valid": false, "errors": [...]} where each error carries a machine code, the location in the document, a message, and context (e.g. the list of valid column names). A failed validation is a NORMAL result, not an error — read the errors, fix the document, and validate again before running.