QuanterLab

Poll progress of a stochastic backtest. Returns `{task_id, status, progress, message, dashboard_url}`.

get_stochastic_backtest_progress

Poll progress of a walk-forward started with `start_walkforward`. Returns `{task_id, status, progress, message, dashboard_url}`. The walk-forward ticks progress per fold so you'll see it advance smoothly. Open the dashboard URL once completed or call `summarize_workflow(task_id)` for a verdict.

get_walkforward_progress

List the strategy codes available via `start_basic_backtest`. Returns metadata for each engine — code, human-readable name, and the body keys the upstream expects.

list_basic_backtest_strategies

List the single-stock fundamental analyzers available in QuanterLab. Returns each analyzer's code, human-readable name, a one-line blurb, and the list of extra parameters it accepts (beyond `ticker`). The analyzers themselves run inside the QuanterLab dashboard — use this catalog to discover what's available and direct the user to the dashboard to execute one.

list_fundamental_analyzers

List the authenticated user's saved backtest results, newest first. Returns ID + strategy code + ticker + duration + total_trades + a categorical `performance_tier` enum (one of `promising` / `mixed` / `weak` / `unrated`) so the caller can rank or filter without seeing the underlying Sharpe / drawdown / return scalars. To inspect a specific backtest open `https://quanterlab.com/dashboard` and look up the listed `id`. Args: strategy_code: Optional filter — e.g. "UB001UNIV", "SC001STCB", "RG001RGMO". When omitted, returns backtests from all strategies. limit: Max rows to return (1-100, default 20).

list_my_backtests

List the authenticated user's saved Primitives projects, newest first. Returns ownership-scoped summary rows only: opaque id, the user's project name, the circuit's node_count, the number of registered hypotheses, and timestamps. It does NOT return the circuit itself (the strategy), its parameters, ticker lists, the hypothesis claim text, or any run outcomes — open a project in the QuanterLab Primitives canvas to inspect it. Use the listed `id` to start a run with `start_primitives_run`.

list_my_primitives_projects

List the user's projects with item counts. Returns project metadata only (name, description, category, item count, timestamps). To view a project's items / attachments, open it in the QuanterLab dashboard.

list_my_projects

List the user's tasks currently counted against the 3-in-flight cap. Returns one row per slot held in the user's MCP in-flight set, with the task_id, kind, seconds since the last progress update, and a `wedged` flag set when the slot would be evicted by the watchdog on the next spawn attempt (no progress update in the last 15 minutes). Use this when `start_*` returns "Too many tasks in flight: 3 max per user" and you can't recall what's running — most often after switching LLM sessions mid-workflow. Returns `{count, limit, tasks: [{task_id, kind, last_progress_age_s, wedged}], _data_policy}`. No FMP / pricing data crosses the boundary — pure ownership metadata. Red-team 2026-05-22 N-1 — exposed to give users a self-service window into stuck slots; the watchdog also auto-evicts wedged entries on the next start_* call.

list_my_running_tasks

List the user's saved scanner / filter results, newest first. Returns summary fields only (universe size, stocks passed, pass rate). To see the per-stock universe with bucketed regime/liquidity/vol labels, open the result in the QuanterLab dashboard.

list_my_filter_results

List the user's saved trading configs (exported from strategy builders). Default rows carry ID + strategy_type + strategy_code + trade_count tier + categorical performance_tier — enough to drive a UB002UBKT `config_ids` portfolio backtest without redistributing the user's full ticker watchlist on every call. Pass `include_details=True` to opt into the full row (ticker, timeframe, primary indicator, virtual_today). Opting in is logged for audit. Args: limit: Max rows to return (1-100, default 20). include_details: When True, returns the ticker / timeframe / primary_indicator / virtual_today / config_id fields. Defaults to False to avoid redistributing the full watchlist on every list call (opting in is audited).

list_my_trading_configs

List the stochastic methods QuanterLab supports for SC001STCB backtests. Returns metadata only — id, display name, category, parameters with defaults and bounds, and a short description. Use this to discover valid `primary_method.id` values for `start_stochastic_backtest`. Does NOT return any market data or fitted parameter values. Args: category: Optional filter, e.g. "mean_reversion", "trend", "pairs", "regime". search: Optional case-insensitive substring matched against method id and name.

list_stochastic_methods

List the QuanterLab Primitives blocks available on the strategy-builder canvas. Primitives is QuanterLab's visual strategy builder: a strategy is wired as a DAG of research blocks (universe → selection → signal / stochastic → optimizer → walk-forward → forward test). This returns the block CATALOG — metadata only (block type, label, category, input/output ports, parameter schema, description). It does NOT return any market data, saved circuits, or computed values. Args: category: Optional category filter (e.g. "signal", "regime", "filter", "forward", "optimize", "factor", "autopsy", "analysis", "allocate"). search: Optional case-insensitive substring matched against block type and label.

list_primitives

List the technical indicators QuanterLab supports for strategy building. Returns metadata only — id, display name, category, parameters with defaults and bounds, and a short description of typical use. Does NOT return any market data or computed indicator values. Args: category: Optional category filter, e.g. "momentum", "trend", "volatility", "volume". search: Optional case-insensitive substring matched against indicator id and display name.

list_indicators

Save the workflow's INPUT config to the user's trading-config ribbon. Saves what the user (or you on their behalf) configured to launch the workflow — ticker, indicator, conditions, risk settings — as a TradingConfig row in the ribbon. The user can then: - Re-run the same config from the ribbon UI. - Pass the config's id to `start_basic_backtest(strategy_code= "UB002UBKT", config_ids=[...])` for a portfolio backtest. Useful AFTER you've validated a config (e.g. walk-forward looked good) so the user has it in their working library. Note: only saves for kinds that produce a deployable strategy (backtest, walkforward, stochastic_backtest, basic_backtest, regime_optimization). Scanner kinds (mr_scan, pairs_scan) don't have a config to save in this sense — call save_workflow_result instead for those. Args: task_id: The task_id returned by a prior `start_*` call. label: Optional human-readable label, max 200 chars.

save_trading_config

Save a completed workflow's result to the user's library. Persists the full result of any completed workflow so the user can find it later in their saved-work surfaces: - Backtests / walkforward / stochastic / basic / regime tasks land in "Saved Backtests" + "Analysis Reports" as a BacktestResult row, with the full metrics, trades, equity curve, and the original config. - Scanner tasks (mr_scan / pairs_scan) land in "Saved Filters" as a FilterResult row with the universe + per-stock configs. The task MUST be in a completed state — the wrapper rejects partial saves. If you call this on a still-running task the tool returns an error telling you to wait + poll first. Args: task_id: The task_id returned by a prior `start_*` call. label: Optional human-readable label, max 200 chars. Saved as the `strategy_name` (BacktestResult) or `filter_name` (FilterResult). Defaults to "MCP <kind> <short id>" if omitted.

save_workflow_result

Search QuanterLab's published research papers (registered walk-forward studies with their trials record). Returns up to 20 papers as {id, title, url}; pass an id to fetch for the paper's text. An empty query lists the newest papers.

search

Return a categorical verdict + narrative summary for a workflow. Looks up `task_id`, fetches the upstream result, classifies the outcome into a verdict enum, and emits a short headline + narrative + next-step suggestions. The underlying numeric metrics NEVER leave the server — only the categorical verdict and the narrative text do. Use this for a quick read on whether a completed task is worth opening in the dashboard. Returns: ``{task_id, kind, status, verdict, headline, narrative, next_steps, dashboard_url, _data_policy}`` `verdict` is one of: `strong`, `promising`, `mixed`, `weak`, `failed`, `running`, `incomplete`, `unrated`. Args: task_id: A task id from any earlier `start_*` call.

summarize_workflow