QuantWright
Server Details
Backtests with costs, a held-out test that counts once, a score that counts every version tried.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool has a clearly distinct role in the backtest lifecycle: describe_data for discovery, create_study for setup, run_backtest for execution, get_result for reading, compare_trades for reconciling a trader's own trades, and run_held_out_test for the final out-of-sample check. The only mild overlap is between run_backtest and run_held_out_test, both of which run strategy code, but the descriptions clearly separate in-sample development from the one-shot hold-out validation.
All six names follow a clean verb_noun snake_case pattern (compare_trades, create_study, describe_data, get_result, run_backtest, run_held_out_test). No mixing of conventions or vague verbs.
Six tools is well-scoped and each earns its place, mapping neatly onto the backtest workflow steps. Nothing feels redundant or padded.
The surface covers the full lifecycle: discovery, study creation, running, results retrieval, trade comparison, and final hold-out validation. Minor gaps like study/run deletion or a dedicated list-studies operation exist, but get_result with study_id partially compensates and agents can work around these.
Available Tools
6 toolscompare_tradesCheck my own tradesAInspect
Checks a trader's own trades against a run's rule, on the price history this server holds: for each trade, in their order, whether the rule would have taken it and, if not, why (already in a trade, no entry signal that day, no bar that day). Use it when the trader lists trades they made and asks which the rule took. Takes a run (run_id) and the trades, each {side, entry, exit?}; answers in words, never prices. It re-runs the run's code, so it counts as a run on the run's symbol.
Inputs: trades (required), run_id, version, study_id, +1 more. Returns: note, clock, counts, market, +9 more
create_studyStart a studyAInspect
Opens a study, the named set of runs every backtest belongs to: call it once per question, before run_backtest. Can set a hold-out period, once and only here, that no run tests except run_held_out_test. Only the first held-out test per account and market counts, and any earlier run on the market (in any study, at any bar size) that read its days disqualifies it: set the hold-out in your first study on a market, before any run on it.
Inputs: name (required), hold_out. Returns: next, reason, status, message, +2 more
describe_dataWhat can be backtestedARead-onlyInspect
Start here to backtest a trading idea. This server holds the price history (US stocks and ETFs, FX, spot gold and silver, spot crypto; daily and intraday bars) and runs backtests on it. Returns the markets and bar sizes served, the default costs per market, the rules and daily limits every run is held to, and how to write the strategy code; then call create_study.
Inputs: no named parameters. Returns: notes, rules, reason, status, +7 more
get_resultRead a resultARead-onlyInspect
Reads a backtest result by its run_id (when run_backtest answered "running", call this until the run ends), or a study's runs by study_id (one of them with version). A run comes with its trades, a page at a time (trades_page).
Inputs: run_id, version, study_id, trades_page, +1 more. Returns: next, runs, basis, grade, +29 more
run_backtestBacktest a strategyAInspect
Backtests a trading rule on this server's price history: one backtesting.py Strategy class, one symbol, one bar size, in a study. Use it to test, backtest or evaluate a trading rule or strategy. Returns summary figures (return, drawdown, Sharpe, win rate, trades, a grade, whether it beat buy-and-hold) and the run's trades (when each entered and left, which exit ended it, its side, win or loss), never prices or bars; a figure may be withheld, with the reason. Waits up to 90 s, then answers status "running" with a run_id for get_result.
Inputs: code (required), symbol (required), study_id (required), timeframe (required), +5 more. Returns: next, basis, grade, lines, +26 more
run_held_out_testTest on the hold-outAInspect
The final out-of-sample check: runs a finished run's exact code once over its study's hold-out period. Call it at the end, on the run you would keep: the first held-out test per account and market is the one that counts, and a hold-out with too few trades for figures (a result needs 10) spends it all the same: each development run says how many trades the hold-out is expected to hold, in hold_out_estimate.
Inputs: run_id (required). Returns: next, basis, grade, lines, +26 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Backtest plain-English trading strategies on real market data: graded results, honesty flags.
Crypto backtest statistics: the server owns the trial count, so it cannot be understated.
Real cost per AI result, LLM prices, switch costs, shutdown dates, A/B test sizes and judge checks.
Probability of Backtest Overfitting (CSCV), Deflated Sharpe Ratio, and purged CV splits.
Related MCP Servers
- AlicenseBqualityCmaintenanceVerify a number before an agent asserts it — a Deflated Sharpe Ratio for backtest, plus eval-gap, subset-win, and judge-bias checks, with signed receipts anyone can verify offline.34MIT
- AlicenseNot gradedqualityBmaintenanceGrades prediction market trade logs to determine if a strategy has a statistically significant, fee-adjusted edge using out-of-sample holdout, returning a signed verdict.MIT
- AlicenseNot gradedqualityDmaintenanceChecks whether a trading backtest survives its own statistics: deflated Sharpe, multiple-testing correction against a best-of-N-noise benchmark, minimum track record length, and fill realism. Takes no market data and no API keys, and cannot recommend a trade — it only reports that a result is weaker than claimed or not yet provable.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and developers to independently verify trading-strategy backtests, detect look-ahead bias, hidden costs, and overfitting, and obtain verdicts with reproducible, optionally signed certificates.151 PyPI10MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.