canli-validation-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 1 of 1 tool tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y canli-validation-mcp@0.16.0
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
1 tool that takes no input and looks read-only was called once with nothing. 1 returned a result.
service_status | Returned a result 1.4 s · 1,740 characters |
During the calls (not necessarily because of them) it first contacted: canlicapital.com.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
get_key label
Issue a free validation key for this session. Rarely needed: the first validation issues one itself unless CANLI_KEY or local mode is set, and the read tools need none. Quotas: 1000 validations per key per UTC day, 5 keys per client per UTC day, 1048576 bytes per validation request, 1024 bytes per key revocation request, 20000 observations per series, 200 variants per matrix.
validate_deflated_sharpe observed_sharpe_annualized, observations, periods_per_year, skew, non_excess_kurtosis, effective_independent_trials, cross_trial_sharpe_sd_annualized, returns
Deflated Sharpe ratio: the probability (0 to 1) that the selected strategy's Sharpe beats the best that luck gives across the variants tried, with the probabilistic Sharpe and that luck benchmark. Send the seven statistics or a return series. With every variant's returns use validate_overfitting; luck as a trial count, validate_luck_trials; a multiple-testing haircut, validate_haircut_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
validate_overfitting matrix, n_splits, max_combinations, seed
Probability of backtest overfitting (0 to 1) by CSCV: how often the in-sample best variant falls below the out-of-sample median. Needs every variant's returns (periods by variants); with summary statistics only, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
validate_reality_check matrix, matrix_file, benchmark, block_length, reps, seed, alpha
Data-snooping tests on every variant a search tried: Hansen's SPA p-value that the best beat the benchmark only by luck, White's Reality Check, and the variants Romano-Wolf StepM finds better. Send all variants tried, not only the winners. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
validate_paper_evidence record, record_file, journal_file, signature
Checks paper-evidence.v0 structure and disclosures. With CANLI_LOCAL=1, record_file reads an export bundle and journal_file verifies signatures, source hashes and recomputed claims. Without a journal, source facts and signatures are unchecked. Local files are never uploaded. This verdict is about the series exactly as submitted. The service never saw the data source, its costs, survivorship, or any lookahead in how the series was built.
14 more tools
validate_breadth sleeve_sharpe, average_pairwise_correlation, sleeves, target
Book Sharpe ceiling from adding sleeves of this quality and correlation, the Sharpe at a sleeve count, and the sleeves a target needs. For portfolio construction; it validates no single strategy. This verdict is about the series exactly as submitted. The service never saw the data source, its costs, survivorship, or any lookahead in how the series was built.
validate_track_record observed_sharpe_annualized, periods_per_year, skew, non_excess_kurtosis, benchmark_sharpe_annualized, confidence, observations
Minimum track record length (observations and years) for an observed Sharpe to beat a benchmark at a confidence level; with observations, the record's probabilistic Sharpe so far. For live or paper records; to size a backtest for its trials, use validate_backtest_length. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
validate_backtest_length effective_independent_trials, backtest_years, target_sharpe_annualized
Minimum backtest length (years) before the best of N independent trials is not expected to reach a target Sharpe by luck; with backtest_years, the most trials those years allow. For planning a search; once it has a result, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
validate_haircut_sharpe observed_sharpe_annualized, periods_per_year, observations, tests, autocorrelation, other_sharpe_ratios_annualized
Haircut Sharpe for multiple testing (Harvey and Liu 2015): the Sharpe a single test would have needed, by Bonferroni and independent tests, and with the other tests' Sharpes, Holm and BHY. For the probability the Sharpe is real, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
validate_luck_trials observed_sharpe_annualized, periods_per_year, observations, effective_independent_trials, skew, autocorrelation
How many skill-less strategies a search would need for its best to reach this Sharpe by luck (Monte Carlo), and with a trial count, the chance it did. States luck as the best of N random tries; for the probability the Sharpe is real, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
audit_backtest returns, returns_file, returns_column, periods_per_year, effective_independent_trials, cross_trial_sharpe_sd_annualized, benchmark_sharpe_annualized, confidence, variants, variants_file, n_splits
One-call audit of a strategy's returns. Headline: one test whose false-positive rate was measured on nine return shapes (White's Reality Check with variants, luck trials with Lo's correction without). Then deflated Sharpe, minimum track record and, with variants, overfitting and out-of-sample decay, each with its receipt, plus fix_next. Send every variant tried (variants_file) so trials are counted; point returns_file at a CSV instead of pasting. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.
verify_receipt id, receipt, include_receipt
Verify a receipt offline: its Ed25519 signature against the bundled canlicapital.com key, its output hash and its id. Send an id to fetch it first, or the receipt itself. The receipt is content-hashed, reproducible from the open-source core it names, and signed with Ed25519 by a key published at https://canlicapital.com/.well-known/canli-receipt-keys.json.
service_status
Whether the validation API is up, with its quotas; check after a timeout before resubmitting. No key. This verdict is about the series exactly as submitted. The service never saw the data source, its costs, survivorship, or any lookahead in how the series was built.
backtest_strategy family, grid, prices, prices_file, prices_column, dates, periods_per_year, cost_bps, allow_short
Backtest a rule on your prices over a whole parameter grid, then validate the best with the count of variants actually run: deflated Sharpe, overfitting probability, minimum track record, vs buy and hold, after costs. A backtest, deflated or not, is not a forecast and not advice.
summarize_series prices, returns, series_file, series_column, series_kind, dates, periods_per_year, benchmark_returns, name
A long price or return series in about 100 words plus fields: growth, risk, dated drawdowns, trend, volatility regime, tails, jumps, stale data. Use instead of reading raw bars. Nothing here is a forecast or advice.
stress_test returns, returns_file, returns_column, periods_per_year, paths, block, seed, drawdown_limit, crash, volatility_multiplier, outage_periods
Stress a strategy's returns: bootstrap histories (how often the drawdown limit breaks or Sharpe turns negative) and named crash, volatility, repeat and stuck-position scenarios, with a fragility share. Frequencies over resampled histories are not forecasts of the future.
check_feasibility broker, asset_class, account, capital_usd, orders_per_rebalance, rebalances_per_year, turnover_per_year, adv_usd, daily_volatility, copies, expected_gross_return, spread_and_fees_bps, impact_coefficient, minutes_per_rebalance, orders_per_minute_limit
Check a trading plan before it trades: broker order-rate and minimum-order limits, 2026 US day-trading rules, square-root market impact with crowding, and the capital where costs eat the return. Checks the plan as described against published broker limits and a market-impact model; it never contacts a broker or sees an account.
check_leakage action, observations, prefixes, seed, cuts, columns, columns_file, timestamps, tolerance
Does a signal look ahead? plan gives cuts; rerun your code on the first cut rows for each, then compare. Rows that changed used later rows; the result names the pattern and horizon. No code is sent. A pass covers only these cuts: the columns are the caller's, and survivorship, vendor revisions or a leak no cut reaches leave no trace.
placebo_test action, data_file, columns, kind, placebos, method, seed, real, placebo_results, lower_is_better
Does your pipeline find edges in noise? plan writes placebo files (your data's returns in random orders, so nothing is predictable); run the whole pipeline on real.csv and on each, then compare for a p-value that counts every choice it makes. Beating the placebos shows the pipeline finds more in the real order of the returns than in random orders of the same returns; it does not show the edge survives costs, capacity or the future.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=20.10 |
| Source | github.com/arhancanli/canlicapital |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-u2geJl5/QlpMfmXHx9tFt1iD9oF4TKxL2OnUfPZ4SJeUpVBCfEe670FOUFsqZb+GOnuUUrKkF65dXBzPwnQoSw== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/canli-validation-mcp)
New version out? Ask for a fresh report.