Canli Validation MCP Server

by arhancanli Your server? Claim it

not responding

Canli Validation is listed as active in the registry but did not answer our last check. 1 161 installs a week from npm. It exposes 18 tools. Last commit 6 Nov 2026.

Deflated Sharpe and PBO checks. A verdict is not admission to anything and is not a forecast.

Installs per day peak 885 · avg 138 · -33% w/w

a month agotoday

Uptime history 41 days of history · worst day 0%

41 days agonow

77.2%

Uptime 24h

71 of 92 checks

Tools

read from the server

176 ms

Response time

average over 24h

1 161

Installs / week

npm and PyPI

What changed 19

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 29 September 2026. No other catalogue keeps this.

7 Oct a tool changed version

7 Oct a tool description was rewritten audit_backtest

6 Oct 6 tools appeared backtest_strategy, check_feasibility, check_leakage and 3 more

6 Oct 5 tools changed the parameters they ask for audit_backtest, validate_overfitting, validate_paper_evidence and 2 more

6 Oct 3 tools disappeared company_financial_history, get_key, get_receipt

6 Oct 2 tool descriptions were rewritten audit_backtest, validate_paper_evidence

29 Sep a tool appeared validate_reality_check

What the code does

We read the source, 18 h ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

A line of code looks encrypted measurements/external-publication.html:1846, measurements/external-publication.html:1847, measurements/external-publication.html:1850

<tr><td>publication/crypto-carry/v0.1.0</td><td>CARRIED_FORWARD_BYTE_IDENTICAL_PDF_FROM_PRIOR_RECEIPT</td><td>10</td><td>93c315aebf3262ae195f7475ce668ceed47290c62549ba707cf8544ab795e421</td><td>48a603b78f9568b18c245f9a0c28286edb1277995e0eaa8e77ca8f89e08f77a8</td><td>f41be57dbcbd0…

Runs an external command _probe2.mjs:5, _probe3.mjs:5, _render_check.mjs:6

const proc=spawn(CHROME,['--headless=new','--disable-gpu','--no-sandbox','--hide-scrollbars',`--remote-debugging-port=${PORT}`,'--remote-allow-origins=*','about:blank'],{stdio:'ignore'});

Runs an external command public/glassbox/reproduce.py:110, artifacts/qa/annotation-intake-integration-20261001/independent-dev-browser-probes.py:13

    r = subprocess.run([sys.executable, "-m", "pytest", str(test), "-q"], capture_output=True, text=True, cwd=repo)

Builds a database query by concatenation mcp-canli/src/view/studio.js:400

<div class="ctl" role="toolbar" aria-label="Chain controls">${opts ? `<label class="sub">Expiration <select data-c="exp"${busy || !host.canCall ? " disabled" : ""}>${opts}</select></label>` : ""}<span class="grp">${Object.keys(CHAIN_SETS).map((k) => toggle(`set-${k}`, k[0].toUppe…

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add canli-validation-mcp --transport http https://canlicapital.com/mcp

Settings → Connectors → Add custom connector, then paste this address

https://canlicapital.com/mcp

~/.codex/config.toml

[mcp_servers.canli-validation-mcp]
url = "https://canlicapital.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "canli-validation-mcp": {
      "url": "https://canlicapital.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "canli-validation-mcp": {
      "type": "http",
      "url": "https://canlicapital.com/mcp"
    }
  }
}

Available tools 18

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

validate

validate_backtest_length

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_breadth

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_deflated_sharpe

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_haircut_sharpe

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

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.

validate_overfitting

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_paper_evidence

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.

validate_reality_check

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_track_record

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.

audit

audit_backtest

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.

backtest

backtest_strategy

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.

feasibility

check_feasibility

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.

leakage

check_leakage

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

placebo_test

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.

service

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.

stress

stress_test

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.

summarize

summarize_series

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.

verify

verify_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.

Tools removed

Tools this server used to expose. Anything built against them stopped working on the day they went.

company_financial_history

removed 6 Oct 2026

get_key

removed 6 Oct 2026

get_receipt

removed 6 Oct 2026

Endpoints

URL	Transport	State	Latency	Checked
https://canlicapital.com/mcp	streamable-http	answering	86 ms	1 min ago

Alternatives to Canli Validation

same job, measured the same way

Alphaassay

by alphaassay

Fail-closed backtest/signal validation: overfitting, leakage, deflated Sharpe. NOT financial advice.

21 tools answering

PingValid Email Validation

by pingvalid

Email validation for AI assistants: verdict, risk score, evidence. Free: 100 checks a month.

answering

Turkish IBAN, Tax Number & National ID Validation

by foster-ops

Checksum validation of Turkish IBANs, tax numbers (VKN) and national IDs (TCKN). Nothing stored.

3 tools answering

Veridigit

by qinisolabs

Verified IBAN, card, ISBN-13 & VIN validation for AI agents — checksums, not guesses.

45 installs/wk local only

Ribcage Agent Services

by jrcage

Verification and research desk for agents: packet validation, token screens, settlement checks.

43 installs/wk local only

rendercheck

by rogermsc

Check generated audio, video and stills for defects. Returns a verdict, not more media.

96 installs/wk local only

MadTaco

by madtaco

Verification and trust checks for AI agents: validate, screen, propose, accounts, usage.

81 installs/wk local only

ServerCard Trust MCP

by servercardtrust

Paid remote MCP for server-card validation, auth checks, trust packets, and readiness.

answering

Canli Validation — questions

Answers built from our own checks of this server.

What can Canli Validation do?

It exposes 18 tools, read directly from the server on our last check. Among them: audit_backtest, backtest_strategy, check_feasibility, check_leakage, placebo_test, service_status and 12 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Canli Validation working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 71 of 92 checks got a reply (77.2%), average response time 176 ms. The bar chart above shows every period we have measured.

Did Canli Validation ever remove tools?

Yes. company_financial_history, get_key, get_receipt are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.

The registry lists Canli Validation as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Canli Validation?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Canli Validation need an API key?

No. Canli Validation completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 18 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Canli Validation?

It answers our handshake in 176 ms on average, which is faster than 79% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Canli Validation?

The npm package canli-validation-mcp was installed 1 161 times in the last week. Week over week that is -33%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Canli Validation open source?

The code is open source: it is published under the MIT licence, written in HTML, 6 stars on GitHub and 13 open issues. The licence covers the code in the repository, not the hosted service at canlicapital.com, which runs on its operator's own terms.