Skip to content

ETFIQ MCP server

com.etfiq/etfiqetfiq.comstreamable-httpv0.5.0Scanned

Independent US ETF data for research agents: 33 tools, holdings to risk checks, each dated.

33 tools: 25 change things and 8 only read.

Tools: 0 delete, 0 irreversible, 25 write, 8 read.
  • Reads private data · 2
  • Reads text others write · 0
  • Can send data out · 0
  • 3 findings

Tools listed without sign-in. Remote posture

With Anlyon

25 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the ETFIQ MCP server can do

The ETFIQ MCP server is published by etfiq.com, a domain the MCP Registry verified. It has 33 tools. It can create or change data (25 tools: etf_profile, etf_holdings, etf_theme, etf_themes and 21 more), but cannot delete data. 8 tools only read.

2 tools read private data (etfiq_page and find_page).

The fixed checks matched 3 findings (tool-shadowing, annotation-conflict and long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 14, 2026, version 0.5.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

33 tools

Changes things 25Claude Code: ask
  • build_portfolioBuilds a custom portfolio of US listed ETFs from construction choices about the portfolio, and shows the rule it applied.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description is 3,224 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...arries the not-advice line in not_advice, written to be shown with the portfolio."

      What this check looks for
    Description, as the server wrote it
    Builds a custom portfolio of US listed ETFs from construction choices about the portfolio, and shows the rule it applied. Two forms. Weights (ETFIQ custom construction rule, version 2): pass weights, the user's own percent for each asset class, adding to exactly 100, for example {"us-stocks": 40, "international-stocks": 15, "us-bonds": 25, "gold": 10, "reits": 10}. The asset classes: us-stocks, us-small-stocks, international-stocks (broad, market-cap-weighted index funds only), international-dividend-stocks, international-esg-stocks, international-factor-stocks, international-ipo-stocks (each only when the user asks for that tilt), emerging-markets-stocks, reits, us-bonds (core, intermediate), us-bonds-short, us-bonds-long, us-corporate-bonds, government-bonds-short, government-bonds-intermediate, government-bonds-long, tips, high-yield-bonds, cash (Treasury bills), gold, commodities (broad), alternatives. Defaults: cheapest funds, one fund per asset class, no fee ceiling; the answer's defaults.line names the ones used. Band (version 1): pass band, include and funds, and the rule sets the weights (stocks at the band's point, international, broad market-cap-weighted funds only, 40% of stocks outside themes, themes 10% of stocks, commodities and alternatives 5% each from bonds, US bonds the rest). In each asset class or sleeve the cheapest (or largest) funds that file N-PORT (a gold trust: its 10-Q or 10-K), hold at least $100 million and have three years of prices, each fund's fee with its filing date. Weights given in words go to the weights form mapped to the ids above. Only two things have no default, and each is refused with its kind: weights that do not add to 100 (kind weights-total) and an asset class with no id here (kind unknown-class). With neither weights nor a band, the tool needs one of them; the bands by stock share are conservative: more than 15% and up to 30% stocks; moderately-conservative: more than 30% and up to 50%; moderate: more than 50% and up to 70%; moderately-aggressive: more than 70% and up to 85%; aggressive: more than 85%. The tool takes nothing about the person: an argument giving their age, income, savings, net worth, goals, time horizon, tax situation, risk tolerance, employment or family is refused (kind person), and weights and bands are the user's choices about the portfolio, not facts about someone. Whether a portfolio suits someone, or whether to buy or sell it, is not something ETFIQ answers, and the not-advice line says so. Its returns field carries the portfolio's hypothetical returns (ETFIQ custom rule, version 3: the weights reset at every month end, as the ETFIQ benchmarks are): total return, return a year, volatility and month-end drawdown over 1Y, 3Y, 5Y, 10Y and since the first month end all its funds share, a window given only where every fund has prices across it; returns.common.sentence says where the history starts and why. They are hypothetical: no window is extended, and no return is estimated beyond the ones given. compare_to_benchmark takes the answer's compare.arguments to set the portfolio beside an ETFIQ benchmark. Every response carries the not-advice line in not_advice, written to be shown with the portfolio.

    Annotations the server declares

    • title: Build a portfolio from construction rules
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compare_to_benchmarkSets an allocation ETF, or a portfolio build_portfolio builds, beside an ETFIQ benchmark.1 finding

    Why it is in this group

    • The name "compare_to_benchmark" says "compare": a word for reading.
    • The description's first verb is "set": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "compare_to_benchmark" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "compare_to_benchmark" says "compare": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Sets an allocation ETF, or a portfolio build_portfolio builds, beside an ETFIQ benchmark. With ticker (such as AOR): how the fund did against the benchmark for its band (set by its look-through stock share), over the same dates, as ETFIQ published it: total returns by window and the difference, risk and cost. With portfolio (the arguments build_portfolio took, its answer's compare.arguments.portfolio): the same portfolio built again beside an ETFIQ benchmark, the benchmark's own 1Y, 3Y, 5Y, 10Y and since-inception windows exactly as published, each with its dates and basis (hypothetical before the freeze date), and the differences in stock share and weighted fee in percentage points; and, in portfolio_returns, the portfolio's hypothetical returns beside the benchmark's over the same months, window by window, with each difference in percentage points. WHICH BENCHMARK: without benchmark, the default rule's (the ETFIQ strategic benchmark nearest the portfolio's looked-through stock share, the lower on a tie; for the band form, its band's), and choice.line says why in one line. When that one is more than 5 percentage points from the stock share, or the share is as near another strategic benchmark, the next-nearest is set beside it in also, with the same windows and differences, and choice.gap.line says so. When the reader names another ETFIQ benchmark ("compare it to Strategic 80 instead"), pass benchmark with their words or its id (etfiq-strategic-80): any benchmark list_benchmarks returns. That one is used, and choice.line still names the default and why. A name that matches no benchmark is refused (kind unknown-benchmark) with the list. Refuses, and estimates nothing, when ETFIQ has not published what is asked.

    Annotations the server declares

    • title: An allocation ETF or a built portfolio against an ETFIQ benchmark
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_benchmarkThe benchmark ETFIQ measures one ETF against, as its page names it: the index the fund names, or its own holdings, never a category stand-in; how that was set, the ETF it is priced…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The benchmark ETFIQ measures one ETF against, as its page names it: the index the fund names, or its own holdings, never a category stand-in; how that was set, the ETF it is priced through, and the fund's return, the benchmark's and the gap for each window. The ETFIQ benchmarks for model portfolios are a different thing (list_benchmarks).

    Annotations the server declares

    • title: One ETF's own benchmark
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_committeeHow each seat of the IQ Investment Committee reads one ETF: 12 legends, 11 seats named for investing philosophies (Bogle-style Low Cost, Graham-style Margin of Safety and the other…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How each seat of the IQ Investment Committee reads one ETF: 12 legends, 11 seats named for investing philosophies (Bogle-style Low Cost, Graham-style Margin of Safety and the others) and ETFIQ Skeptic, each with its state (Supports, Mixed, Challenges or Not enough data), how much of the seat could be measured, and each criterion's state. States are never a call to buy, sell or hold, and every answer carries the disclosure to show with it. Each seat links its own page, which gives the investor's published source and the thresholds.

    Annotations the server declares

    • title: IQ Investment Committee seats on one ETF
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_flowsFund flows as ETFIQ publishes them, computed from each fund's daily change in shares outstanding times its NAV.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Fund flows as ETFIQ publishes them, computed from each fund's daily change in shares outstanding times its NAV. With ticker: that fund's net flow over 1D, 1W, 1M, 3M, YTD and 1Y, each with its dates and its share of net assets at the window's start, its streak, and its filed N-PORT months. Without ticker: the biggest inflows and outflows among every fund with daily data for window (1D, 1W, 1M, 3M, YTD or 1Y; default 1W), how many funds were counted, each row with the last day its numbers reach (through; a row short of the window counts fewer days), and the latest weekly flows report (Monday to Friday) with its own top inflows and outflows, each with its days. Filter by desk, category (Stocks, Bonds, Commodities, Allocation) or issuer. It answers questions about money going into or out of ETFs.

    Annotations the server declares

    • title: ETF fund flows
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_holdersWhich US listed ETFs hold a given company, ranked by how much of each fund it is.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Which US listed ETFs hold a given company, ranked by how much of each fund it is. It answers "which ETFs hold X", "which fund holds the most X" and "how do I get exposure to X" questions, where X is a company rather than a fund, and for "which bond ETFs hold X's debt". Takes a company name or its ticker. Returns every fund holding its shares with the weight its issuer published and the date that book was filed, and separately every fund holding its bonds or other debt. Covers 31,019 companies.

    Annotations the server declares

    • title: Which ETFs hold a company
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_holdingsAnalyst: what a fund holds, by weight, and how old that is.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Analyst: what a fund holds, by weight, and how old that is. Use after etf_profile to read the book, or before etf_overlap to see what two funds share. top_n limits the rows. lag_days says how old the book is: an issuer file read today and a filing from two months ago both come back here and are not the same answer.

    Annotations the server declares

    • title: Holdings of one ETF
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_moversScout: what moved.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Scout: what moved. The biggest fund inflows and outflows for a flow window (1D, 1W, 1M, 3M, YTD or 1Y; default 1D) and the best and worst total returns over a return window (1M, 3M or 1Y; default 1M), each row dated with the days it covers. ETFIQ publishes no single-day return, so today's movers are the flows. Filter by desk (buffer, income, themes, leverage, crypto, alternatives, core) or category (Stocks, Bonds, Commodities, Allocation); funds under min_assets_usd (default 100,000,000) are left out of the return lists, and leveraged funds are flagged. Start a daily scan here, then etf_profile or etf_risk_check on a name that stands out. limit is rows per list (1 to 25, default 10).

    Annotations the server declares

    • title: Biggest flows and returns
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_news_todayScout: ETF news for one day from ETFIQ's ETF News, read from SEC filings: launches (funds that began trading), closures and closing notices, funds filed and not yet trading, name o…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Scout: ETF news for one day from ETFIQ's ETF News, read from SEC filings: launches (funds that began trading), closures and closing notices, funds filed and not yet trading, name or ticker changes, fee changes and splits. Defaults to the latest day published (is_latest and lag_days say how old that is); pass date (YYYY-MM-DD) for an earlier trading day, kind to see one kind, ticker for one fund. Each event is one dated sentence with its SEC form, filing date and link. Closures and launches come first. limit 1 to 100, default 25; matching is the whole count.

    Annotations the server declares

    • title: ETF news for one day
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_overlapAnalyst and Risk Officer: how much of their weight two funds hold in common, as ETFIQ published it on the comparison page for that pair.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Analyst and Risk Officer: how much of their weight two funds hold in common, as ETFIQ published it on the comparison page for that pair. Use when asked whether two ETFs are the same thing, or whether owning both adds anything. Refuses rather than estimating when the pair is not compared or either holdings book is incomplete.

    Annotations the server declares

    • title: Holdings overlap of two ETFs
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_profileEverything ETFIQ publishes about one fund: issuer, category, and each number with its source and as-of date, plus a one sentence verdict on how it did against what its own label pr…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Everything ETFIQ publishes about one fund: issuer, category, and each number with its source and as-of date, plus a one sentence verdict on how it did against what its own label promises. benchmark is the fund's own benchmark as its page names it: its name, how it was set, and the fund's return, the benchmark's and the gap for each window (periods is the page's whole window table). A closed fund answers with closed (the day and the page's words); a former ticker answers as the fund it trades as now, and says so. The ETFIQ benchmarks for model portfolios (list_benchmarks) are a different thing.

    Annotations the server declares

    • title: Everything about one ETF
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_promiseWhether one ETF delivers what its category promises, from the ETFIQ Promise Index: a badge (Delivered, Partly or Missed) with the number behind it, its window and the sentence the …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Whether one ETF delivers what its category promises, from the ETFIQ Promise Index: a badge (Delivered, Partly or Missed) with the number behind it, its window and the sentence the fund page prints, plus its category's promise, the test and its thresholds, and the category's Promise Index. A fund the test cannot be run on says so with the reason.

    Annotations the server declares

    • title: Promise check for one ETF
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_rankingsStrategist and Scout: the ranked lists ETFIQ publishes, or one of them.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Strategist and Scout: the ranked lists ETFIQ publishes, or one of them. Each ranks ONE published number inside a stated set: the cheapest funds in a theme, the leveraged funds furthest from their stated multiple, the buffer funds closest to their cap. Call with no argument for the list.

    Annotations the server declares

    • title: Published rankings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_return_of_capitalHow much of an income ETF's distributions were return of capital: the rows its page prints, each with its source, window and date (the issuer's Rule 19a-1 notices, weighted by amou…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How much of an income ETF's distributions were return of capital: the rows its page prints, each with its source, window and date (the issuer's Rule 19a-1 notices, weighted by amount), the annual report's final tax character (Form N-CSR) with its fiscal year and filing date, the comparison of the two where both exist, and the kind of options the fund writes from N-PORT. A notice ETFIQ has not read is never reported as 0%. Facts from filings, not tax advice.

    Annotations the server declares

    • title: Return of capital and tax character
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_risk_checkRisk Officer: for 1 to 20 fund tickers, the observations to check before the funds are read one by one.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Risk Officer: for 1 to 20 fund tickers, the observations to check before the funds are read one by one. Per fund: net assets, fee, top-10 weight, premium or discount to NAV (median, 95th percentile, days over 1%), bid-ask spread, IQ Liquidity Score, leverage (stated multiple and the gap to it over the window), and whether the fund is closed or no longer updated. For the list: the overlap between every pair ETFIQ publishes, the largest fund, issuer and category shares, a leveraged share. Pass weights ({"SPY": 60, "QQQ": 40}, percent) for weighted shares; omit for equal. Each flag names its number, date and the line it crossed (lines); none is advice. A number not published for a fund is listed under that fund, never read as zero.

    Annotations the server declares

    • title: Risk check for a list of funds
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_scorecardThe risk and return scorecard for one ETF against its own ETFIQ benchmark, or, with versus, for two ETFs side by side as their comparison page prints it: total, annualised and pric…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The risk and return scorecard for one ETF against its own ETFIQ benchmark, or, with versus, for two ETFs side by side as their comparison page prints it: total, annualised and price return, volatility, downside deviation, maximum drawdown with its dates, Sharpe, Sortino and Calmar, and beta, R2, upside and downside capture, tracking error and alpha with its t-stat and 95% range. The window, the count of weekly returns and the risk-free rate come with it. alpha_test.significant is true only when |t| is at least 2 and the range leaves out zero.

    Annotations the server declares

    • title: Risk and return scorecard
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_screenEvery fund matching some filters, each with its net assets and the source and date that number came from.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Every fund matching some filters, each with its net assets and the source and date that number came from. Filters: desk, issuer, max_fee_pct, min_assets_usd; and, from the ETFIQ screener, tracks (the index the funds track, such as "S&P 500"), min_yield_pct (12-month yield of at least that percent), pays (payout frequency: weekly, monthly, quarterly, semiannual or annual, published for income ETFs) and sort (assets, largest first; fee, lowest first; yield, highest first). count is the whole matching set: when fewer rows come back, truncated and note say so, so the rows are part of the set, not all of it. first names every fund tied at the top of the order. Use for "find me all X" and "cheapest X" questions rather than repeated searches. Fees are percentages, not basis points. Funds with no published data for a filter are set aside and counted, not treated as failing it.

    Annotations the server declares

    • title: Screen ETFs by filters
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_themeScout and Strategist: every US listed fund in a theme, largest first, with what each charges and how much of it is already in the S&P 500.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Scout and Strategist: every US listed fund in a theme, largest first, with what each charges and how much of it is already in the S&P 500. For "what X ETFs are there" or "top X ETFs" questions it returns the whole published set rather than a sample.

    Annotations the server declares

    • title: Every fund in a theme
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_themesStrategist: every theme ETFIQ publishes and how many funds each holds.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Strategist: every theme ETFIQ publishes and how many funds each holds. Call when unsure what a theme is called, then etf_theme.

    Annotations the server declares

    • title: All themes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etf_trading_costWhat it costs to trade one ETF: its IQ Liquidity Score on a fixed 0 to 100 scale, the bid-ask spread and premium or discount to NAV the issuer publishes under Rule 6c-11, ETFIQ's o…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    What it costs to trade one ETF: its IQ Liquidity Score on a fixed 0 to 100 scale, the bid-ask spread and premium or discount to NAV the issuer publishes under Rule 6c-11, ETFIQ's own premium from NAV and closing prices with its window, and, where a number is not published, why. The lead sentence is quoted from the fund's trading page.

    Annotations the server declares

    • title: What it costs to trade one ETF
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etfiq_as_ofWhat ETFIQ published on a given date, from its frozen dated archive.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The description contains "every other tool", wording about other tools or servers.

      Matched text

      description: "...needs to stay true after it is quoted: every other tool here answers about today and today move..."

      What this check looks for
    Description, as the server wrote it
    What ETFIQ published on a given date, from its frozen dated archive. Use when a question is about a past date, or when a number needs to stay true after it is quoted: every other tool here answers about today and today moves overnight. Takes YYYY-MM-DD. Covers the pieces written that night, not an arbitrary per-fund number on an arbitrary day.

    Annotations the server declares

    • title: What ETFIQ published on a date
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etfiq_methodologyHow ETFIQ computes a number, from the methodology page that says so: one page per desk (income, buffer, leverage, crypto, alternatives, themes), flows, scores, categories (how stoc…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How ETFIQ computes a number, from the methodology page that says so: one page per desk (income, buffer, leverage, crypto, alternatives, themes), flows, scores, categories (how stock and bond funds are placed and which benchmark each is measured against), portfolio look-through, and the ETFIQ benchmarks for model portfolios. Pass topic, the reader's question in their words; the answer names the page, quotes the paragraphs that answer it and gives the page's text. A single fund's own benchmark follows its desk's rule (an income fund's is on the income page), never the model-portfolio benchmarks. Call with no topic for the list of pages.

    Annotations the server declares

    • title: How ETFIQ computes a number
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etfiq_sectionsWhat ETFIQ publishes, section by section, with a page count for each, and start_here: the main pages (fund flows, the weekly flows report, ETF model portfolios and benchmarks, the …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    What ETFIQ publishes, section by section, with a page count for each, and start_here: the main pages (fund flows, the weekly flows report, ETF model portfolios and benchmarks, the filed prediction-market and sports-team funds, issuers, methodology, rankings, the screener) with what each holds. Start here when the question is not about one fund.

    Annotations the server declares

    • title: What ETFIQ publishes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • strategy_recordStrategist and Strategy Tracker: one Advanced Strategies record, labelled hypothetical.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Strategist and Strategy Tracker: one Advanced Strategies record, labelled hypothetical. For a 2x strategy the real-days-only numbers since every fund traded come first, then the tracked record (NAV from the start of tracking, windows, drawdown, Sharpe), then the full back-test (windows, statistics, how much of it is simulated), the scorecard against its benchmark ETF, modelled costs and turnover, and the second-source check. Read the tracked record before the back-test: the back-test never ranks. Takes a slug from strategy_list.

    Annotations the server declares

    • title: One strategy: tracked record and back-test
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • strategy_signalsStrategist and Strategy Tracker: one Advanced Strategies rule and today's state: each fund's signal (in, out, cash and the like, with the distance from its line in plain words), th…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Strategist and Strategy Tracker: one Advanced Strategies rule and today's state: each fund's signal (in, out, cash and the like, with the distance from its line in plain words), the target holdings in percent, the next signal and trade dates, the last moves, and the tracked blotter (the last blotter_limit hypothetical trades, 0 to 50, default 10). Hypothetical: the blotter is what the rule would have traded at the next close, ETFIQ places no orders, and nothing here is an instruction. Takes a slug from strategy_list.

    Annotations the server declares

    • title: One strategy: signals, holdings, blotter
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 8Show 8 read-only tools
  • etf_compareTwo ETFs compared as ETFIQ's comparison page for the pair publishes them: the page's title and dated lead sentence, each fund's verdict and key numbers, the share of holdings they …No findings

    Why it is in this group

    • The name "etf_compare" says "compare": a word for reading.
    Description, as the server wrote it
    Two ETFs compared as ETFIQ's comparison page for the pair publishes them: the page's title and dated lead sentence, each fund's verdict and key numbers, the share of holdings they have in common, the dated answers in the page's FAQ, and the pair's risk and return scorecard where one is published. A pair with no comparison page is refused, with each fund's own page.

    Annotations the server declares

    • title: Two ETFs compared
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etfiq_listThe pages inside one section, optionally filtered to those whose address contains a word.No findings

    Why it is in this group

    • The name "etfiq_list" says "list": a word for reading.
    Description, as the server wrote it
    The pages inside one section, optionally filtered to those whose address contains a word. Use after etfiq_sections to find a page, then etfiq_page to read it. The count returned is the whole matching set even when the list is capped.

    Annotations the server declares

    • title: Pages in one section
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • etfiq_pageRead any published ETFIQ page as text: a theme hub, a ranking, a comparison of two funds, an issuer, a methodology note, a dated study.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "note": it reads notes.
    Description, as the server wrote it
    Read any published ETFIQ page as text: a theme hub, a ranking, a comparison of two funds, an issuer, a methodology note, a dated study. Takes a path like /themes/cyber or a full etfiq.com URL. This reaches all 40,000 pages, including everything the typed tools above do not cover, and returns the page content rather than its navigation.

    Annotations the server declares

    • title: Read any ETFIQ page
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • find_pageThe designed ETFIQ pages that answer a question, best first, at most three: a fund, a comparison of two funds, the ETFs that hold a company, a ranking, a theme, a category, an issu…Reads private dataNo findings

    Why it is in this group

    • The name "find_page" says "find": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "calendar": it reads calendars.
    Description, as the server wrote it
    The designed ETFIQ pages that answer a question, best first, at most three: a fund, a comparison of two funds, the ETFs that hold a company, a ranking, a theme, a category, an issuer, the weekly flows report, a flows ranking, a dividend calendar, a screen, a benchmark, a model portfolio comparison, an FAQ answer or a methodology page. Suited to any question one ETFIQ page answers ("who holds NVDA", "SCHD vs VYM", "highest yielding covered call ETFs", "biggest ETF inflows this week"). Each page comes with its title, its address, its dated lead sentence exactly as the page prints it, and numbers from its own .json twin (a fund's key facts, or the dated answers in the page's FAQ), with the match score (0 to 100) and the reason. answered is false when no page reaches the threshold: then answer with the other tools. Matching is deterministic: an exact phrase, an exact pair or a named entity with the intent its page answers, then word overlap. Pass path instead of query to read one page's card by its address.

    Annotations the server declares

    • title: Find the ETFIQ page that answers a question
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_benchmarkOne ETFIQ benchmark in full: its rule as the methodology states it, the funds and weights in force (with SEC series ids and each fund's expense ratio and its date), and every stati…No findings

    Why it is in this group

    • The name "get_benchmark" says "get": a word for reading.
    Description, as the server wrote it
    One ETFIQ benchmark in full: its rule as the methodology states it, the funds and weights in force (with SEC series ids and each fund's expense ratio and its date), and every statistic ETFIQ computes for it by window (total return, return a year, volatility, maximum drawdown, Sharpe ratio, turnover, factor loadings, weighted expense ratio), each with its dates and its basis. basis marks each number from before the freeze date as hypothetical. Takes an id such as etfiq-strategic-60 or strategic-60. Serves the published benchmark only; it cannot be customised.

    Annotations the server declares

    • title: One ETFIQ benchmark
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_benchmarksThe ETFIQ benchmarks: published, rules-based yardsticks for model portfolios, each a written rule over broad, low-cost ETFs, grouped in families (strategic, tax-aware, factor, inco…No findings

    Why it is in this group

    • The name "list_benchmarks" says "list": a word for reading.
    Description, as the server wrote it
    The ETFIQ benchmarks: published, rules-based yardsticks for model portfolios, each a written rule over broad, low-cost ETFs, grouped in families (strategic, tax-aware, factor, income, tactical, thematic) by stock share. Filter by family, or by band (a name such as moderate, a stock share such as 60, or "all stocks"). Use when asked which benchmark measures a kind of model portfolio, then get_benchmark for one. These are not a single fund's own benchmark: that is in etf_profile (benchmark), and how it is chosen is in etfiq_methodology. A benchmark is identical for everyone and never a recommendation: a request to customise one or to say what to buy is refused, and a request to build a custom portfolio is for build_portfolio.

    Annotations the server declares

    • title: ETFIQ benchmarks for model portfolios
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • strategy_listStrategist: the ETFIQ Advanced Strategies list (trend, momentum, rotation, risk-parity, 2x shelf, income and the like, each a written rule over ETFs), ranked by tracked return sinc…No findings

    Why it is in this group

    • The name "strategy_list" says "list": a word for reading.
    Description, as the server wrote it
    Strategist: the ETFIQ Advanced Strategies list (trend, momentum, rotation, risk-parity, 2x shelf, income and the like, each a written rule over ETFs), ranked by tracked return since tracking started. Each row: risk, benchmark, tracked and back-test windows, today's holdings, signal pill, next signal and trade dates, and whether the second-source rebuild agreed. All hypothetical, never advice. Filter by group. Call first, then strategy_signals or strategy_record with a slug.

    Annotations the server declares

    • title: Advanced Strategies
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:38 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
25
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 25 tools that change things (25 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.etfiq.com: tools/list returned 33 tools to an anonymous client, including etf_profile (write), etf_holdings (write), etf_theme (write), etf_themes (write), etfiq_sections (write) and 20 more

    What this check looks for

Posture changes

  1. Nov 6, 2026
    • Tools that change things, listed without credentials: 20 to 25
  2. Oct 29, 2026
    • Tools that change things, listed without credentials: 14 to 20

Findings

Matches of fixed checks, with the text they matched.

2 warn1 info
  • The description contains "every other tool", wording about other tools or servers.

    Matched text

    description: "...needs to stay true after it is quoted: every other tool here answers about today and today move..."

    What this check looks for
  • The server marks "compare_to_benchmark" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "compare_to_benchmark" says "compare": a word for reading.

    What this check looks for
  • The description is 3,224 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...arries the not-advice line in not_advice, written to be shown with the portfolio."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools4 changed.~4 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 20 -> 25.View diff
    • Tools that change things, listed without credentials: 20 to 25
  3. Tools6 added, 5 changed.+6 added~5 changedView diff
  4. Tools7 added, 14 changed.+7 added~14 changedView diff
  5. PostureRemote posture changed. Tools that change things, listed without credentials: 14 -> 20.View diff
    • Tools that change things, listed without credentials: 14 to 20

Install

Pinned to version 0.5.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http etfiq https://mcp.etfiq.com
claude mcp add --transport http etfiq https://mcp.etfiq.com

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__etfiq__etf_search",
      "mcp__etfiq__etfiq_page",
      "mcp__etfiq__etfiq_list",
      "mcp__etfiq__find_page",
      "mcp__etfiq__list_benchmarks",
      "mcp__etfiq__get_benchmark",
      "mcp__etfiq__etf_compare",
      "mcp__etfiq__strategy_list"
    ],
    "ask": [
      "mcp__etfiq__etf_profile",
      "mcp__etfiq__etf_holdings",
      "mcp__etfiq__etf_theme",
      "mcp__etfiq__etf_themes",
      "mcp__etfiq__etfiq_sections",
      "mcp__etfiq__etf_screen",
      "mcp__etfiq__etf_overlap",
      "mcp__etfiq__etfiq_as_of",
      "mcp__etfiq__etf_holders",
      "mcp__etfiq__etf_rankings",
      "mcp__etfiq__etf_flows",
      "mcp__etfiq__etfiq_methodology",
      "mcp__etfiq__compare_to_benchmark",
      "mcp__etfiq__build_portfolio",
      "mcp__etfiq__etf_committee",
      "mcp__etfiq__etf_scorecard",
      "mcp__etfiq__etf_promise",
      "mcp__etfiq__etf_trading_cost",
      "mcp__etfiq__etf_return_of_capital",
      "mcp__etfiq__etf_benchmark",
      "mcp__etfiq__etf_movers",
      "mcp__etfiq__etf_news_today",
      "mcp__etfiq__strategy_signals",
      "mcp__etfiq__strategy_record",
      "mcp__etfiq__etf_risk_check"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as etfiq. Review it before you use it.

Capability tags behind 2 rules
  • mcp__etfiq__etfiq_page private-data
  • mcp__etfiq__find_page private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.etfiq/etfiq/verify?hash=268c3ec57c157a09be5f7aeddbaa79607d75b7b09a8343ce33963ab768ed52c3" | jq -e '.changed == false'

Pinned hash 268c3ec57c15, from Nov 14, 2026, 16:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.etfiq/etfiq/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.etfiq/etfiq
[![Anlyon Radar](https://radar.anlyon.com/badge/com.etfiq/etfiq.svg)](https://radar.anlyon.com/servers/com.etfiq/etfiq)

Source: MCP Registry. Synced Nov 14, 2026, 16:17 UTC.

ETFIQ MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the ETFIQ MCP server safe?

No scan can promise that. What its definitions show: 33 tools, 25 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the ETFIQ MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the ETFIQ MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the ETFIQ MCP server have?

33 tools: 25 write, 8 read. etf_profile, etf_holdings, etf_theme, etf_themes, etfiq_sections, etf_screen, etf_overlap, etfiq_as_of and 25 more.

Does the ETFIQ MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the ETFIQ MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the ETFIQ MCP server changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.