# Folionomiq (remote · folionomiq.com)

Measures a portfolio from price history: real bets, look-through, past crises in money. No advice.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-29

## Components

- remote · `folionomiq.com`: 66/100 (this document), [markdown](https://verifymcp.io/servers/com-folionomiq-folionomiq/folionomiq.md), [page](https://verifymcp.io/servers/com-folionomiq-folionomiq/folionomiq)

## Channel facts

- Endpoint: `https://folionomiq.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.5.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-29.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 33/100
  - 60% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 3983 tokens (~165/item across 24 items; 22 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - Manipulation check failed: an AI judge found 1 of 24 captured unit(s) of tool text manipulative, the first being "server instructions".
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Folionomiq MCP server?

Folionomiq is a hosted endpoint at https://folionomiq.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-folionomiq-folionomiq 'https://folionomiq.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-folionomiq-folionomiq": {
      "url": "https://folionomiq.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-folionomiq-folionomiq": {
      "type": "http",
      "url": "https://folionomiq.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-folionomiq-folionomiq]
url = "https://folionomiq.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-folionomiq-folionomiq": {
      "type": "remote",
      "url": "https://folionomiq.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-folionomiq-folionomiq --url 'https://folionomiq.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-folionomiq-folionomiq:
    url: "https://folionomiq.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-folionomiq-folionomiq": {
      "Transport": "http",
      "Url": "https://folionomiq.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-folionomiq-folionomiq -t streamable-http -u 'https://folionomiq.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-folionomiq-folionomiq": {
      "type": "http",
      "url": "https://folionomiq.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-29 (score 66, 0)

- [functional] Server version: c0cc594 → 95e9a6e

### 2026-09-28 (score 66, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 65, 0)

- [functional] Server version: f23f310 → ec9f467

### 2026-09-26 (score 65, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: d3509a5 → f23f310

### 2026-09-25 (score 64)

First indexed and scored.

## MCP tools (22)

### `measure_portfolio` (~214 tokens)

Measure a portfolio

Measure a portfolio from its price history: how many independent bets it
        really holds (effective bets), which holding carries risk out of line with
        its money, what it owns through its funds (with how much of the money that
        view covers), what past crises did to it in money with the time it took to
        come back, and the engine's full report with every figure numbered F1, F2…
        beside the method that produced it. Descriptive: no forecast, no advice.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `lookthrough`: What the portfolio owns through its funds.
- `report`: The numbered report: every figure beside its method.
- `stress`: What past crises did to this mix, replayed on its holdings.
- `structure`: How many independent bets the holdings add up to and who carries the risk.

### `compare_portfolios` (~101 tokens)

Compare portfolios side by side

Measure up to eight portfolios over one shared window of price history:
        growth, volatility, worst fall, and how each moved against the others.
        Says what each was; does not say which to hold.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `portfolios` (object, required): Two to eight portfolios, {label: {ticker: weight}}. Labels are shortened to letters and digits.

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `correlation`: Per pair of labels: how the portfolios moved together.
- `data`: Where the prices came from and what was missing or repaired.
- `end` (string|null): Shared window end.
- `metrics`: Per portfolio label: growth, volatility, worst fall and related figures.
- `series`: Per portfolio label: the growth path over the window.
- `start` (string|null): Shared window start.

### `test_a_change` (~156 tokens)

Before and after a proposed change

Measure a change before it is made: the current portfolio and the proposed
        one on the same price history — structure, risk, worst falls, and what the
        change adds or removes. The 'after' figures are counterfactual (that
        portfolio was not held). Never says whether to make the change.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `current` (object, required): What is held now, {ticker: weight}.
- `end`: Optional window end, YYYY-MM-DD.
- `proposed` (object, required): What would be held after the change, {ticker: weight}.
- `start`: Optional window start, YYYY-MM-DD.

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `axes`: Per axis: label, the question it answers, before, after.
- `data`: Where the prices came from and what was missing or repaired.
- `deltas`: Per measure: label, before, after, direction, unit.
- `historical`: Per past crisis: before and after.
- `improved`: Measures that moved one way.
- `introduces`: Risk the proposed holdings add that the current ones did not carry.
- `kind` (string|null): Kind of figures (counterfactual).
- `kind_means` (string|null): What that kind means.
- `limitations`: What this comparison cannot show.
- `similar`: Measures that barely moved.
- `summary` (string|null): One sentence on what the change moves.
- `window`: The shared window: start, end, years, which holding set it, crises inside.
- `worsened`: Measures that moved the other way.

### `search_symbols` (~86 tokens)

Find a ticker by name

Find the ticker for a fund or company by name, ticker fragment or ISIN,
        with the exchange it trades on. Listings nobody here has checked are
        marked unchecked.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `query` (string, required): A fund or company name, a ticker, or an ISIN.

Output parameters:

- `results` (array): Matches, best first.

### `validate_symbols` (~75 tokens)

Check symbols before measuring

Say which tickers have usable price history for a measurement, which do
        not, and the closest listing where a symbol is ambiguous.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `tickers` (array, required): Tickers to check, up to 150.

Output parameters:

- `base` (string|null): Base currency.
- `currencies`: Per ticker: its trading currency.
- `data`: Where the prices came from and what was missing or repaired.
- `problems`: Per failing ticker: why.
- `suggestions`: Per ambiguous ticker: the closest listing.
- `valid`: Per ticker: true when it has usable price history.

### `portfolio_structure` (~158 tokens)

How many real bets, and who carries the risk

How many independent bets the holdings add up to (from how they move
        together, not how many tickers there are), each holding's share of the
        risk beside its share of the money, and the same over recent years only.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `data`: Where the prices came from and what was missing or repaired.
- `effective_bets` (number|null): Effective number of independent bets (from correlations, not the ticker count).
- `max_risk_contribution` (number|null): That holding's share of the risk, 0 to 1.
- `max_risk_ticker` (string|null): The holding carrying the largest share of the portfolio's risk.
- `max_weight` (number|null): Its share of the money, 0 to 1.
- `max_weight_ticker` (string|null): The largest holding by money.
- `n_holdings` (number|null): Holdings measured.
- `recent`: The same figures over the recent years only.
- `risk_contributions`: [ticker, share of risk] pairs.
- `top_factor_share` (number|null): Share of the movement explained by the single strongest common factor.

### `look_through` (~172 tokens)

What the funds hold underneath

The companies owned through the funds, added up across funds: the largest
        names with their share of the whole portfolio, names reached through more
        than one fund, sectors, and how much of the money this view covers
        (funds publish their largest holdings, so the figures are minimums).

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `covered_fraction` (number|null): Share of the money whose underlying holdings are visible, 0 to 1.
- `data`: Where the prices came from and what was missing or repaired.
- `duplicated_exposure` (number|null): Share held more than once through different funds.
- `exposures`: [company, share of the whole portfolio] pairs, largest first.
- `n_companies` (number|null): Distinct companies seen underneath.
- `n_funds` (number|null): Funds looked through.
- `opaque`: Holdings with no breakdown to look through.
- `refused`: Funds whose breakdown the data vendor refused.
- `sectors`: [sector, share] pairs.
- `top_symbol` (string|null): The largest single company underneath.
- `top_symbol_weight` (number|null): Its share of the whole portfolio.

### `past_crises` (~179 tokens)

What past crises did to this mix

Replays the holdings through past crises (2008, 2020, 2022 and others
        inside their price history): the fall, the worst day, and the days it took
        to come back. In money when amounts are given. Measured, not forecast;
        crises before a holding existed are named as not tested.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `data`: Where the prices came from and what was missing or repaired.
- `limited_by` (string|null): The holding whose short history limits the window.
- `scenarios` (array|null): One entry per crisis.
- `window_start` (string|null): First date all holdings have prices.

### `portfolio_report` (~148 tokens)

The numbered report

The engine's written report on the portfolio: every figure numbered F1,
        F2… beside the method and window that produced it, plus a short receipt.
        Quote figures by their number.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `end` (string|null): Window end.
- `facts`: One entry per figure: id, label, value, method, window, limit.
- `markdown` (string|null): The report as markdown, figures numbered F1, F2…
- `receipt` (string|null): A short plain-text receipt of the same figures.
- `start` (string|null): Window start.

### `factor_exposure` (~163 tokens)

Sensitivity to common return patterns

How the portfolio's daily moves line up with the market, small versus
        large companies, value versus growth, and momentum (a four-factor
        regression), with which sensitivities are distinguishable from zero and how
        much of the movement the patterns explain.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `alpha_annual` (number|null): Return not explained by the factors, per year (estimated, not a skill measure).
- `betas`: Sensitivity per factor: mkt_rf (market), smb (small minus big), hml (value minus growth), mom (momentum).
- `data`: Where the prices came from and what was missing or repaired.
- `fit_caveat` (string|null): Why the fit is poor, when it is.
- `frequency` (string|null): Data frequency.
- `model` (string|null): Factor model used.
- `poor_fit` (boolean|null): True when the factors explain little.
- `r_squared` (number|null): Share of the daily movement the factors explain, 0 to 1.
- `t_stats`: t-statistic per factor; below about 2 in size, not distinguishable from zero.
- `years` (number|null): Years of history used.

### `currency_effect` (~164 tokens)

What exchange rates did to it

How much of the portfolio is priced outside the base currency, and what
        exchange-rate moves added to its growth, volatility and worst fall compared
        with the same holdings currency-hedged. Needs `base` set to the reader's
        currency to mean anything.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `base` (string|null): Base currency.
- `by_currency`: [currency, share of the money] pairs, by listing currency.
- `cagr_from_currency` (number|null): Growth per year added (or removed) by exchange rates.
- `data`: Where the prices came from and what was missing or repaired.
- `foreign_share` (number|null): Share of the money priced outside the base currency.
- `headline` (string|null): One sentence summary.
- `hedged`: The same with the currency moves removed.
- `limitations`: What this cannot show (listing currency is not earning currency).
- `share_of_vol` (number|null): Share of the volatility that comes from exchange rates.
- `unhedged`: Growth, volatility and worst fall as held.

### `health_axes` (~168 tokens)

The portfolio along separate axes

The portfolio read along separate axes (what the risk is built from, how
        it held up in crises, and others), each answering one question with the
        figures behind it. Readings, not a grade of how safe or good it is: no
        overall score is returned.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `axes`: Per axis: key, label, the question it answers, band, kind, drivers (each with label, value, unit and a plain reading).
- `data`: Where the prices came from and what was missing or repaired.
- `headline` (string|null): One sentence across the axes.
- `inputs`: What was measured: holdings, window, what was left out.
- `kinds`: What each kind of figure means (observed, replayed, estimated…).
- `limitations`: What these axes cannot show.
- `subscores`: The individual measured readings behind the axes.

### `sweep_holding` (~194 tokens)

One holding across its whole range

One holding measured at every weight from none to all, the rest of the
        money redistributed in proportion: volatility, that holding's share of the
        risk and the independent bets at each point, and whether most of the change
        comes from the first slice. Counterfactual; never says what weight to hold.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…
- `ticker` (string, required): The holding to sweep; must be one of `holdings`.

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `data`: Where the prices came from and what was missing or repaired.
- `end` (string|null): Window end.
- `kind` (string|null): Kind of figures (counterfactual).
- `knee` (number|null): Weight below which most of the change happens, when there is one.
- `note` (string|null): One sentence on where the change comes from.
- `points`: Per weight: weight, vol (volatility), risk_share (that holding's share of the risk), effective_bets, top_factor_share.
- `redistribution` (string|null): How the rest of the money is spread at each point.
- `start` (string|null): Window start.
- `ticker` (string|null): The holding swept.
- `total_change` (number|null): Change in volatility from none to the current weight.

### `reverse_stress` (~177 tokens)

What it would take to lose that much

Starts from a loss the reader cannot absorb and reports the least extreme
        combination of market moves that would produce it, beside the worst each of
        those moves actually did in the record. No probability is computed.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…
- `loss` (number): The loss to explain, as a fraction: 0.25 = lose a quarter.

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `coverage` (number|null): Share of the portfolio's movement these directions explain.
- `data`: Where the prices came from and what was missing or repaired.
- `line` (string|null): One sentence: what it would take.
- `moves`: Per market direction: label, plain wording, shock needed, sensitivity (beta), share of the loss, worst_seen in the record over the same number of days.
- `target` (number|null): The loss explained, as a negative fraction.
- `window_days` (number|null): Length of the move considered, in trading days.
- `window_end` (string|null): Record end.
- `window_start` (string|null): Record start.

### `return_history` (~170 tokens)

The record, month by month

What the mix returned over its record: growth per year (and after
        inflation), best and worst months and years, the range of any 12 months in a
        row, monthly returns by year, and how far the weights drift between
        rebalances. Past record, not a forecast.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `cagr` (number|null): Growth per year over the record.
- `data`: Where the prices came from and what was missing or repaired.
- `distribution`: Histogram of monthly returns: centers, counts.
- `drift`: Per holding: target weight and how far it drifted between rebalances.
- `grid`: Monthly returns: one row per year, null where the record has no month.
- `months`: Month names, aligned with each row of `grid`.
- `rolling_stats`: Any 12 months in a row: min, max, percentiles, share negative.
- `stats`: best_month, worst_month, best_year, worst_year, pct_positive, n_months, var95, cvar95, real_cagr (after inflation).
- `yearly`: Return per calendar year, aligned with `years`.
- `years`: Calendar years.

### `plain_findings` (~153 tokens)

The findings in plain words

A few findings in plain words (what the risk is built from, the worst
        historical shock), each with the evidence and window it rests on. Fast; for
        a first look before the full measurement.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `data`: Where the prices came from and what was missing or repaired.
- `insights`: Per finding: key, title, detail, severity (info or warning), evidence.

### `last_price` (~91 tokens)

Latest close

The latest daily close per ticker, in the base currency and in its own,
        with the date. Useful to turn a number of shares into an amount. A single
        figure per ticker; no price history is returned.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `tickers` (array, required): Tickers, up to 50.

Output parameters:

- `as_of` (string|null): Date of the close.
- `base` (string|null): Base currency.
- `currencies`: Per ticker: its trading currency.
- `data`: Where the prices came from and what was missing or repaired.
- `native_prices`: Per ticker: latest close in its own currency.
- `prices`: Per ticker: latest close in the base currency.

### `asset_info` (~57 tokens)

One fund or share: what it is and holds

One fund or share: name, type, exchange, yearly cost, its measured return,
        volatility and worst fall, and for a fund its largest holdings and sectors.

Input parameters:

- `ticker` (string, required): One ticker, as the exchange lists it.

Output parameters:

- `data`: Where the prices came from and what was missing or repaired.
- `fund`: For a fund: is_fund, holdings ([symbol, weight] pairs), sectors.
- `meta`: name, type, category, expense_ratio, currency, exchange, fund_family, total_assets, sector, isin.
- `stats`: last, ret_1y, vol, max_drawdown, years, start, end.
- `ticker` (string|null): Ticker.

### `simulate_paths` (~269 tokens)

Paths drawn from the record (simulated)

4,000 paths resampled from the portfolio's own price history: where the
        middle path and the outer tenths end after the years asked, in money and
        in today's money, and the share of paths ending below what was put in.
        SIMULATED, not a forecast: it assumes the future pays what the record paid,
        and it is refused when the record is too short or too extreme for the
        years asked.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `haircut` (number): Yearly return removed from every path, as a fraction (0.02 = assume 2% a year less than the record paid).
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…
- `monthly` (number): Amount added every month, in the base currency.
- `years` (integer): Years to run the paths, 1 to 40.

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `assumption` (string|null): The assumption every path rests on.
- `bands`: Percentile paths over time: p5 … p95, aligned with `years`.
- `data`: Where the prices came from and what was missing or repaired.
- `extrapolation` (number|null): Years asked divided by years of history.
- `historical_cagr` (number|null): Growth per year the record paid.
- `invested` (number|null): Money put in over the years asked.
- `kind` (string|null): simulated.
- `prob_below_invested` (number|null): Share of paths ending below what was put in (a share of simulated paths, not a probability of the future).
- `prob_below_real` (number|null): The same after inflation.
- `refused`: Present when no paths were drawn: the reasons, in words.
- `sample_years` (number|null): Years of shared history the paths are drawn from.
- `terminal`: Where the paths end, by percentile: p5, p10, p25, p50, p75, p90, p95.
- `terminal_real`: The same in today's money.
- `years`: Time axis of the bands, in years.
- `youngest` (string|null): When refused: the holding whose short history cut the record.

### `walk_forward` (~201 tokens)

Would refitting have helped? (out of sample)

Tests an allocation method honestly: refit on the years before each date,
        hold it on prices it had not seen, repeat, and compare that record with the
        portfolio actually held and with equal weight. Says whether refitting
        bought anything measurable. Returns no allocation to hold.

Input parameters:

- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings`: Optional: the portfolio actually held, {ticker: weight}, measured on the same span for comparison.
- `objective` (string): What each refit maximises or minimises: max_sharpe, min_variance, min_drawdown, min_cvar or max_quadratic_utility.
- `step_months` (integer): Months each fitted mix is held.
- `tickers` (array, required): The candidate holdings, 2 to 30.
- `train_years` (number): Years of history each refit sees.

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `data`: Where the prices came from and what was missing or repaired.
- `fitted_window`: First and last date of shared history.
- `objective` (string|null): What each refit optimised.
- `out_of_sample`: start, end, n_refits, train_years, step_months, mean_turnover, verdict (one sentence on the record), limitations, tracks (per track: label, cagr, vol, sharpe, max_drawdown, nav), refits (date, turnov…

### `check_before_you_buy` (~235 tokens)

Check before you buy

Measure one addition on the portfolio it would join, in the order a person
        asks: how much of it they already own (for a fund, the share of its money in
        companies already held, from its SEC filing when there is one), whether it
        adds an independent bet, and what past crises would have done to the money
        with it. Counterfactual; never says whether to buy.

Input parameters:

- `add` (string, required): The one ticker being considered.
- `amount` (number, required): How much of it, in the same units as `holdings` (money when holdings are amounts).
- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `add` (string|null): The ticker considered.
- `amount` (number|null): How much of it.
- `bets`: Independent bets before and after.
- `crises`: Per past crisis: fall before and after, as fractions.
- `data`: Where the prices came from and what was missing or repaired.
- `overlap`: How much of it is already owned: kind (fund, stock, opaque); for a fund already_share (share of its money in companies already held), seen_share, shared ([company, weight in it, weight in the portfol…
- `top_risk`: The holding carrying the most risk, and its share, before and after.
- `total_after` (number|null): Portfolio size after.
- `total_before` (number|null): Portfolio size before.
- `window`: The shared price window.

### `living_off_it` (~288 tokens)

Living off it: withdrawals replayed

Replays yearly withdrawals, raised with real inflation, on the portfolio's
        own monthly history from every month the record allows as a start: in how
        many starts the money lasted the full span, how many ran out and when, the
        lowest point from the worst start, and the highest yearly rate that ran out
        from no start in the record (this portfolio's own historical safe rate).
        Replayed, not simulated; a count of starts, never a probability; a span the
        record is too short for is said, not invented.

Input parameters:

- `amount`: How much is in the portfolio, when `holdings` are weights rather than money.
- `base`: Currency every figure is expressed in (USD, EUR, GBP, CAD…). Default USD.
- `holdings` (object, required): What is held: {ticker: weight or amount}. Weights need not sum to one; amounts in the base currency are also accepted (then the crises are shown in money). 1 to 100 holdings. Tickers as the exchange…
- `withdrawal` (number, required): Taken each year, in today's money; raised with the real price index of the base currency.
- `years` (integer): How many years, 5 to 50.

Output parameters:

- `_fence` (string|null): What these figures are and are not: descriptive, no forecast, no advice. Repeat its sense when presenting the result.
- `amount` (number|null): Money in the portfolio at each start.
- `data`: Where the prices came from and what was missing or repaired.
- `inflation`: Price index used: source, last_published, assumed.
- `n_complete` (number|null): Starts old enough for the full span.
- `n_complete_lasted` (number|null): Of those, how many lasted.
- `n_going` (number|null): Recent starts not run out so far, span not over.
- `n_ran_out` (number|null): Starts, complete or not, where the money ran out.
- `n_starts` (number|null): Starts followed (at least a year).
- `rate` (number|null): withdrawal / amount.
- `record`: start, end and years of the shared monthly record.
- `safe_rate` (number|null): Highest yearly rate that ran out from no start; null if no start is complete.
- `starts`: A sample of starts (every sixth): start, complete, months, ran_out, low_real, end_real.
- `testable_years` (number|null): The longest span the record can test in full.
- `withdrawal` (number|null): Taken each year, in start-month money, raised with prices.
- `worst`: The worst start: start, ran_out, months, low_real, low_at, end_real.
- `years` (number|null): Span asked for.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-folionomiq-folionomiq/folionomiq#diagnostics

## Score history

- 2026-09-29: 66
- 2026-09-28: 66
- 2026-09-27: 65
- 2026-09-26: 65
- 2026-09-25: 64

## Common questions

### What is the Folionomiq MCP server?

Folionomiq is an MCP server listed in the public MCP registry as com.folionomiq/folionomiq. Measures a portfolio from price history: real bets, look-through, past crises in money. No advice. This page covers its hosted endpoint (https://folionomiq.com/mcp).

### Is the Folionomiq MCP server safe to use?

Folionomiq scores 66 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Folionomiq MCP server expose?

Folionomiq exposes 22 tools: measure_portfolio, compare_portfolios, test_a_change, search_symbols, validate_symbols, and 17 more. Their descriptions and schemas cost roughly 3,619 tokens of context every time the server is loaded.

### Does the Folionomiq MCP server require authentication?

No. We connected to Folionomiq without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Folionomiq MCP server still maintained?

Folionomiq is still listed as active in the MCP registry. We last reached this channel on 29 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://folionomiq.com/mcp
- Website: https://folionomiq.com/connect
- Changelog RSS feed: https://verifymcp.io/servers/com-folionomiq-folionomiq/folionomiq.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-folionomiq-folionomiq/folionomiq.json
- HTML version of this page: https://verifymcp.io/servers/com-folionomiq-folionomiq/folionomiq