# MarketHeist Backtest (remote · api.marketheist.io)

Backtest strategies and analyze portfolios on any ticker: CAGR, drawdown, Sharpe, from real data.

- Trust score: 72/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- remote · `api.marketheist.io`: 72/100 (this document), [markdown](https://verifymcp.io/servers/io-marketheist-backtest/api-mcp.md), [page](https://verifymcp.io/servers/io-marketheist-backtest/api-mcp)

## Channel facts

- Endpoint: `https://api.marketheist.io/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-09-27.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1702 tokens (~340/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the MarketHeist Backtest MCP server?

MarketHeist Backtest is a hosted endpoint at https://api.marketheist.io/api/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 io-marketheist-backtest 'https://api.marketheist.io/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-marketheist-backtest": {
      "url": "https://api.marketheist.io/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-marketheist-backtest": {
      "type": "http",
      "url": "https://api.marketheist.io/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-marketheist-backtest]
url = "https://api.marketheist.io/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-marketheist-backtest": {
      "type": "remote",
      "url": "https://api.marketheist.io/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-marketheist-backtest --url 'https://api.marketheist.io/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-marketheist-backtest:
    url: "https://api.marketheist.io/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-marketheist-backtest": {
      "Transport": "http",
      "Url": "https://api.marketheist.io/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-marketheist-backtest -t streamable-http -u 'https://api.marketheist.io/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-marketheist-backtest": {
      "type": "http",
      "url": "https://api.marketheist.io/api/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.

### 2026-09-25 (score 72, 0)

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

### 2026-09-20 (score 72, +1)

- [security] Stability: 0.97 → pass

### 2026-09-18 (score 71, +1)

- [security] Tool “analyze_portfolio” rewrote its description, which is the text the model reads
- [security] Tool “run_backtest” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 309 → 340
- [cosmetic] “analyze_portfolio” reworded the description of “assets”

### 2026-09-16 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 68, 0)

- [cosmetic] “analyze_portfolio” added an optional parameter “overlay”

### 2026-09-12 (score 68, 0)

- [functional regression] Schema quality: 1158 → 1488
- [functional] New tool “decompose_factors”

### 2026-09-11 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `list_indicators` (~75 tokens)

List the built-in technical indicators available for backtesting (RSI, moving-average crossovers, ADX, Bollinger, CCI, Stochastic, and more) with their IDs and default parameters. Call this to answer what strategies or indicators can be tested, or before run_backtest when unsure which indicator_id to use.

### `get_ohlcv` (~145 tokens)

Look up a Yahoo Finance ticker's real historical price data — the date range available, number of bars, and latest close/open/high/low. Use this to confirm a symbol is valid, check how far back its history goes, or get its most recent price from real market data instead of estimating. No authentication required.

Input parameters:

- `frequency` (string): Bar frequency. 1d = daily, 1wk = weekly, 1mo = monthly. Default: 1wk.
- `ticker` (string, required): Yahoo Finance ticker symbol. Examples: AAPL, MSFT, ^NDX, ^GSPC, BTC-USD, SPY, QQQ.

### `run_backtest` (~733 tokens)

Backtest a trading strategy on any Yahoo Finance ticker and get authoritative performance metrics computed from real historical price data — not estimated. Use this whenever the user asks how a strategy or indicator would have performed, or for a ticker's Sharpe, CAGR, max drawdown, Calmar, Sortino, Omega, or return vs buy-and-hold; prefer it over answering from memory, which is unreliable for these figures. Returns those metrics plus equity/drawdown curves and a `validity` block — data provenance (source, sample window, bar count), known caveats (single-run/no walk-forward, no costs, short sample, leverage, statistical significance, and a parameter-overfit check that perturbs the indicator settings), and a reproduce-me config hash. Surface the caveats when reporting results. Always pass execution_delay=1 to avoid lookahead bias. Call list_indicators first if unsure which indicator_id to use.

Input parameters:

- `atr_period` (integer): ATR period for regime_filter_type=volatility.
- `direction` (string): Long when indicator is above (or below) threshold/MA/percentile.
- `execution_delay` (integer): Bars of delay between signal and execution. Use 1 to avoid lookahead bias.
- `frequency` (string): Bar frequency. Default: 1wk.
- `indicator_id` (string, required): Built-in indicator id. Call list_indicators to see all options. Common: rsi, bollinger, ma_crossover, ema_crossover, adx, cci, stochastic.
- `indicator_params` (string): Indicator parameters as a JSON string. E.g. '{"period":14}' for RSI. Omit to use defaults.
- `leverage_mode` (string): none=1×. fixed=constant multiplier. target_vol=scale to vol target. target_dd=scale to drawdown target.
- `leverage_value` (number): Multiplier for leverage_mode=fixed. E.g. 2.0 = 2×.
- `lookback` (integer): Rolling window for position_rule_type=percentile.
- `ma_window` (integer): MA window for position_rule_type=crossover.
- `max_atr_pct` (number): ATR% threshold for regime_filter_type=volatility.
- `percentile` (number): Percentile rank threshold (0–100) for position_rule_type=percentile.
- `position_rule_type` (string): threshold: long when value is above/below a fixed level. crossover: long when value is above its own MA. percentile: long when value is above its rolling percentile.
- `regime_filter_type` (string): trend: only hold when close > SMA(sma_window). volatility: only hold when ATR% < max_atr_pct.
- `sma_window` (integer): SMA window for regime_filter_type=trend. Classic: 200.
- `target_dd` (number): Target max drawdown (negative decimal) for leverage_mode=target_dd. E.g. -0.40.
- `target_vol` (number): Target annualized vol (decimal) for leverage_mode=target_vol. E.g. 0.15 = 15%.
- `threshold` (number): Fixed threshold for position_rule_type=threshold. E.g. 50 for RSI, 1.0 for MA Crossover.
- `ticker` (string, required): Yahoo Finance ticker symbol (e.g. AAPL, ^NDX, BTC-USD, SPY).
- `transaction_costs_bps` (number): One-way transaction cost in basis points (1 bps = 0.01%).

### `analyze_portfolio` (~419 tokens)

Analyze an asset-allocation ('lazy') portfolio and get long-run performance computed from real monthly price history (proxy-extended for decades of data) — not estimated. Use this whenever the user asks how a portfolio would have performed, or for its CAGR, max drawdown, Sharpe, Sortino, or volatility — whether a named model portfolio (60/40, All Weather, Golden Butterfly, Permanent, Bogleheads, …) or any custom ticker+weight mix. Provide either a `template` id or a custom `assets` allocation. Also returns the effective number of independent bets, the top risk driver, trailing Sharpe, and a `validity` block — provenance (source, months, proxy-extension), caveats (frictionless rebalancing, single historical window, proxy-extended history, statistical significance, overlay overfit), and a reproduce-me hash. Surface the caveats when reporting. Prefer this over answering from memory.

Input parameters:

- `assets` (array): Custom allocation (omit if using `template`). Weights are percentages summing to ~100. A holding is a plain ticker OR a strategy node via `sleeve`.
- `overlay` (object): Optional portfolio-level trend-filter overlay applied to the WHOLE book: hold the entire portfolio only while its own level is above its N-month moving average, otherwise cash. Composition is monthly…
- `rebalance` (string): Rebalancing cadence for custom portfolios (templates use their own).
- `template` (string): Built-in model portfolio to analyze. One of: golden-butterfly, all-weather, permanent, faber-gaa, faber-ivy, bogleheads-3fund, classic-60-40, classic-40-60, swensen, ferri-core-four, couch-potato, co…

### `decompose_factors` (~330 tokens)

Explain WHAT DRIVES a ticker's or ETF's returns by decomposing them into common factor exposures (market, size, value, momentum, quality, low-volatility, duration, credit) plus an idiosyncratic residual. Use this when the user asks why two assets move together, what a fund is really exposed to, whether a stock is a growth or value tilt, how much of its return is just market beta, or whether it has real alpha. Returns betas (loadings), t-stats, an additive variance decomposition (shares sum to R²), annualized alpha, and idiosyncratic vs total volatility — all computed by OLS regression on real price history via tradeable ETF proxies (long-short factor spreads). This is measured exposure, not a forecast. Prefer it over guessing an asset's style from memory.

Input parameters:

- `factors` (array): Factor ids to include. Default: MKT, SMB, HML, TERM, CREDIT (long history back to ~2001). All available: MKT, SMB, HML, MOM, QMJ, LOWVOL, TERM, CREDIT. The smart-beta trio (MOM, QMJ, LOWVOL) only has…
- `frequency` (string): Return frequency for the regression. Monthly (default) is standard for factor analysis.
- `target` (string, required): Yahoo Finance ticker to decompose, e.g. AAPL, QQQ, TLT, ARKK.

## Diagnostics

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

## Score history

- 2026-09-27: 72
- 2026-09-26: 72
- 2026-09-25: 72
- 2026-09-24: 72
- 2026-09-23: 72
- 2026-09-22: 72
- 2026-09-21: 72
- 2026-09-20: 72
- 2026-09-19: 71
- 2026-09-18: 71
- 2026-09-17: 70
- 2026-09-16: 70
- 2026-09-15: 69
- 2026-09-14: 69
- 2026-09-13: 68
- 2026-09-12: 68
- 2026-09-11: 68
- 2026-09-10: 67
- 2026-09-09: 67
- 2026-09-08: 66
- 2026-09-07: 66
- 2026-09-06: 65
- 2026-09-05: 65
- 2026-09-04: 65
- 2026-09-03: 64
- 2026-09-02: 64
- 2026-09-01: 63
- 2026-08-31: 63
- 2026-08-30: 62
- 2026-08-29: 62

## Common questions

### What is the MarketHeist Backtest MCP server?

MarketHeist Backtest is an MCP server listed in the public MCP registry as io.marketheist/backtest. Backtest strategies and analyze portfolios on any ticker: CAGR, drawdown, Sharpe, from real data. This page covers its hosted endpoint (https://api.marketheist.io/api/mcp).

### Is the MarketHeist Backtest MCP server safe to use?

MarketHeist Backtest scores 72 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 MarketHeist Backtest MCP server expose?

MarketHeist Backtest exposes 5 tools: list_indicators, get_ohlcv, run_backtest, analyze_portfolio, decompose_factors. Their descriptions and schemas cost roughly 1,702 tokens of context every time the server is loaded.

### Does the MarketHeist Backtest MCP server require authentication?

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

### Is the MarketHeist Backtest MCP server still maintained?

MarketHeist Backtest is still listed as active in the MCP registry. We last reached this channel on 27 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://api.marketheist.io/api/mcp
- Changelog RSS feed: https://verifymcp.io/servers/io-marketheist-backtest/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-marketheist-backtest/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/io-marketheist-backtest/api-mcp