# EA Trade Tester by TrueTest (remote · truetest.uk)

FREE first read, no sign-up: test an EA, trading bot, indicator or MT4/MT5 report for luck and costs

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `truetest.uk`: 79/100 (this document), [markdown](https://verifymcp.io/servers/uk-truetest-ea-tester/truetest.md), [page](https://verifymcp.io/servers/uk-truetest-ea-tester/truetest)

## Channel facts

- Endpoint: `https://truetest.uk/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## 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 2026-11-21.

- **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. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1327 tokens (~331/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 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**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 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 current MCP spec version (2026-07-28).

## Install

### How do I install the EA Trade Tester by TrueTest MCP server?

EA Trade Tester by TrueTest is a hosted endpoint at https://truetest.uk/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 uk-truetest-ea-tester 'https://truetest.uk/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "uk-truetest-ea-tester": {
      "url": "https://truetest.uk/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "uk-truetest-ea-tester": {
      "type": "http",
      "url": "https://truetest.uk/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.uk-truetest-ea-tester]
url = "https://truetest.uk/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "uk-truetest-ea-tester": {
      "type": "remote",
      "url": "https://truetest.uk/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add uk-truetest-ea-tester --url 'https://truetest.uk/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  uk-truetest-ea-tester:
    url: "https://truetest.uk/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "uk-truetest-ea-tester": {
      "Transport": "http",
      "Url": "https://truetest.uk/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add uk-truetest-ea-tester -t streamable-http -u 'https://truetest.uk/mcp'
```

### Other

```json
{
  "mcpServers": {
    "uk-truetest-ea-tester": {
      "type": "http",
      "url": "https://truetest.uk/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.

### 2026-11-21 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 77, +1)

- [functional] Server version: 1.0.0 → 1.0.2

### 2026-11-14 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 75, +1)

- [functional improvement] Schema quality: 374 → 331
- [functional] New tool “get_record_check”
- [cosmetic] “check_trading_record” reworded the description of “record_text”
- [cosmetic] Tool “check_trading_record” changed its title: Check a trading record (MT5 report, statement or CSV) → Check a trading record (MT4/MT5 report, statement or CSV)

### 2026-11-11 (score 74, +1)

- [functional improvement] Stability: unverified → 0.03
- [cosmetic] “test_strategy_code” reworded the description of “ai_draft”

### 2026-11-10 (score 73)

First indexed and scored.

## MCP tools (4)

### `check_trading_record` (~345 tokens)

Check a trading record (MT4/MT5 report, statement or CSV)

Judges whether a finished trading record's results look real or like luck: reads the trades, applies a luck test that allows for the number of versions tried, checks costs, losing years and grid/martingale signs, and returns a verdict (REAL / PROMISING / LIKELY_LUCK / NO_EVIDENCE / FAIL / HIDDEN_RISK / TOO_FEW) with its reason. Use it for a record of trades already taken or backtested; for strategy code or written rules use test_strategy_code. Nothing is stored: the record is read as data, never run, and discarded after the answer.

Input parameters:

- `filename` (string): The file's name, e.g. ReportTester.html or trades.csv (helps read the format)
- `is_forward` (boolean): True if every trade in the record was taken after the strategy was fixed (a forward or live record)
- `name` (string): Optional name of the strategy or EA
- `record_text` (string, required): Text of an MT4 or MT5 Strategy Tester report (HTML), an MT4/MT5 account statement (HTML), a cTrader, NinjaTrader, TradingView ('List of trades') or Myfxbook CSV export, or any CSV of closed trades (c…
- `versions_tried` (integer): How many versions, settings or EAs were tried before this one, as stated by the user (it raises the luck bar)

Output parameters:

- `evidence_scope`: what the verdict shows and what it does not show
- `first` (string)
- `good_points`: what the record does well; it follows the verdict and its reason
- `hidden_risk_found` (boolean)
- `last` (string)
- `losing_years` (integer)
- `luck_bar` (number)
- `luck_counter`
- `more` (string)
- `next_step`
- `note` (string)
- `read`: what was read from the record (trades, net, dates, currency, rows left out)
- `reason` (string)
- `summary` (string)
- `t_day_clustered`: left out when the record has no spread of results to measure
- `trade_days` (integer)
- `trades` (integer)
- `verdict` (string)
- `versions_tried` (integer)
- `worst_day`: info only: the largest daily loss, for scale (never a verdict input)

### `get_record_check` (~160 tokens)

Read a website result with its assistant code

Reads the result of a trading record the user checked on the TrueTest website, by the assistant code shown with that result. Use it when the record is too big for check_trading_record (over about 700 KB): the user uploads the file at https://truetest.uk/strategy and gives the code. It returns the verdict and numbers the website showed; it changes nothing, cannot buy anything, and never returns the trades, the file name or the strategy's name.

Input parameters:

- `code` (string, required): The assistant code shown with a record-check result on https://truetest.uk/strategy, e.g. 1A2B-3C4D-5E6F-7A8B (dashes and spaces are ignored)

Output parameters:

- `evidence_scope`: what the verdict shows and what it does not show
- `first` (string)
- `good_points`: what the record does well; it follows the verdict and its reason
- `hidden_risk_found` (boolean)
- `last` (string)
- `losing_years` (integer)
- `luck_bar` (number)
- `luck_counter`
- `more` (string)
- `next_step`
- `note` (string)
- `read`: what was read from the record (trades, net, dates, currency, rows left out)
- `reason` (string)
- `summary` (string)
- `t_day_clustered`: left out when the record has no spread of results to measure
- `trade_days` (integer)
- `trades` (integer)
- `verdict` (string)
- `versions_tried` (integer)
- `worst_day`: info only: the largest daily loss, for scale (never a verdict input)

### `test_strategy_code` (~603 tokens)

Test trading-strategy code (EA, indicator, Python bot, written rules)

Reads trading-strategy code - an MT5/MT4 Expert Advisor or indicator (.mq5/.mq4/.mqh/.set), a Python trading bot (.py), a TradingView Pine Script (.pine), a cTrader cBot or NinjaTrader strategy in C# (.cs) or rules written in plain words (.txt) - and reports code faults: wrong server clock, modules never called, settings never used, missing include files, unchecked orders, martingale or grid sizing. Without an email it returns this free first read only and stores nothing. With the user's email it also opens a private Strategy Lab and returns its link: TrueTest rebuilds the strategy as plain-English rules, the user checks them on the lab page, then TrueTest backtests its own rebuilt copy on up to 16 years of prices with real costs, runs a luck check and keeps a forward watch. It never runs the uploaded code as given and never places trades. For a finished trade record use check_trading_record; compiled .ex5/.ex4 files cannot be read (test their Strategy Tester report instead). Files are kept up to 90 days; the lab 12 months after the user's last visit (https://truetest.uk/security).

Input parameters:

- `ai_draft` (boolean): True only if the user agreed that our AI service may read the code text to draft the rule card. It is run by an outside AI provider, on servers in a country the UK has not approved for data protectio…
- `code` (string): One file's text, if you are not using files
- `email` (string): The user's email address, only if the user wants the full backtest: it identifies the user's tests for the luck bar and the 3-free-labs-a-day limit. TrueTest sends no email to it for a request made t…
- `filename` (string): That one file's name with its extension, e.g. MyEA.mq5. Give it whenever you have it; without it the language is guessed from the text.
- `files`: All the strategy's files together, e.g. the .mq5 plus its .mqh includes and .set settings; at most 20 files and about 1 MB in total through this connector (larger: upload on https://truetest.uk/strat…
- `name` (string): Optional name of the strategy
- `symbols` (string): Optional symbols to test, e.g. EURUSD, GBPUSD, XAUUSD
- `timeframe` (string): Optional timeframe, e.g. M15 or H1

Output parameters:

- `compiled`: free first read: true if a compiled file was sent
- `files`: free first read: the files read
- `findings` (array)
- `lab_url`: with an email: the private Strategy Lab link
- `language`: free first read: the language read
- `next_step`: compiled files only: what to send instead
- `note` (string)
- `read_as_from_text`: true when a file had no name with a known extension, so its language was guessed from its text (the summary says which)
- `reader_note`: the code reader is busy: what that means for this upload
- `reference`: with an email: the submission reference
- `rule_card`: with an email: who writes the plain-English rule card
- `stored`: free first read: always false (nothing is stored)
- `summary` (string)

### `get_lab_status` (~139 tokens)

Get a Strategy Lab's status and result

Returns where a Strategy Lab stands - waiting for the rule card, waiting for the user's check, queued, running, done or watching forward - with the place in the queue, a rough wait, and once tested the verdict and its reason. Use it when the user asks how their test is going. It changes nothing in the lab; a look counts as a visit, which keeps the lab for 12 more months.

Input parameters:

- `lab` (string, required): The private lab link from test_strategy_code or from a TrueTest email (https://truetest.uk/lab/...), or its 32-character code; 'demo' for the public sample lab

Output parameters:

- `cost_estimate`: present when the costs of some tested symbols are an estimate not yet checked against live prices: which ones
- `evidence_scope`: once tested: what the result shows and does not show
- `forward_watch`
- `good_points`: once tested: what the rebuilt strategy does well; it follows the verdict
- `kept_at_least_until`: a customer lab: the UTC date (yyyy-mm-dd) until which it is kept at least, under the current policy
- `kept_note`: how long the lab is kept and what moves that date on
- `lab_url` (string)
- `luck_counter`
- `meaning` (string)
- `note` (string)
- `queue_length`: queued or running: labs in the queue
- `reason`
- `rebuild`: present when the rebuild is not exact
- `rough_wait_minutes`: queued or running: a rough wait
- `sample`: present only for the public sample lab
- `status` (string)
- `summary` (string)
- `verdict`
- `versions_tested` (integer)
- `worst_day`: info only: the largest daily loss, for scale

## Diagnostics

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

## Score history

- 2026-11-21: 79
- 2026-11-20: 78
- 2026-11-19: 78
- 2026-11-18: 77
- 2026-11-17: 77
- 2026-11-16: 76
- 2026-11-15: 76
- 2026-11-14: 76
- 2026-11-13: 75
- 2026-11-12: 74
- 2026-11-11: 74
- 2026-11-10: 73

## Common questions

### What is the EA Trade Tester by TrueTest MCP server?

EA Trade Tester by TrueTest is an MCP server listed in the public MCP registry as uk.truetest/ea-tester. FREE first read, no sign-up: test an EA, trading bot, indicator or MT4/MT5 report for luck and costs. This page covers its hosted endpoint (https://truetest.uk/mcp).

### Is the EA Trade Tester by TrueTest MCP server safe to use?

EA Trade Tester by TrueTest scores 79 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 EA Trade Tester by TrueTest MCP server expose?

EA Trade Tester by TrueTest exposes 4 tools: check_trading_record, get_record_check, test_strategy_code, get_lab_status. Their descriptions and schemas cost roughly 1,247 tokens of context every time the server is loaded.

### Does the EA Trade Tester by TrueTest MCP server require authentication?

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

### Is the EA Trade Tester by TrueTest MCP server still maintained?

EA Trade Tester by TrueTest is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the EA Trade Tester by TrueTest MCP server?

VerifyMCP ran 13 checks on EA Trade Tester by TrueTest, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://truetest.uk/mcp
- Repository: https://github.com/postandcouriers-jpg/truetest-mcp
- Website: https://truetest.uk/connector
- Changelog RSS feed: https://verifymcp.io/servers/uk-truetest-ea-tester/truetest.xml
- Changelog JSON feed: https://verifymcp.io/servers/uk-truetest-ea-tester/truetest/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/uk-truetest-ea-tester/truetest.json
- HTML version of this page: https://verifymcp.io/servers/uk-truetest-ea-tester/truetest
