EdgeLock Trading Journal

Talk to your trading journal.

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Edgelock Query Trades: Search the trader's journal for individual trades, newest first. Returns prices, P/L, R, edge tag, market condition, plan adherence, and notes per trade. Use this to inspect or
  • Edgelock Get Stats: Aggregate performance stats: trade count, total P/L, win rate, average R, expectancy ($/trade), profit factor — optionally grouped. Win rate excludes break-even trades, matching th
  • Edgelock Get Edges: The trader's edge/setup tags with their written definitions (entry rules, criteria) and per-edge risk settings. Call this before judging whether a trade fits an edge, before writin

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Talk to your trading journal. Query your real trades, performance stats (win rate, P/L, R-multiples, with grouping that surfaces patterns like win rate by sleep quality), equity curve, edges, A+ setups, and journal — and log trades, save journal entries, define edge rules, and set your standing focus, all by chat. Trade screenshots return as viewable images. The first trading journal with a native MCP server. Per-user OAuth, free account.

Как подключить

Как подключить EdgeLock Trading Journal к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://edgelock-journal--elliot.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить EdgeLock Trading Journal к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://edgelock-journal--elliot.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить EdgeLock Trading Journal к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://edgelock-journal--elliot.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (14)

Технические названия из tools/list. Нужны только разработчикам.

edgelock_query_tradesSearch the trader's journal for individual trades, newest first. Returns prices, P/L, R, edge tag, market condition, plan adherence, and notes per trade. Use this to inspect or list specific trades; for aggregate questions (win rate, totals, "best edge") prefer edgelock_get_stats. Example: { ticker: "NQ", direction: "short", time_from: "10:00", date_from: "2026-06-01" }
edgelock_get_statsAggregate performance stats: trade count, total P/L, win rate, average R, expectancy ($/trade), profit factor — optionally grouped. Win rate excludes break-even trades, matching the in-app Dashboard. Aggregation is server-side, so prefer this over edgelock_query_trades for any "what is my win rate / which edge performs best / P&L by X" question. Example: { group_by: "edge", market_condition: "Trending" } answers "which edge works best in trends".
edgelock_get_edgesThe trader's edge/setup tags with their written definitions (entry rules, criteria) and per-edge risk settings. Call this before judging whether a trade fits an edge, before writing rules with edgelock_set_edge_rules, or to learn the trader's own rulebook. Returns all edges; no parameters.
edgelock_get_aplus_setupsTrades the trader marked as A+ (premium) setups — their visual pattern library of best entries. Returns trade details plus short-lived signed URLs for the screenshots (cheap, no inline images). To actually view a setup's chart, pass its trade id to edgelock_get_screenshots. Use when the trader asks about their best setups or wants pattern comparisons.
edgelock_get_screenshotsFetch the chart screenshots attached to a specific trade and return them as inline images you can actually see — use this to read a setup off the chart, compare entries, or describe what happened visually. Get the trade id from edgelock_query_trades or edgelock_get_aplus_setups first (that A+ tool returns signed URLs; this one returns the actual image bytes). Inline images are heavy, so call this only when you need to look at the chart, and for one trade at a time. Defaults to the first 4 screenshots; raise max_images for more.
edgelock_get_equity_curveCumulative P/L over time (all trade filters apply, so per-edge or per-ticker curves work). Returns equity points plus summary: max drawdown, peak/final equity, best/worst period, win/loss streaks. Use for drawdown, consistency, and streak questions. Periods bucket by UTC date.
edgelock_get_journalPremarket plans, postmarket reviews, daily personal-state check-ins (sleep, mood, stress), and weekly notes by date range. Also returns current_focus — the trader's ONE standing focus item (with who set it and when) plus recent focus history. Use for "what was my plan on X", "what did I write last week", and for reviewing whether trading followed the written plan. Defaults to the most recent 30 days.
edgelock_get_market_contextThe economic calendar EdgeLock ingests: scheduled economic events (CPI, FOMC, NFP, …) with impact level, forecast, previous, and actual readings. Use for trade-prep questions ("what events are coming up?") and for explaining volatility around a trade. Returns events in the requested date range, or all cached events when no range is given.
edgelock_log_tradeRecord a new trade in the journal. The server computes P/L and R exactly like the in-app form: P/L from entry/exit prices, position size, and the instrument's contract multiplier (futures point values are known server-side); R = P/L / risk. If the trader only knows their dollar P/L, pass pl instead of exit_price and the exit is back-computed (tick-snapped). Risk defaults from the stop-loss distance, then the edge's per-edge risk setting. ALWAYS pass an idempotency_key — any stable string unique to this trade (e.g. "nq-short-2026-06-11-1432") — so retries can't double-log. Example: { ticker: "NQ", direction: "short", size: 2, entry_price: 18000, stop_loss: 18010, pl: 250, edge: "Breakout", idempotency_key: "nq-short-2026-06-11-1432" }
edgelock_update_tradePatch an existing trade by id — the post-trade review path: set followed_plan and market_condition, append notes, or correct prices/size/risk (P/L and R are recomputed the same way the app does). Notes append by default; pass notes_mode: "replace" to overwrite. Get the id from edgelock_query_trades first, and confirm the returned ticker/timestamp matches the trade the trader meant. Example: { id: 1765432100000, followed_plan: false, notes: "Chased the entry." }
edgelock_save_journalWrite to the trading journal for a date: the premarket plan, the postmarket review, and/or the daily personal-state check-in (sleep, mood, stress, life stressors — the inputs behind the sleep/mood performance stats). Notes append to existing text by default; personal-state fields merge with what's already recorded. scope: "weekly" writes the weekly review instead (date may be any day in that week). Example: { date: "2026-06-11", premarket_notes: "A-setups only, max 2 trades.", personal_state: { sleep_quality: "poor", stress_level: "high" } }
edgelock_set_focusSet the trader's ONE standing focus — the single thing they're working on until it's replaced. Exactly one item: one imperative sentence, not a list. Read current_focus from edgelock_get_journal first; if you're replacing an existing focus, acknowledge it to the trader (kept, done, or superseded) before setting the new one. Inserts a new focus_items row with source "coach" — history is preserved, nothing is deleted. Example: { text: "Skip Reversal entries when the market condition is Volatile." }
edgelock_set_edge_rulesWrite the definition (entry rules / criteria) and/or per-edge risk for one of the trader's edges — the rulebook the coach checks behavior against. ALWAYS read the current edges with edgelock_get_edges first, and when you're overwriting an existing definition, show the trader what it was and confirm before replacing. Help the trader articulate THEIR rules — don't invent a rulebook for them. definition_mode "append" adds to the existing text; "replace" (default) overwrites it (the previous text comes back in the result either way). Risk needs both risk_amount AND risk_type to be meaningful. By default an unknown edge name is an error (so a typo can't spawn a junk edge); pass create: true to deliberately make a new edge. You cannot rename an edge here — historical trades are tagged by name. Example: { edge: "Breakout", definition: "Price breaks the prior-day high on rising volume; enter on the retest, stop below the breakout candle.", risk_amount: 200, risk_type: "dollar" }
edgelock_health_checkAudit how well the trading journal itself is set up — NOT trading performance. Checks: edges exist with written definitions and per-edge risk, premarket/postmarket journaling and personal-state check-in cadence on traded days, plan adherence and risk recorded on trades, and an A+ pattern library. Returns a pass/warn/fail checklist with a concrete fix per gap. Use it when the trader asks how complete their journal is, when starting to coach a new trader, or when stats come back hollow (R always 0, no sleep data) and you want to find out why.