ai_trading_journel_mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TJ_MT5_DIR | No | Override the MetaTrader 5 Expert Advisor export folder path if the folders are not found automatically. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| log_tradeA | Log a trade the user dictates that is NOT in MT5 (other broker, or not synced). Returns the trade and warnings. |
| annotate_tradeC | Add journal details (setup, emotions, mistakes, notes, rating) to a trade, usually one synced from MT5. |
| delete_tradeB | Delete a manually logged trade (MT5 trades can't be deleted; they come back on sync). |
| write_day_noteB | Save the pre-session plan or post-session review for a day (text is appended to what is there). |
| list_tagsA | The user's setup, emotion and mistake vocabularies. Reuse these names when tagging. |
| set_trading_rulesB | Save the user's written trading rules; coaching reviews check behaviour against them. |
| find_tradesC | Search trades. Returns a compact list plus the total count. |
| get_tradeA | Full detail of one trade: prices, costs, R, MFE/MAE, deals, journal, and any behaviour flags it triggered. |
| get_performanceC | Win rate, P&L, profit factor, expectancy, R, drawdown, streaks — optionally broken down by dimension. |
| get_instrument_breakdownC | Per-instrument stats, verdict (edge/leaking/breakeven/unproven), best/worst sessions, insights and red flags. |
| get_calendarB | Daily P&L for a month (trading days only), weekly totals and the month summary. |
| get_behavior_reportB | Behavioural red flags (revenge trading, overtrading, no/widened stops, early exits, sizing up after losses...) with cost. |
| get_coaching_contextA | Everything needed for a coaching review in one call: stats vs previous period, per-instrument verdicts and insights, breakdowns, behaviour flags, best/worst trades, journal notes, day notes, the user's trading rules and the previous report's action plan. |
| save_ai_reportA | Save a coaching review so it shows in the web app (AI Coach page and each instrument's page). Every claim should be backed by numbers from the journal. |
| save_trade_feedbackB | Attach AI feedback to a single trade (shown on the trade's page). |
| sync_mt5B | Pull the latest trades from MT5 right now. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| weekly_review | Review the last 7 days and save a coaching report. |
| monthly_review | Review the last 30 days and save a coaching report. |
| instrument_review | Deep-dive one instrument over the last quarter. |
| trade_review | Review one trade and attach feedback to it. |
| log_trades | Dictate one or more trades or annotations. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 16 tools
Most tools have clearly distinct resource+action targets: logging vs annotating vs deleting a trade, note writing, searching, single-trade detail, and various reporting dimensions. The main overlap is get_coaching_context, which bundles data also available via get_performance, get_instrument_breakdown, and get_behavior_report, so an agent might wonder when to use the bundle versus the individual reports. save_ai_report vs save_trade_feedback is also a mild boundary that descriptions mostly resolve (report vs per-trade feedback).
All names follow a consistent snake_case verb_noun pattern (log_trade, annotate_trade, delete_trade, get_performance, save_ai_report, sync_mt5, etc.). Verb choice is predictable and domain-appropriate, with no mixed conventions or cryptic abbreviations.
16 tools is slightly above the ideal 3-15 range but each appears to earn its place: core CRUD on trades, journaling, tagging, rules, and several targeted analytics views. The set is well-scoped for a trading journal rather than padded with redundant operations.
Core lifecycle is well covered: log/annotate/delete trades, sync MT5, day notes, rules, search/detail, and rich analytics plus coaching reports. Minor gaps exist: no way to edit a manually logged trade's core fields (only annotate or delete), no tag creation/management beyond list_tags, and no update operation for day notes or trading rules beyond overwrite/append.