Tradetron · MCP tool reference

All 47 tools. This is what your AI can actually do.

The Tradetron MCP is the connector that turns ChatGPT, Gemini, Grok or Claude into a working quant desk on your account. This page is the power-user map: every tool, grouped by job, with worked examples of what really comes back — and an exact account of what the debug logs can and cannot show. New here? Start with the friendlier TT Assistant page.

Browse the tools → See real responses
47 tools8,500+ resolvable underlyings Runs on your own AI planZero lines of code
01 · The arc

It meets you where you are — explorer, builder, or live operator.

Stage 01 · Explore

Just looking around

Grounded answers about the platform, no account needed — plans, brokers, instruments, market hours.

  • "What plans do you have, and what do they cost?"
  • "Is Zerodha connected? Can I trade Sensex options?"
  • "Is the market open on 15 Aug?"
Stage 02 · Build

First strategies

Describe it; the MCP resolves keywords, validates the spec, and creates a real template in your account.

  • "NIFTY weekly short straddle, exit at 30% profit"
  • "Buy CE when RSI < 30, exit 2% or 3:15pm"
  • "Backtest it from Jan 2022, then save it"
Stage 03 · Run

Operating a live book

Where power users live: diagnostics that fuse engine and broker logs, surgical edits, portfolio-level review.

  • "Why didn't my straddle trade this morning?"
  • "Add a hedge leg to set 2 — don't rebuild it"
  • "Rank my strategies by damage done"
02 · The full arsenal

Every tool, grouped by the job you’re trying to get done.

You never call these by name — you just ask, and the assistant picks the right ones. The names are here so you know exactly what’s under the hood.

Build

Plain English → real strategy

Pulls a worked pattern, resolves every keyword, emits the exact template, creates it in your account with a link to open in the builder. Large multi-set books handled too.

tt_create_strategytt_create_strategy_chunkedtt_get_sample_strategytt_get_tradetron_quickstarttt_get_authoring_reference
Check first

Catch mistakes before they cost

Every spec validated against the locked schema before saving — wrong types, unknown keywords, silently-dropped legs caught locally. Custom Python is security-checked.

tt_validate_markdowntt_validate_pythontt_lookup_keywordtt_find_keywordtt_list_keywords_by_category
Backtest

Prove it on history

Run a backtest from the chat and get the full FastBT report link back — 6.5 years of audited data, ₹20 flat. Sweep parameters, poll long runs, check backtestability up front.

tt_backtest_strategytt_backtest_sweeptt_backtest_statustt_check_backtestability
Edit

Change one thing, not everything

Fetch, edit scalar fields, replace whole sets, or apply a surgical patch to one leg or condition. Structural edits are round-trip-verified — silent drops fail loud. Export to an importable file.

tt_get_strategytt_update_strategytt_apply_strategy_patchtt_export_strategytt_list_editable_fields
Paper trade

Rehearse before you risk capital

Deploy any strategy to paper trading — never live, that stays with you — and let it run against real market data. Ownership-checked, so it only ever touches your own account.

tt_deploy_strategy_paper
Debug live

Know exactly why it did — or didn’t — trade

One question fuses the deployment record, engine notification log and broker log into a diagnosis that names the layer at fault. Drill into either log, or the run counters, when you need to.

tt_diagnose_strategy ★tt_get_strategy_notificationstt_get_strategy_broker_logtt_get_my_deployed_strategiestt_get_my_deployed_strategy_detailtt_get_strategy_counters
Performance

Where the money is really going

P&L for one strategy — win-days, payoff ratio, max drawdown — or the whole book ranked winner-to-loser. Formatted reports and exports. Descriptive reads, never buy/sell advice.

tt_strategy_performancett_portfolio_reporttt_export_reportstt_report_template
What’s tradable

Brokers, instruments & your lists

Authoritative, deterministic lookups — not training-data guesses. Broker support, symbol tradability by exchange, step-by-step broker setup, and your watchlists resolved, read and modified.

tt_check_broker_supporttt_list_brokerstt_broker_integration_guidett_check_underlying_supporttt_list_underlyingstt_search_liststt_get_listtt_modify_list
Answers & account

Product Q&A, calendar, plan — and a human

Grounded, cited answers to any Tradetron question; market open/close for any date; your profile, plan and marketplace subscriptions. When the bot can’t help, it opens a real support conversation and relays the thread — with your say-so.

tt_ask_tttt_market_calendartt_get_my_profilett_get_my_subscriptiontt_list_planstt_get_my_strategy_subscriptionstt_open_crisp_conversationtt_check_crisp_responsett_reply_to_agent
03 · Ask & answer

You ask in plain English. Here’s what actually comes back.

Three real flows — build, debug, review. The sentence you type, the tools the assistant reaches for, and the shape of the response. Values are illustrative of the format.

Flow 01 · Buildplain English → a template you can deploy
You“Create a NIFTY weekly short straddle. Exit each leg at 30% profit, and square off everything at 3:15pm.”
MCP runs  tt_get_sample_strategytt_validate_markdowntt_create_strategy
tt_create_strategy · response
{
  "ok": true,
  "data": {
    "id": 9987412,
    "name": "NIFTY Weekly Short Straddle",
    "edit_url": "https://tradetron.tech/strategies/9987412/edit",
    "dry_run_verified": true,
    "validation": { "warnings": [] }
  }
}

You get a clickable edit_url — the strategy is already in your account, ready to review in the Advanced Strategy Builder. Nothing was saved until it validated clean.

Flow 02 · Debugone question, engine + broker logs fused
You“My short straddle is showing an error and didn’t trade this morning. What happened? (SID 30288650)”
MCP runs  tt_diagnose_strategy  — fuses the deployment record + engine log + broker log
tt_diagnose_strategy · diagnosis card
DIAGNOSIS · SID 30288650 · "NIFTY Weekly Short Straddle"
status  Error-Execution      mode  live      window  last 24h

ENGINE LOG  (what the strategy decided)
  09:20:01  Entry condition met — Time ≥ 09:20
  09:20:02  Placing SELL · NIFTY 24800 CE · NIFTY 24800 PE
  09:20:04  ✕ order rejected at broker

BROKER LOG  (what the broker actually did)
  09:20:04  Zerodha · order status REJECTED
  09:20:04  RMS: "margin exceeds available limit"

ANALYSIS   Not a strategy-logic fault. Your entry fired correctly;
           the broker blocked the order — insufficient margin.
FIX        Add funds or reduce lots, then re-enter. Logic is sound.

Before it reads a single line, the MCP verifies the SID is yours — ownership-checked and fail-closed. The card names which layer broke, so you don’t spend an hour editing a strategy that was never the problem.

Flow 03 · Reviewyour deployed strategies, at a glance
You“Which of my strategies are running right now, and are any stopped or in error?”
MCP runs  tt_get_my_deployed_strategies
tt_get_my_deployed_strategies · your account
DEPLOYED · 6 strategies

  ● Active       NIFTY Weekly Short Straddle    live
  ● Active       Bank Nifty Iron Condor         live
  ● Active       Gold Calendar Spread           live
  ⏸ Paused       Reversal Scalper               paper
  ✕ Error-Exec   Momentum Futures               live
  ○ Exited       Expiry Day Butterfly           live

NEXT  Just say "why is Momentum Futures in error?" — the
      engine + broker logs get pulled and the fault named
      (that's Flow 02, in the same chat).

One question surfaces every deployment and its state — Active, Paused, Blocked, Error-Execution, Exited — with live vs paper mode. Name any strategy and the assistant drills in: diagnose it, read its performance, or manage the deployment.

04 · Read this before you debug

What the logs show you — and the one thing they can’t.

The debug tools are the most misunderstood part of the connector, so let’s be exact about where the data comes from and where its edges are.

Where the log actually comes from. When you ask “why did my strategy do X”, the MCP reads your strategy’s live engine notification log — the engine’s own logging stream, pulled live. It is not a separate copy and not a summarised MCP-only table; it’s the same engine-side log, filtered to your strategy and gated so it will only ever read a strategy you own. Your dashboard’s event view is a summarised layer on top; this reads the raw stream underneath it.

What the notification log shows

state & decisions — persisted by the engine
  • Every position entry and exit, with instrument and side
  • Which entry/exit condition fired, and when
  • The Exited / terminal-status line when a strategy closes out
  • Engine errors and tracebacks
  • Broker rejections and blocks — RMS, margin, token, auth
  • Orders placed, order statuses, and the broker-side reason

What it can’t show — and why

the arithmetic behind a decision isn’t stored
  • The evaluated value of an indicator at each candle — e.g. “RSI was 62.3 at 10:15”
  • The live left- and right-hand values a condition compared
  • Anything computed in memory, per tick, only to answer true/false

Why: those numbers are evaluated live — every tick, in memory — purely to decide whether a condition is met. The log records the decision, not the arithmetic behind it, so there’s no stored per-candle value to fetch after the fact. Capturing the operand values behind each decision is on the roadmap.

05 · Connect

One URL. Works in ChatGPT, Gemini, Grok and Claude.

Tradetron MCP server URL
https://mcp.tradetron.tech/mcp
Sign-in: OAuth — you log in on Tradetron’s own page; the AI never sees your password

Step-by-step setup for each AI app — with plan requirements — lives on the TT Assistant page ↗. Read-only tools (plans, brokers, docs, drafts) work before you sign in; saving strategies and reading your logs, deployments and P&L need the OAuth connection.

06 · Power users

A rules file your AI reads every session

Save this once and stop re-typing the same guardrails. It tells any AI — Claude, ChatGPT, Gemini — how to work on your Tradetron strategies: ask before building, look up every keyword, validate and read back what was stored, and never touch a deployed template without telling you what that means. Drawn from real measured behaviour of the tools on this page.

Where to put it
Claude Code → CLAUDE.md · Claude apps → Project Instructions · ChatGPT → Custom Instructions
One file, ~8 KB. Edit the bracketed "My setup" lines at the bottom to match what you trade.

Prefer a file? Download tt-mcp-instructions.md — same content, save it straight into your project.

07 · Questions

The things power users ask first.

Do I need to know how Tradetron’s builder works?
No — that’s the point. You describe the strategy in plain English and the MCP handles keyword lookups, the schema, and field-by-field wiring. You end up with a real template in the Advanced Strategy Builder that you can review, tweak by hand, and deploy — you just didn’t have to assemble it.
Is the notification log the same as the one in my dashboard?
It’s the engine’s own notification log, read live — not a separate MCP table and not a summarised copy. The differences from reading it directly: it’s filtered to your strategy, and ownership-gated so it will only ever return a strategy you own. Your dashboard’s event view is a summarised layer on top of the same engine logging; the MCP reads the raw stream underneath. See the can/can’t panel above for exactly what it contains.
Can it show me the value of an indicator while my strategy runs?
Not from the logs. The log records which condition fired, not the value that made it fire — indicator values are computed live each tick and aren’t stored for retrieval. Capturing the operand values behind each decision, so you can read back exactly what an indicator saw when it triggered, is on the roadmap.
Do I need a Tradetron account to use it?
Not to explore. Plans and pricing, broker and instrument support, the market calendar, product Q&A, keyword lookups, and building and validating a draft all work without connecting. You need to connect to save a strategy, or to read your own logs, deployments and P&L. The MCP never places live orders; going live stays with you in Tradetron.
Does it place trades or move money?
No. Its job is the strategy lifecycle — create, validate, backtest, edit, paper-deploy, diagnose, report. It cannot take a strategy live, place live orders, or move funds — and managing what is already running (pause, resume, square off) stays with you in Tradetron too.
ChatGPT, Gemini, Grok or Claude — does it matter?
No — the 47 tools and their behaviour are identical underneath; the AI app is just the conversation layer. Use whichever you already have. The same tools also power Tradetron’s native chat.
What if it can’t answer something?
It won’t guess. Broker, instrument and pricing questions are answered from authoritative catalogs, not training data; product questions come with citations. When something genuinely needs a human, the MCP can open a real support conversation for you and relay the replies into the chat — only after you say yes.
Talk to your account

Stop clicking through menus. Just say what you want.

Build, backtest, paper trade, debug and review — all from one conversation, in the AI you already use.

Connect your AI See what you can build