Ai Trading Agent

AI Trader MCP

Build your own AI hedge fund with Claude, Codex, Cursor, and OpenClaw.

The agent-native skills directory for Trader Dev MCP — write Pine Script, backtest crypto strategies, optimize parameters, and run a full quant research desk from one conversation.

[](https://github.com/DaviddTech/ai-trading-agent/stargazers) [](https://github.com/DaviddTech/ai-trading-agent/network/members) [](LICENSE) [](https://github.com/DaviddTech/ai-trading-agent/commits/main) [](https://trader.dev/) [](#-30-second-quickstart) [](#-30-second-quickstart) [](#-30-second-quickstart) [](#-what-you-can-build)

[Quickstart](#-30-second-quickstart) · [Skills](#-the-skills-directory) · [Examples](#-example-session) · [Roadmap](#-roadmap) · [Discord](#-community) · [YouTube](#-community)

---

> ⚠️ Research and education only. AI Trader MCP does not place real trades, send real orders, or guarantee profits. Backtests are not future performance. Crypto trading is risky and leverage can cause catastrophic losses. Read [docs/DISCLAIMER.md](docs/DISCLAIMER.md) before doing anything.

---

https://github.com/user-attachments/assets/fabc1c81-dab0-4ce5-863d-2d5fa633a579

▶ Watch the AI hedge fund desk in action — 60 seconds.

> "Just like human traders have TradingView, AI agents need their own quant research desk."

Most AI tools help traders write code. AI Trader MCP helps AI agents run the entire research workflow — generate hypotheses, write Pine Script, backtest, optimize, compare, and report. Built by DaviddTech, backtesting live on YouTube for 5+ years.

⚡ 30-second quickstart

https://github.com/user-attachments/assets/95757099-9a4c-4fea-a618-9b015eec942e

▶ Full install walkthrough — under a minute.

1. Install Trader Dev MCP in your agent (pick one):

# Claude Code
claude mcp add --transport sse --scope user trader-dev https://mcp.trader.dev/sse

# Codex
codex mcp add trader-dev -- npx -y mcp-remote https://mcp.trader.dev/sse

# Cursor / OpenClaw / Cline / Continue / Windsurf / Gemini CLI
Register https://mcp.trader.dev/sse as a remote SSE MCP server.

2. Paste this one-liner to your agent:

Read https://raw.githubusercontent.com/DaviddTech/ai-trading-agent/main/SKILL.md
and help me build an AI hedge fund research desk using Trader Dev MCP.

3. Ship your first backtest:

Backtest a Bollinger Band squeeze breakout on the top 10 Bybit pairs at 1h.
Report profit factor, max drawdown, and stability across symbols.
Reject overfit results.

That's it. Your agent is now a quant.

🔥 Why AI Trader MCP

| Without AI Trader MCP | With AI Trader MCP | |---|---| | Open TradingView, hand-code Pine Script, click backtest, copy results into a spreadsheet. | "Backtest this strategy on the top 10 Bybit pairs at 1h." Done in one message. | | Click-optimize parameters one input at a time. | Parameter sweeps across stop loss, take profit, ATR multiples, regime filters — natural language. | | Forget which version of a strategy worked last week. | Strategies live in Trader Dev. Fork, version, compare, promote, demote — all from chat. | | Pay for a quant team. | Spin up a Mathematician, Mean-Reversion Engineer, Strategy Optimizer, and Position Optimizer — for free. | | Wonder if your backtest is curve-fit. | Built-in robustness discipline: multi-pair, multi-timeframe, drawdown control, honest verdict labels. | | Use AI to write code. | Use AI to run the whole research desk. |

🏭 Don't want to build your own strategies?

Not every trader wants to be a quant researcher. If you'd rather skip the research and run trading bots that already work, StrategyFactory.ai is where they live.

• 400+ trading bots — every one **backtested and forward-tested with real-money live results**
• No Pine Script knowledge required — pick a bot, plug in, go
• Real performance data — not curve-fit screenshots, not "based on backtest" — actual live results
• Plays nicely with this repo — the AI Trader MCP skills can analyze, fork, and improve any Strategy Factory bot

| Path | What you do | Where to start | |---|---|---| | 🛠 Build it yourself | Use the skills, prompts, and loop roles in this repo. Pine Script + backtests + optimization, all from chat. | Stay here | | 🚀 Use what already works | Browse the marketplace, pick a bot, plug into your trading stack. | strategyfactory.ai |

> → Browse 400+ live-tested trading bots at StrategyFactory.ai →

🧠 The skills directory

Each skill is a focused, agent-readable SKILL.md that turns your AI client into a specialist on the desk.

| Skill | What it does | |---|---| | [Main SKILL.md](SKILL.md) | The entrypoint. Routes your agent into the right workflow. Start here. | | [AI Hedge Fund Manager](skills/ai-hedge-fund/SKILL.md) | Coordinates the research desk. Picks specialists. Enforces discipline. | | [Quant Mathematician](skills/quant-mathematician/SKILL.md) | Renaissance-style first-principles strategy creation. No retail indicator soup. | | [Mean Reversion Engineer](skills/mean-reversion-engineer/SKILL.md) | Engineered mean-reversion systems for crypto. Volatility-aware, regime-filtered. | | [Strategy Optimizer](skills/strategy-optimizer/SKILL.md) | Searches Trader Dev for existing strategies. Forks. Improves. Compares against baseline. | | [Position Optimizer](skills/position-optimizer/SKILL.md) | Tests leverage, fractional Kelly, vol-targeting, drawdown throttling, bounded recovery. Keeps entries frozen. |

Plus copy-paste workflow prompts in [prompts/](prompts/) and [examples/](examples/).

🔁 The 24/7 desk — loop roles

One conversation. Fifteen specialists. Forever. Every role is TradingView-native — pure Pine Script and OHLCV, no off-chain data feeds.

Drop any of these into your AI client's /loop command and walk away. Each role fires every 15 minutes, runs one focused research cycle through Trader Dev MCP, and writes a structured report.

# Greenfield strategy creation, every 15 minutes
/loop 15m read loop/01-quant-mathematician.md and execute it

# Risk audits the existing book, every 15 minutes
/loop 15m read loop/08-risk-manager.md and execute it

| Category | Roles | |---|---| | 🎯 Coordination | [Hedge Fund Manager](loop/00-ai-hedge-fund-manager.md) | | 🧮 Strategy creation | [Quant Mathematician](loop/01-quant-mathematician.md) · [Mean Reversion Engineer](loop/02-mean-reversion-engineer.md) · [Trend Following Engineer](loop/03-trend-following-engineer.md) · [Volatility Strategist](loop/04-volatility-strategist.md) · [Breakout Engineer](loop/05-breakout-engineer.md) | | 🔧 Optimization | [Strategy Optimizer](loop/06-strategy-optimizer.md) · [Position Optimizer](loop/07-position-optimizer.md) | | 🛡 Risk & robustness | [Risk Manager](loop/08-risk-manager.md) · [Drawdown Auditor](loop/09-drawdown-auditor.md) · [Overfitting Detector](loop/10-overfitting-detector.md) | | 📐 Structural & pattern | [Multi-Timeframe Strategist](loop/11-multi-timeframe-strategist.md) · [Liquidity Sweep Hunter](loop/12-liquidity-sweep-hunter.md) · [Pattern Recognition Strategist](loop/14-pattern-recognition-strategist.md) | | 🧪 Experimental | [Calendar & Lunar Cycle Strategist](loop/13-moon-phase-strategist.md) |

Full guide: [loop/README.md](loop/README.md).

📈 What you can build

• An AI hedge fund research desk — generate hypotheses → Pine Script → backtest → compare → report.
• A Pine Script generator — paste a strategy idea, get clean, no-repaint, no-lookahead Pine.
• A TradingView backtest worker — paste any Pine script, get a multi-pair, multi-timeframe robustness report.
• A parameter optimizer — sweep stops, TPs, ATR multiples, filters; reject overfits.
• A position-sizing lab — improve P&L by tuning leverage/Kelly/vol-targeting without changing entries.
• A live signal monitor — pipe Trader Dev signals to Telegram alerts.
• A strategy fork-and-improve loop — search the strategy library, fork winners, iterate one variable at a time.

🤖 Works with

| | | | | | | | | |:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|

If your agent speaks MCP, AI Trader MCP works.

💬 Example session

You:      I want to test a volatility breakout idea on crypto.
          Use the Quant Mathematician skill.

Agent:    Hypothesis: when realized volatility compresses below the
          20-period historical median for 8+ bars, a breakout in
          either direction has positive expectancy on 1h crypto.

          [writes Pine Script — no repaint, no lookahead]
          [calls mcp__trader-dev__run_backtest across 10 pairs × 4 timeframes]

          Results:
          Net profit:     +38.4%
          Profit factor:  1.62
          Max drawdown:   -14.1%
          Trades:         412
          Stable on 7/10 pairs across 1h, 2h, 4h.
          Fails on BTC and ETH — needs trend filter.

          Verdict: Incubate.
          Next iteration: add ADX 

**Built by [DaviddTech](https://davidd.tech) · Powered by [Trader Dev](https://trader.dev/)**

If AI agents should become real trading research assistants, **[star the repo ⭐](https://github.com/DaviddTech/ai-trading-agent)**.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [DaviddTech](https://github.com/DaviddTech)
- **Source:** [DaviddTech/ai-trading-agent](https://github.com/DaviddTech/ai-trading-agent)
- **License:** MIT
- **Homepage:** https://trader.dev/

Install and usage instructions live in the source repository linked above.