Skip to content
Back to search

ai-trading-agent

Build your own AI hedge fund with Claude, Codex, Cursor & OpenClaw. The agent-native skills directory for Trader Dev MCP โ€” write Pine Script, backtest crypto strategies, optimize parameters.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/daviddtech--ai-trading-agent/badge.svg)](/listings/daviddtech--ai-trading-agent)

HTML

<a href="/listings/daviddtech--ai-trading-agent"><img src="/api/listings/daviddtech--ai-trading-agent/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

> ๐Ÿค– **Prefer to hand it all to your AI?** Open [WORKBOOK.md](WORKBOOK.md) and paste it into any MCP-capable agent. It's a step-by-step, self-contained install and usage guide written for AI agents to follow top to bottom.

<div align="center">

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

*โ–ถ Full install walkthrough โ€” under a minute.*

</div>

**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.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md ยท Manifest ยท 183 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # AI Trader MCP Skill
  2. You are an AI trading research assistant connected to Trader Dev MCP.
  3. Your job is to help the user build an AI-powered quant research workflow using Pine Script, backtesting, optimisation, and disciplined reporting.
  4. ## Core principle
  5. Do not behave like a hype trading bot.
  6. Behave like a careful research assistant working inside an AI hedge fund lab.
  7. You must:
  8. 1. Understand the user's strategy goal.
  9. 2. Check that Trader Dev MCP tools are available.
  10. 3. Use the available MCP tool schemas instead of guessing arguments.
  11. 4. Write or inspect Pine Script carefully.
  12. 5. Backtest before making claims.
  13. 6. Compare results across symbols and timeframes.
  14. 7. Report weaknesses honestly.
  15. 8. Avoid overfitting.
  16. 9. Prioritise risk-adjusted performance over pretty equity curves.
  17. ## MCP setup
  18. Trader Dev MCP endpoint:
  19. ```text
  20. https://mcp.trader.dev/sse
  21. ```
  22. Claude Code:
  23. ```bash
  24. claude mcp add --transport sse --scope user trader-dev https://mcp.trader.dev/sse
  25. ```
  26. Codex:
  27. ```bash
  28. codex mcp add trader-dev -- npx -y mcp-remote https://mcp.trader.dev/sse
  29. ```
  30. OpenClaw:
  31. ```text
  32. Add https://mcp.trader.dev/sse as a remote SSE MCP server, then read this SKILL.md file.
  33. ```
  34. ## Market support
  35. Current support: crypto pairs.
  36. If the project gets enough demand, future support may include forex, stocks, futures, and additional data sources.
  37. ## Main workflows
  38. ### Workflow 1: Backtest a Pine Script strategy
  39. When the user provides Pine Script:
  40. 1. Read the full code.
  41. 2. Identify whether it is an indicator or a strategy.
  42. 3. If it is an indicator, explain what must be converted to create a strategy.
  43. 4. Check for repainting, lookahead, and future-looking logic.
  44. 5. Prepare the strategy for Trader Dev backtesting.
  45. 6. Backtest it across crypto pairs and timeframes.
  46. 7. Report the results.
  47. Metrics to report:
  48. - Net profit
  49. - Profit factor
  50. - Max drawdown
  51. - Win rate
  52. - Average trade
  53. - Number of trades
  54. - Average win
  55. - Average loss
  56. - Long performance
  57. - Short performance
  58. - Stability across symbols
  59. - Stability across timeframes
  60. ### Workflow 2: Build a new strategy
  61. When the user wants new strategy research:
  62. 1. Start from a mathematical hypothesis.
  63. 2. Do not use existing website strategies.
  64. 3. Do not optimise old strategies.
  65. 4. Do not copy retail indicator recipes.
  66. 5. Convert the hypothesis into Pine Script rules.
  67. 6. Backtest the strategy using Trader Dev.
  68. 7. Diagnose results.
  69. 8. Iterate scientifically.
  70. ### Workflow 3: Optimise an existing strategy
  71. When the user wants an optimizer:
  72. 1. Use `mcp__trader-dev__search_strategies` when available.
  73. 2. Select a strategy that already shows potential.
  74. 3. Fork the strategy.
  75. 4. Preserve a clean baseline.
  76. 5. Change one major idea at a time.
  77. 6. Backtest each version.
  78. 7. Keep only variants with meaningful risk-adjusted improvement.
  79. ### Workflow 4: Position optimisation
  80. When the user wants position optimisation:
  81. 1. Do not change entries or exits.
  82. 2. Optimise only position size, leverage, risk, Kelly fraction, drawdown throttle, volatility sizing, anti-martingale, or bounded recovery logic.
  83. 3. Compare against the baseline.
  84. 4. Report whether improvement came from genuine efficiency or simply more leverage.
  85. 5. Never hide liquidation risk, risk of ruin, or drawdown expansion.
  86. ## Research standards
  87. Always favour:
  88. 1. Robustness across symbols
  89. 2. Drawdown control
  90. 3. Profit factor
  91. 4. Average trade quality
  92. 5. Meaningful trade count
  93. 6. Stability across nearby timeframes
  94. 7. Simplicity
  95. 8. Net profit
  96. Never favour:
  97. - One amazing cherry-picked backtest
  98. - Low trade count results
  99. - Hidden overfitting
  100. - Unlimited martingale
  101. - Future-looking logic
  102. - Repainting
  103. - Ignoring fees or slippage
  104. - Ignoring liquidation risk
  105. ## Reporting format
  106. Use this format whenever possible:
  107. ```markdown
  108. # Trader Dev Research Report
  109. ## 1. Goal
  110. ## 2. Strategy or Hypothesis
  111. ## 3. Pine Script Changes
  112. ## 4. Backtest Matrix
  113. Symbols:
  114. Timeframes:
  115. Assumptions:
  116. ## 5. Results
  117. Net profit:
  118. Profit factor:
  119. Max drawdown:
  120. Win rate:
  121. Average trade:
  122. Trades:
  123. ## 6. Robustness Analysis
  124. ## 7. Weaknesses
  125. ## 8. Next Iteration
  126. ## 9. Verdict
  127. Reject / Watchlist / Incubate / Candidate / Production candidate
  128. ```
  129. ## Risk notice
  130. This skill is for research and education only. It is not financial advice. Do not encourage reckless live trading. Backtests are not guarantees of future performance.
README.md ยท README ยท 323 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. # AI Trader MCP
  3. ### Build your own AI hedge fund with Claude, Codex, Cursor, and OpenClaw.
  4. The agent-native skills directory for **Trader Dev MCP** โ€” write Pine Script, backtest crypto strategies, optimize parameters, and run a full quant research desk from one conversation.
  5. [![GitHub stars](https://img.shields.io/github/stars/DaviddTech/ai-trading-agent?style=social)](https://github.com/DaviddTech/ai-trading-agent/stargazers)
  6. [![GitHub forks](https://img.shields.io/github/forks/DaviddTech/ai-trading-agent?style=social)](https://github.com/DaviddTech/ai-trading-agent/network/members)
  7. [![License: MIT](https://img.shields.io/github/license/DaviddTech/ai-trading-agent)](LICENSE)
  8. [![Last commit](https://img.shields.io/github/last-commit/DaviddTech/ai-trading-agent)](https://github.com/DaviddTech/ai-trading-agent/commits/main)
  9. [![MCP](https://img.shields.io/badge/MCP-Trader.dev-blue)](https://trader.dev/)
  10. [![Claude Code](https://img.shields.io/badge/Claude%20Code-compatible-7C3AED)](#-30-second-quickstart)
  11. [![Codex](https://img.shields.io/badge/Codex-compatible-000000)](#-30-second-quickstart)
  12. [![Cursor](https://img.shields.io/badge/Cursor-compatible-000000)](#-30-second-quickstart)
  13. [![Pine Script](https://img.shields.io/badge/Pine%20Script-AI%20native-22C55E)](#-what-you-can-build)
  14. **[Quickstart](#-30-second-quickstart)** ยท **[Workbook](WORKBOOK.md)** ยท **[Skills](#-the-skills-directory)** ยท **[Examples](#-example-session)** ยท **[Roadmap](#-roadmap)** ยท **[Discord](#-community)** ยท **[YouTube](#-community)**
  15. </div>
  16. ---
  17. > โš ๏ธ **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.
  18. ---
  19. <div align="center">
  20. https://github.com/user-attachments/assets/fabc1c81-dab0-4ce5-863d-2d5fa633a579
  21. *โ–ถ Watch the AI hedge fund desk in action โ€” 60 seconds.*
  22. </div>
  23. > *"Just like human traders have TradingView, AI agents need their own quant research desk."*
  24. Most AI tools help traders write code. **AI Trader MCP helps AI agents run the entire research workflow** โ€” generate hypotheses, write Pine Script, backtest, optimize, compare, and report. Built by [DaviddTech](https://davidd.tech), backtesting live on YouTube for 5+ years.
  25. ## โšก 30-second quickstart
  26. > ๐Ÿค– **Prefer to hand it all to your AI?** Open [WORKBOOK.md](WORKBOOK.md) and paste it into any MCP-capable agent. It's a step-by-step, self-contained install and usage guide written for AI agents to follow top to bottom.
  27. <div align="center">
  28. https://github.com/user-attachments/assets/95757099-9a4c-4fea-a618-9b015eec942e
  29. *โ–ถ Full install walkthrough โ€” under a minute.*
  30. </div>
  31. **1. Install Trader Dev MCP in your agent (pick one):**
  32. ```bash
  33. # Claude Code
  34. claude mcp add --transport sse --scope user trader-dev https://mcp.trader.dev/sse
  35. ```
  36. ```bash
  37. # Codex
  38. codex mcp add trader-dev -- npx -y mcp-remote https://mcp.trader.dev/sse
  39. ```
  40. ```text
  41. # Cursor / OpenClaw / Cline / Continue / Windsurf / Gemini CLI
  42. Register https://mcp.trader.dev/sse as a remote SSE MCP server.
  43. ```
  44. **2. Paste this one-liner to your agent:**
  45. ```text
  46. Read https://raw.githubusercontent.com/DaviddTech/ai-trading-agent/main/SKILL.md
  47. and help me build an AI hedge fund research desk using Trader Dev MCP.
  48. ```
  49. **3. Ship your first backtest:**
  50. ```text
  51. Backtest a Bollinger Band squeeze breakout on the top 10 Bybit pairs at 1h.
  52. Report profit factor, max drawdown, and stability across symbols.
  53. Reject overfit results.
  54. ```
  55. That's it. Your agent is now a quant.
  56. ## ๐Ÿ”ฅ Why AI Trader MCP
  57. | Without AI Trader MCP | With AI Trader MCP |
  58. |---|---|
  59. | 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. |
  60. | Click-optimize parameters one input at a time. | Parameter sweeps across stop loss, take profit, ATR multiples, regime filters โ€” natural language. |
  61. | Forget which version of a strategy worked last week. | Strategies live in Trader Dev. Fork, version, compare, promote, demote โ€” all from chat. |
  62. | Pay for a quant team. | Spin up a Mathematician, Mean-Reversion Engineer, Strategy Optimizer, and Position Optimizer โ€” for free. |
  63. | Wonder if your backtest is curve-fit. | Built-in robustness discipline: multi-pair, multi-timeframe, drawdown control, honest verdict labels. |
  64. | Use AI to *write* code. | Use AI to *run the whole research desk.* |
  65. ## ๐Ÿญ Don't want to build your own strategies?
  66. 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](https://strategyfactory.ai)** is where they live.
  67. - **400+ trading bots** โ€” every one **backtested *and* forward-tested with real-money live results**
  68. - **No Pine Script knowledge required** โ€” pick a bot, plug in, go
  69. - **Real performance data** โ€” not curve-fit screenshots, not "based on backtest" โ€” actual live results
  70. - **Plays nicely with this repo** โ€” the AI Trader MCP skills can analyze, fork, and improve any Strategy Factory bot
  71. | Path | What you do | Where to start |
  72. |---|---|---|
  73. | ๐Ÿ›  **Build it yourself** | Use the skills, prompts, and loop roles in this repo. Pine Script + backtests + optimization, all from chat. | Stay here |
  74. | ๐Ÿš€ **Use what already works** | Browse the marketplace, pick a bot, plug into your trading stack. | [strategyfactory.ai](https://strategyfactory.ai) |
  75. > **[โ†’ Browse 400+ live-tested trading bots at StrategyFactory.ai โ†’](https://strategyfactory.ai)**
  76. ## ๐Ÿง  The skills directory
  77. Each skill is a focused, agent-readable `SKILL.md` that turns your AI client into a specialist on the desk.
  78. | Skill | What it does |
  79. |---|---|
  80. | **[Main SKILL.md](SKILL.md)** | The entrypoint. Routes your agent into the right workflow. Start here. |
  81. | **[AI Hedge Fund Manager](skills/ai-hedge-fund/SKILL.md)** | Coordinates the research desk. Picks specialists. Enforces discipline. |
  82. | **[Quant Mathematician](skills/quant-mathematician/SKILL.md)** | Renaissance-style first-principles strategy creation. No retail indicator soup. |
  83. | **[Mean Reversion Engineer](skills/mean-reversion-engineer/SKILL.md)** | Engineered mean-reversion systems for crypto. Volatility-aware, regime-filtered. |
  84. | **[Strategy Optimizer](skills/strategy-optimizer/SKILL.md)** | Searches Trader Dev for existing strategies. Forks. Improves. Compares against baseline. |
  85. | **[Position Optimizer](skills/position-optimizer/SKILL.md)** | Tests leverage, fractional Kelly, vol-targeting, drawdown throttling, bounded recovery. Keeps entries frozen. |
  86. Plus copy-paste workflow prompts in [`prompts/`](prompts/) and [`examples/`](examples/).
  87. ## ๐Ÿ” The 24/7 desk โ€” loop roles
  88. One conversation. Fifteen specialists. Forever. **Every role is TradingView-native** โ€” pure Pine Script and OHLCV, no off-chain data feeds.
  89. 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.
  90. ```bash
  91. # Greenfield strategy creation, every 15 minutes
  92. /loop 15m read loop/01-quant-mathematician.md and execute it
  93. # Risk audits the existing book, every 15 minutes
  94. /loop 15m read loop/08-risk-manager.md and execute it
  95. ```
  96. | Category | Roles |
  97. |---|---|
  98. | ๐ŸŽฏ Coordination | [Hedge Fund Manager](loop/00-ai-hedge-fund-manager.md) |
  99. | ๐Ÿงฎ Strategy creation | [Quant Mathematician](loop/01-quant-mathematician.md) ยท [Mean Reversion Engineer](loop/02-mean-reversion-engineer.md) ยท [Trend Following Engineer](loop/03-trend-following-engineer.md) ยท [Volatility Strategist](loop/04-volatility-strategist.md) ยท [Breakout Engineer](loop/05-breakout-engineer.md) |
  100. | ๐Ÿ”ง Optimization | [Strategy Optimizer](loop/06-strategy-optimizer.md) ยท [Position Optimizer](loop/07-position-optimizer.md) |
  101. | ๐Ÿ›ก Risk & robustness | [Risk Manager](loop/08-risk-manager.md) ยท [Drawdown Auditor](loop/09-drawdown-auditor.md) ยท [Overfitting Detector](loop/10-overfitting-detector.md) |
  102. | ๐Ÿ“ Structural & pattern | [Multi-Timeframe Strategist](loop/11-multi-timeframe-strategist.md) ยท [Liquidity Sweep Hunter](loop/12-liquidity-sweep-hunter.md) ยท [Pattern Recognition Strategist](loop/14-pattern-recognition-strategist.md) |
  103. | ๐Ÿงช Experimental | [Calendar & Lunar Cycle Strategist](loop/13-moon-phase-strategist.md) |
  104. Full guide: [loop/README.md](loop/README.md).
  105. ## ๐Ÿ“ˆ What you can build
  106. - **An AI hedge fund research desk** โ€” generate hypotheses โ†’ Pine Script โ†’ backtest โ†’ compare โ†’ report.
  107. - **A Pine Script generator** โ€” paste a strategy idea, get clean, no-repaint, no-lookahead Pine.
  108. - **A TradingView backtest worker** โ€” paste any Pine script, get a multi-pair, multi-timeframe robustness report.
  109. - **A parameter optimizer** โ€” sweep stops, TPs, ATR multiples, filters; reject overfits.
  110. - **A position-sizing lab** โ€” improve P&L by tuning leverage/Kelly/vol-targeting *without* changing entries.
  111. - **A live signal monitor** โ€” pipe Trader Dev signals to Telegram alerts.
  112. - **A strategy fork-and-improve loop** โ€” search the strategy library, fork winners, iterate one variable at a time.
  113. ## ๐Ÿค– Works with
  114. <div align="center">
  115. | ![Claude](https://img.shields.io/badge/Claude%20Code-7C3AED?logo=anthropic&logoColor=white) | ![Codex](https://img.shields.io/badge/Codex-000000?logo=openai&logoColor=white) | ![Cursor](https://img.shields.io/badge/Cursor-000000?logo=cursor&logoColor=white) | ![OpenClaw](https://img.shields.io/badge/OpenClaw-FF6B35) | ![Cline](https://img.shields.io/badge/Cline-1E40AF) | ![Continue](https://img.shields.io/badge/Continue-22C55E) | ![Windsurf](https://img.shields.io/badge/Windsurf-06B6D4) | ![Gemini](https://img.shields.io/badge/Gemini%20CLI-4285F4?logo=google&logoColor=white) |
  116. |:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
  117. </div>
  118. If your agent speaks MCP, AI Trader MCP works.
  119. ## ๐Ÿ’ฌ Example session
  120. ```text
  121. You: I want to test a volatility breakout idea on crypto.
  122. Use the Quant Mathematician skill.
  123. Agent: Hypothesis: when realized volatility compresses below the
  124. 20-period historical median for 8+ bars, a breakout in
  125. either direction has positive expectancy on 1h crypto.
  126. [writes Pine Script โ€” no repaint, no lookahead]
  127. [calls mcp__trader-dev__run_backtest across 10 pairs ร— 4 timeframes]
  128. Results:
  129. Net profit: +38.4%
  130. Profit factor: 1.62
  131. Max drawdown: -14.1%
  132. Trades: 412
  133. Stable on 7/10 pairs across 1h, 2h, 4h.
  134. Fails on BTC and ETH โ€” needs trend filter.
  135. Verdict: Incubate.
  136. Next iteration: add ADX < 25 regime filter.
  137. ```
  138. *(Illustrative format. Numbers depend on your strategy, market, and assumptions.)*
  139. ## ๐Ÿ›  Powered by Trader Dev MCP
  140. [Trader Dev](https://trader.dev/) is the live MCP server doing the heavy lifting. Agents connected to it can:
  141. - ๐Ÿ” `search_strategies` โ€” discover proven strategy ideas
  142. - โš™๏ธ `create_strategy` / `update_strategy` / `fork_strategy` โ€” version your research
  143. - ๐Ÿ“Š `run_backtest` / `quick_backtest` โ€” backtest Pine Script across crypto pairs
  144. - ๐ŸŽฏ `optimize_strategy` โ€” automated parameter sweeps
  145. - ๐Ÿ”ฌ `compare_backtests` โ€” diff versions side by side
  146. - ๐Ÿ“ˆ `get_equity_curve` / `get_trades` / `get_backtest_result` โ€” pull granular metrics
  147. - ๐Ÿ“ก `get_recent_signals` / `list_active_alerts` / `test_telegram_sink` โ€” live signal monitoring
  148. - ๐Ÿ’ผ `promote_strategy` / `demote_strategy` โ€” lifecycle management
  149. Full tool reference: [docs/AGENT_GUIDE.md](docs/AGENT_GUIDE.md). Agents should always call `tools/list` first โ€” never guess arguments.
  150. ## ๐Ÿช™ Current market support
  151. Trader Dev currently works on **crypto pairs**.
  152. If we get enough interest, we'll add **US stocks, Forex, and Futures** next.
  153. ## ๐Ÿ—บ Roadmap
  154. **Live now**
  155. - Trader Dev MCP server (SSE)
  156. - Pine Script backtesting from any MCP-compatible agent
  157. - Crypto pair coverage
  158. - Parameter and position optimization workflows
  159. - 5 specialist agent skills + prompt library
  160. - Telegram alert workflows
  161. **In progress**
  162. - Native AI Trader alert system (less reliance on TradingView alerts)
  163. - Backtest screenshots and shareable report cards pulled from the web app
  164. - Downloadable Pine Scripts from the web app
  165. - Risk Manager, PineScript Developer, Backtest Analyst, and Report Writer skills
  166. - Walk-forward and Monte Carlo robustness checks
  167. **Community-requested**
  168. - Forex, stocks, futures
  169. - More exchange data sources
  170. - Strategy tournament leaderboards
  171. - AI quant team presets by trading style
  172. ## ๐Ÿงช Research standards
  173. This is not a hype trading bot. The skills are written to enforce:
  174. - โœ… Robustness across symbols and nearby timeframes
  175. - โœ… Drawdown control and profit factor over raw net profit
  176. - โœ… Honest verdict labels โ€” *Reject / Watchlist / Incubate / Candidate / Production candidate*
  177. - โœ… No repainting, no lookahead, no future data
  178. - โŒ No martingale without strict caps
  179. - โŒ No one-coin cherry-picked backtests
  180. - โŒ No hidden liquidation risk
  181. ## โญ Star history
  182. [![Star History Chart](https://api.star-history.com/svg?repos=DaviddTech/ai-trading-agent&type=Date)](https://star-history.com/#DaviddTech/ai-trading-agent&Date)
  183. If this repo saves you a single evening of manual backtesting, **[give it a star](https://github.com/DaviddTech/ai-trading-agent)**.
  184. ## ๐Ÿค Contributing
  185. Great contributions:
  186. - New prompts and agent skills
  187. - Pine Script strategy templates
  188. - Backtest report formats
  189. - Risk-management workflows
  190. - Translations
  191. - Demo videos and screenshots
  192. See [CONTRIBUTING.md](CONTRIBUTING.md). Open an issue with [`Skill request`](.github/ISSUE_TEMPLATE/skill_request.md) or share a result with [`Backtest result`](.github/ISSUE_TEMPLATE/backtest_result.md).
  193. ## ๐Ÿ‘‹ Community
  194. - ๐Ÿฆ **Twitter / X** โ€” follow [@DaviddTech](https://twitter.com/DaviddTech) for new strategies and AI quant updates
  195. - ๐ŸŽฅ **YouTube** โ€” 5 years of live strategy backtesting on [DaviddTech](https://www.youtube.com/@DaviddTech)
  196. - ๐ŸŒ **Website** โ€” [davidd.tech](https://davidd.tech)
  197. - ๐Ÿ’ฌ **Discord** โ€” *coming soon โ€” watch the repo to be notified*
  198. ## โ“ FAQ
  199. **Is this a trading bot?**
  200. No. It is a skills directory that lets AI agents talk to the Trader Dev MCP server. Trader Dev runs the backtests; the skills tell your agent how to behave like a quant researcher.
  201. **Does it place real trades?**
  202. No. AI Trader MCP is for research, backtesting, and education. Live signals can be piped to Telegram, but execution is your responsibility.
  203. **Which AI agents are supported?**
  204. Anything that speaks MCP โ€” Claude Code, Codex, Cursor, OpenClaw, Cline, Continue, Windsurf, Gemini CLI, and any custom agent using the [Model Context Protocol](https://modelcontextprotocol.io).
  205. **Why Pine Script?**
  206. Because TradingView is where most traders already live, and Pine Script is the fastest path from idea to backtest. Python/Polars support is on the roadmap.
  207. **How is this different from `virattt/ai-hedge-fund`?**
  208. That repo is a Python simulation of named-investor personas. AI Trader MCP is the **infrastructure layer** โ€” an MCP server plus skills that any AI agent can use to actually generate, backtest, and optimize Pine Script strategies. They are complementary.
  209. **Do I need a Trader Dev account?**
  210. Some MCP tools require authentication. See [docs/QUICKSTART.md](docs/QUICKSTART.md).
  211. **Will this make me money?**
  212. No promises, no guarantees, no financial advice. See the disclaimer.
  213. ## ๐Ÿ›ก Risk notice
  214. Trading is risky. Crypto is risky. Leverage is risky. Backtests are not guarantees. This project is for **research, backtesting, and education only**. Always paper trade and forward test before considering any live deployment. The authors and contributors accept no responsibility for losses. Full text: [docs/DISCLAIMER.md](docs/DISCLAIMER.md).
  215. ## ๐Ÿ“„ License
  216. MIT โ€” see [LICENSE](LICENSE).
  217. ---
  218. <div align="center">
  219. **Built by [DaviddTech](https://davidd.tech) ยท Powered by [Trader Dev](https://trader.dev/)**
  220. If AI agents should become real trading research assistants, **[star the repo โญ](https://github.com/DaviddTech/ai-trading-agent)**.
  221. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If itโ€™s helped, pass it on.