AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading
QuantDinger is a self-hosted, open-source MCP server written in Python that covers the full quantitative trading workflow: AI-assisted strategy research, automated Python code generation, backtesting, paper trading, and live order execution across crypto exchanges (Binance, Coinbase), stock brokers (Alpaca), and forex platforms including MetaTrader 5. It exposes all of these capabilities as MCP tools, meaning Claude Code and other MCP-compatible AI agents can call them directly to retrieve market data, run backtests, or place trades through conversational prompts. The stack ships as a Docker Compose bundle with a prebuilt frontend, a PostgreSQL 16 database, and an Agent Gateway layer that handles the MCP protocol. A notable detail is the two-minute quick-start promise via a single Docker command, with no need to clone the repo or build any frontend assets. Quantitative traders, algorithmic strategy developers, and teams wanting to automate research-to-execution pipelines without relying on a third-party SaaS will find the most use here.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add quantdinger -- python -m quantdinger{
"mcpServers": {
"quantdinger": {
"command": "python",
"args": ["-m", "http.server"],
"env": {
"SECRET_KEY": "<secret_key>"
}
}
}
}SECRET_KEYMCP Servers overview
<div align="center">
<a href="https://github.com/brokermr810/QuantDinger">
<img src="docs/screenshots/logo.jpg" alt="QuantDinger Logo" width="220" height="220">
</a>
<h1>QuantDinger</h1>
<h3>The open-source AI infrastructure layer for quant trading</h3>
<p><strong>Turn trading ideas into Python strategies, backtests, paper trading, and live execution — all in one self-hosted stack.</strong></p>
<p><em>AI research → Strategy code → Backtest → Paper/Live execution → Monitoring</em></p>
<div align="center" style="max-width: 680px; margin: 1.25rem auto 0; padding: 20px 22px 22px; border: 1px solid #d1d9e0; border-radius: 16px;">
<p style="margin: 0 0 14px; line-height: 1.65;">
<a href="README.md"><strong>English</strong></a>
<span style="color: #afb8c1;"> · </span>
<a href="docs/README_CN.md"><strong>简体中文</strong></a>
<span style="color: #afb8c1;"> · </span>
<a href="docs/README_JA.md"><strong>日本語</strong></a>
<span style="color: #afb8c1;"> · </span>
<a href="docs/README_KO.md"><strong>한국어</strong></a>
<span style="color: #afb8c1;"> · </span>
<a href="docs/README_TH.md"><strong>ไทย</strong></a>
<span style="color: #afb8c1;"> · </span>
<a href="docs/README_VI.md"><strong>Tiếng Việt</strong></a>
<span style="color: #afb8c1;"> · </span>
<a href="docs/README_AR.md"><strong>العربية</strong></a>
</p>
<p style="margin: 0 0 18px; padding-bottom: 16px; border-bottom: 1px solid #eaeef2; line-height: 2;">
<a href="https://ai.quantdinger.com"><strong>SaaS</strong></a>
<span style="color: #d8dee4;"> · </span>
<a href="docs/api/README.md"><strong>API Docs</strong></a>
<span style="color: #d8dee4;"> · </span>
<a href="https://www.youtube.com/watch?v=tNAZ9uMiUUw"><strong>Video Demo</strong></a>
<span style="color: #d8dee4;"> · </span>
<a href="https://www.quantdinger.com"><strong>Website</strong></a>
<span style="color: #d8dee4;"> · </span>
<a href="https://aws.amazon.com/marketplace/pp/prodview-naanrb7d2mbc6"><strong>AWS Marketplace</strong></a>
</p>
<p style="margin: 0; line-height: 2;">
<a href="https://t.me/quantdinger"><img src="https://img.shields.io/badge/Telegram-Join-26A5E4?style=flat-square&logo=telegram&logoColor=white" alt="Telegram"></a>
<a href="https://discord.com/invite/tyx5B6TChr"><img src="https://img.shields.io/badge/Discord-Server-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord"></a>
<a href="https://youtube.com/@quantdinger"><img src="https://img.shields.io/badge/YouTube-%40quantdinger-FF0000?style=flat-square&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://x.com/QuantDinger_EN"><img src="https://img.shields.io/badge/X-%40QuantDinger_EN-000000?style=flat-square&logo=x&logoColor=white" alt="X"></a>
</p>
</div>
<p style="margin-top: 1.45rem; margin-bottom: 10px;">
<a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=flat-square&logo=apache" alt="License"></a>
<img src="https://img.shields.io/github/v/release/brokermr810/QuantDinger?style=flat-square&color=orange&label=Version" alt="Version">
<img src="https://img.shields.io/badge/Python-3.10%2B%20%7C%20Docker%20image%203.12-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python">
<img src="https://img.shields.io/badge/Docker-Compose%20Ready-2496ED?style=flat-square&logo=docker&logoColor=white" alt="Docker">
<img src="https://img.shields.io/badge/Frontend-Prebuilt-1f8b4c?style=flat-square" alt="Frontend">
<img src="https://img.shields.io/badge/Agent%20Gateway-MCP%20Ready-6f42c1?style=flat-square" alt="Agent Gateway">
<img src="https://img.shields.io/badge/PostgreSQL-16-336791?style=flat-square&logo=postgresql&logoColor=white" alt="PostgreSQL">
<img src="https://img.shields.io/github/stars/brokermr810/QuantDinger?style=flat-square&logo=github" alt="Stars">
<img src="https://img.shields.io/github/forks/brokermr810/QuantDinger?style=flat-square&logo=github&label=Forks" alt="Forks">
</p>
<p style="margin: 10px 0 12px;">
<a href="https://aws.amazon.com/marketplace/pp/prodview-naanrb7d2mbc6"><img src="https://img.shields.io/badge/AWS%20Marketplace-AMI%20%7C%20CentOS%209-232F3E?style=flat-square&logo=amazonaws&logoColor=white" alt="QuantDinger on AWS Marketplace (ThinkCloud AMI)"></a>
</p>
<p style="margin: 12px 0 10px;">
<a href="https://oosmetrics.com/repo/brokermr810/QuantDinger"><img src="https://api.oosmetrics.com/api/v1/badge/achievement/4991ab54-52d2-46d4-a03a-67b47b61ae4b.svg" alt="oosmetrics — Top 7 in Training by acceleration (2026-04-25)"></a>
</p>
<p style="margin-top: 14px;">
<a href="https://www.producthunt.com/products/quantdinger/launches/quantdinger?embed=true&utm_source=badge-featured&utm_medium=badge&utm_campaign=badge-quantdinger" target="_blank" rel="noopener noreferrer"><img alt="QuantDinger - A local-first, open-source AI quant trading workspace | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=1057439&theme=light&t=1777556016131"></a>
</p>
</div>
---
## Contents
[Try in 2 minutes](#try-in-2-minutes) · [Why QuantDinger](#why-quantdinger) · [Safety model](#safety-model) · [Technical highlights](#technical-highlights) · [Repositories](#related-repositories) · [AI agents & MCP](#use-it-from-an-ai-agent-cursor--claude-code--codex--mcp) · [Overview](#product-overview) · [Features](#features-at-a-glance) · [Visual tour](#visual-tour) · [Architecture](#architecture) · [Install](#installation--first-time-setup-docker-compose) · [Docs](#documentation) · [FAQ](#faq) · [License](#license-and-commercial-terms)
---
## Try in 2 minutes
> **Fastest path: one command.** No `git clone`, no `npm`, no Vue source tree. Prebuilt images from GHCR; `SECRET_KEY` auto-generated on first backend start.
**Prerequisites:** [Docker](https://docs.docker.com/get-docker/) with Compose v2 (Docker Desktop on Windows/macOS). **Node.js is not required.**
```bash
curl -fsSL https://raw.githubusercontent.com/brokermr810/QuantDinger/main/install.sh | bash
```
Installs to `~/quantdinger` by default (override: `… | bash -s -- /opt/quantdinger`). Re-run the same command to pull latest images and restart.
Then open **`http://localhost:8888`**, sign in with **`quantdinger` / `123456`**, and **change the default admin password**.
<details>
<summary><b>Windows, manual clone, or mirror troubleshooting</b></summary>
**Windows (PowerShell)** — folder name after clone is **`QuantDinger`**:
```powershell
git clone https://github.com/brokermr810/QuantDinger.git
Set-Location QuantDinger
Copy-Item backend_api_python\env.example -Destination backend_api_python\.env
$key = & python -c "import secrets; print(secrets.token_hex(32))" 2>$null
if (-not $key) { $key = & py -c "import secrets; print(secrets.token_hex(32))" 2>$null }
(Get-Content backend_api_python\.env) -replace '^SECRET_KEY=.*$', "SECRET_KEY=$key" | Set-Content backend_api_python\.env -Encoding utf8
docker compose pull
docker compose up -d
```
**Standard clone (macOS / Linux):**
```bash
git clone https://github.com/brokermr810/QuantDinger.git && cd QuantDinger && cp backend_api_python/env.example backend_api_python/.env && chmod +x scripts/generate-secret-key.sh && ./scripts/generate-secret-key.sh && docker compose pull && docker compose up -d
```
**Slow `docker pull` (China / VPN):** add `IMAGE_PREFIX=docker.m.daocloud.io/library/` to a repository-root `.env`, or configure **Docker Desktop → Proxies**.
</details>
For step-by-step detail and troubleshooting, see **[Installation & first-time setup](#installation--first-time-setup-docker-compose)**.
---
## Why QuantDinger
| Traditional workflow | QuantDinger |
|----------------------|-------------|
| ChatGPT only generates code | Runs, backtests, and executes strategies in one stack |
| TradingView + Jupyter + exchange bots are fragmented | One self-hosted stack from research to execution |
| SaaS platforms hold API keys | User-owned deployment — your infra, your keys |
| AI agents without scopes or audit | Scoped Agent Gateway, paper-only default, audit logs |
QuantDinger is a **self-hosted, local-first** quantitative infrastructure layer — not a chatbot with a buy button. It unifies **multi-LLM research**, **Python-native strategy engines**, **server-side backtesting**, and **multi-broker live execution** (10+ crypto venues, IBKR, MT5, Alpaca) in one production-grade stack you fully control.
## Safety model
- **Agent tokens are paper-only by default** — live trading requires explicit server-side unlock.
- **Live execution requires explicit permission** — token scope + `AGENT_LIVE_TRADING_ENABLED` on self-hosted stacks.
- **Exchange keys stay inside the user's own deployment** — not held by QuantDinger SaaS operators on self-hosted installs.
- **Every agent call is audit-logged** — append-only audit trail for automation and compliance review.
- **QuantDinger does not provide investment advice** — software for lawful research and execution only; you are responsible for compliance and risk.
## API documentation
| Resource | Link |
|----------|------|
| Human Web API (OpenAPI) | [`docs/api/openapi.yaml`](docs/api/openapi.yaml) |
| ReDoc viewer (serve over HTTP) | [`docs/api/index.html`](docs/api/index.html) — run `python -m http.server` from `docs/api/` |
| Conventions (auth, envelopes) | [`docs/API_CONVENTIONS.md`](docs/API_CONVENTIONS.md) |
| Agent Gateway | [`docs/agent/agent-openapi.json`](docs/agent/agent-openapi.json) |
---
<div align="center">
<img src="docs/screenshots/ezgif.com-animated-gif-maker.gif" alt="QuantDinger quick demo: install, sign in, charting, AI analysis, and strategy workflow" width="920" style="border-radius: 12px; borWhat people ask about QuantDinger
What is brokermr810/QuantDinger?
+
brokermr810/QuantDinger is mcp servers for the Claude AI ecosystem. AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading It has 7.9k GitHub stars and was last updated 2d ago.
How do I install QuantDinger?
+
You can install QuantDinger by cloning the repository (https://github.com/brokermr810/QuantDinger) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is brokermr810/QuantDinger safe to use?
+
Our security agent has analyzed brokermr810/QuantDinger and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains brokermr810/QuantDinger?
+
brokermr810/QuantDinger is maintained by brokermr810. The last recorded GitHub activity is from 2d ago, with 12 open issues.
Are there alternatives to QuantDinger?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy QuantDinger to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/brokermr810-quantdinger)<a href="https://claudewave.com/repo/brokermr810-quantdinger"><img src="https://claudewave.com/api/badge/brokermr810-quantdinger" alt="Featured on ClaudeWave: brokermr810/QuantDinger" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。