QuantDinger
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 MCP server connects AI assistants to a self-hosted quantitative trading platform supporting cryptocurrency, stocks, and forex markets. The server wraps the QuantDinger Agent Gateway API, allowing Claude Desktop, Cursor, and other MCP-compatible clients to execute approved trading operations—market research, strategy backtesting, paper trading, and optionally live execution—without exposing broker credentials directly to the AI. It uses scoped, rate-limited tokens and requires explicit server-side authorization for live trading, keeping risk controls and deployment under operator supervision.
Key Features
Use Cases
- 01Let AI assistants research market data and generate Python trading strategies without manual API calls
- 02Backtest quantitative strategies across historical crypto and stock data from natural language prompts
- 03Execute paper trading experiments through Claude Desktop or Cursor with automatic risk controls
- 04Monitor live trading positions and orders via MCP tools while keeping broker credentials server-side
- 05Prototype multi-agent trading workflows combining AI research, code generation, and backtesting
- 06Deploy compliant automated trading with audit logs, resource limits, and production hardening overlays
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
QuantDinger — FAQ
What is the QuantDinger MCP server?+
It is a Model Context Protocol server that connects AI clients like Claude Desktop and Cursor to a self-hosted quantitative trading platform. The server provides tools for market research, strategy backtesting, paper trading, and optionally live execution across crypto, stocks, and forex markets.
How do I install and run the QuantDinger MCP server?+
Use the one-command installer (install.sh or install.ps1) to pull prebuilt Docker images, or clone the repository and run docker compose up. Then add the MCP server configuration to your AI client's settings, pointing it at the deployed QuantDinger instance with an agent token.
Which AI clients work with this MCP server?+
Claude Desktop, Cursor, Claude Code, Codex, and other clients supporting the Model Context Protocol can connect to the QuantDinger MCP server.
Do I need API keys or exchange accounts?+
For paper trading and backtesting, no exchange API keys are required. For live trading, you must create accounts on supported exchanges or brokers, generate restricted API keys, and store them encrypted in QuantDinger. AI provider keys (OpenRouter, OpenAI, Google, DeepSeek, etc.) are needed for market research features.
Is the QuantDinger MCP server free and open source?+
The backend is Apache 2.0 licensed and free to use. Web and mobile frontends are source-available under separate licenses. Trademark and branding use requires separate authorization; contact support@quantdinger.com for commercial licensing.
Can the MCP server execute real trades?+
By default, all agent trading is paper-only. Live execution requires an agent token with paper_only=false, AGENT_LIVE_TRADING_ENABLED=true on the server, and operator-configured limits and allowlists. Review the security model and compliance requirements before enabling live trading.
How do I install QuantDinger?+
Open the source repository on GitHub and follow its README. QuantDinger is a mcp server — MCP Agents Market links you directly to the official repo.
Is QuantDinger free?+
QuantDinger is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.