# QuantGPT

Connect an AI coding client to US market data, stock analysis and strategy backtests. Use it to examine trading ideas or review a portfolio.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: quantgptco
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/quantgptco/quantgpt-mcp
- Updated: 2026-10-18
- HTML: https://affpapa.org/en/nevibecode/mcp/quantgpt

## What it does

QuantGPT gives an AI access to prices, returns, fundamentals and macroeconomic data. Its tools can grade US stocks across six dimensions, examine a portfolio and backtest strategies against historical data and a benchmark. The repository is a public listing for the hosted MCP server, not its server code.

The connection uses HTTP at `https://terminal.quantgpt.co/mcp`. Claude Code and other clients that authenticate with a key need a QuantGPT account key. Without that key, those clients cannot authenticate. MCP tools do not place orders; running a user strategy on QuantGPT Cloud is a separate QuantGPT Pro feature.

## Requirements
- Remote server: `https://terminal.quantgpt.co/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://terminal.quantgpt.co/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add quantgpt --url https://terminal.quantgpt.co/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "quantgpt": {
            "url": "https://terminal.quantgpt.co/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "quantgpt": {
            "type": "http",
            "url": "https://terminal.quantgpt.co/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http quantgpt https://terminal.quantgpt.co/mcp
```

## When to use it
- backtest a trading idea against historical data
- compare US stocks using market-wide grades
- retrieve prices and company fundamentals
- review portfolio holdings and implied trades

## Example prompts
- Test this trading idea against historical data and compare it with a benchmark.
- Grade `AAPL` and `MSFT`, then explain the main drivers behind each result.
- Review my portfolio and produce the trades implied by these criteria.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74569
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md