# AKQuant

AKQuant — an MCP server for quantitative trading that enables AI agents to write strategies, run backtests, and analyze financial data.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2627 repo stars
- Author: akfamily
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/akfamily/akquant
- Updated: 2026-11-16
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/akquant

## What it does

AKQuant provides tools for building and testing trading strategies. The server connects your AI agent to a Rust-based engine, handling calculations, risk management, and event processing. It supports stocks, futures, and options, allowing you to run simulations against historical market data.

The tool requires `uv` to be installed. It enables the agent to fetch data, implement trading logic via Python classes, and generate HTML performance reports. During setup, you must specify a project directory using the `--root` flag, where the agent will store strategy files and analysis results.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add akquant -- uvx akquant
```
uvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>

### Codex

**Platform CLI**
```bash
codex mcp add akquant -- uvx akquant
```
uvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "akquant": {
            "command": "uvx",
            "args": [
                "akquant"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "akquant": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "akquant"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add akquant uvx akquant
```
uvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>

## When to use it
- running backtests for trading strategies
- automating financial data retrieval
- generating performance and risk reports
- validating strategies against historical data

## Example prompts
- Use AKQuant to run a backtest for `sh600000` using the last year of data.
- Write a moving average crossover strategy and run it through AKQuant.
- Generate a performance report including drawdown and returns for the current strategy.

## Similar
- [llmquant-options](https://affpapa.org/en/nevibecode/skills/llmquant-options.md) — skill · 517 installs
- [Varrd](https://affpapa.org/en/nevibecode/mcp/varrd.md) — MCP server · 2427 installs
- [algorithmic-trading](https://affpapa.org/en/nevibecode/skills/algorithmic-trading.md) — skill · 544 installs
- [NexusTrade Financial MCP](https://affpapa.org/en/nevibecode/mcp/nexustrade-financial-mcp.md) — MCP server · ★ 11 repo stars
- [Canli Validation](https://affpapa.org/en/nevibecode/mcp/canli-validation.md) — MCP server · ★ 6 repo stars
- [CPZAI](https://affpapa.org/en/nevibecode/mcp/cpzai.md) — MCP server · ★ 1 repo stars

---
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
