AKQuant — Claude Code MCP server: what it does, how to install
AKQuant — an MCP server for quantitative trading that enables AI agents to write strategies, run backtests, and analyze financial data.
MIT ★ 2,627 updated 2026-11-16
claude mcp add akquant -- uvx akquantWhat AKQuant 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.
What it helps with
- running backtests for trading strategies
- automating financial data retrieval
- generating performance and risk reports
- validating strategies against historical data
Example prompts for the agent
- Use AKQuant to run a backtest for
sh600000using 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.
How to install AKQuant
Platform CLI
claude mcp add akquant -- uvx akquantuvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>
Platform CLI
codex mcp add akquant -- uvx akquantuvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>
Config file
{
"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>
Config file
{
"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>
Platform CLI
gemini mcp add akquant uvx akquantuvx runs the command named after the package; if the README names another one, use uvx --from akquant <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about AKQuant
How to install AKQuant in Claude Code?
Run the command claude mcp add akquant -- uvx akquant in your project terminal.
What does AKQuant do?
It enables AI agents to perform quantitative analysis, test trading strategies, and visualize financial performance metrics.
What is required to run AKQuant?
You need uv installed and a Python environment. You must also provide a project directory path via the --root flag when configuring the server.