TickTest

Backtest A-share quant strategies with natural language and compare results fast.

Source

Official Registry

Updated

2026-10-07

// securityCaution

Requires keys· TICKTEST_API_KEY, TICKTEST_API_URL
Runs locally
Official / curated
Open source
Community-trusted

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "TickTest" MCP server from askskill:
Run: claude mcp add 'io-github-shakagold-ticktest-mcp' -- npx -y ticktest-mcp

// use cases

Quickly validate a quant idea

A data analyst or researcher can describe an A-share strategy in natural language and quickly get historical backtest results, reducing the need to write backtest code first. It is useful for validating an idea before deeper research.

Compare moving average parameter sets

When a user wants to compare single MA, dual MA, or different period settings, this tool helps run side-by-side backtests quickly. It is suitable for screening more promising strategy configurations.

Test cross-timeframe and Turtle trading rules

Users can try cross-timeframe combinations or Turtle trading-related rules and examine their historical behavior in A-shares. It is suitable for exploring the feasibility of different trading logics.

// docs

No documentation provided

Check the source repo for usage and examples.

Go to source repo ↗

// FAQ

What does this tool mainly do?

It is an A-share quantitative backtesting MCP server that lets an AI agent run backtests through natural language. The description explicitly mentions single MA, dual MA, arbitrary periods, cross-timeframe combinations, and Turtle trading-related backtests.

Do I need to write backtest code myself?

Based on the description, it emphasizes letting an AI agent backtest A-shares with natural language, so the core workflow does not require writing complex backtest logic first. For exact interfaces and usage details, see the source repository.

What strategy types are supported?

It is stated to support single moving average, dual moving average, arbitrary periods, cross-timeframe combinations, and Turtle trading. The provided materials do not confirm additional strategy types, so see the source repository for more.