Build, backtest and research trading strategies on real tick-by-tick market data from your AI
About
StrategyTune is a backtesting platform for trading strategies, and this MCP server gives your AI hands-on access to it.
Your AI can write and save the pieces you build with: chart indicators, reusable market conditions (StrategyTune calls them signals and filters), and full trading strategies. It then runs them tick-by-tick against real historical market data in StrategyTune's sandboxed cloud. A simple strategy backtests a year of history in seconds, so you can iterate fast.
It is not limited to automated strategy backtesting. Your AI can run custom research code in the same sandbox: count how often a condition occurred, measure values at specific moments, gather your own statistics and write logs during the run. You say what you want to check, the AI writes the code, runs it, reads the output back, and tells you what it found.
When a run finishes you get the full report: performance statistics and the individual trades behind them. The AI can also work with a StrategyTune chart you already have open in your browser: read the bars and each indicator's computed values, add and configure indicators, mark conditions on the timeline so you can see exactly when they held, jump to a date, and switch instrument or timeframe.
37 tools, grouped as: platform knowledge (get_knowledge serves built-in documentation topics so the AI learns the platform by itself), scripts (list, get, save, duplicate, delete, restore), cloud runs (run_backtest, run_code, status, result, trades, cancel), sessions (manual and automated), and open-tab chart control (indicators, timeline tracks, instrument, timeframe, jump to date, attach to a live run). Authentication is OAuth 2.1 with PKCE and Dynamic Client Registration; a free StrategyTune account is enough to connect.
Everything runs on historical data. The server does not connect to a broker, place live orders, or give investment advice.
Security Report
Remote MCP endpoint verified (130ms response). 2 trust signals: valid MCP protocol, requires auth. No security issues detected.
Endpoint verified · Requires authentication · 2 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Remote servers are capped at 8.0 because source code is not available for review. The score reflects endpoint verification only.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
How to Connect
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"strategytune": {
"url": "https://strategytune.com/mcp"
}
}
}Getting Started
Once installed, try these example prompts and explore these capabilities:
- 1Explain how manual and automated backtesting fit together in StrategyTune.
- 2Write a strategy that buys when the 20 EMA crosses above the 50 EMA and sells on the opposite cross, then backtest it on EURUSD 15m for the last year.
- 3How often did EURUSD move more than 50 pips within the first hour of the London session in 2025? Run the code and tell me.
- 4Add an RSI indicator to my open chart and show me where it was below 30 on the timeline.
- 5Show me the trades from my last backtest and summarize what went wrong.
Reviews
No written reviews yet. Be the first!
More Finance MCP Servers
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
FinAgent
Freeby mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.
by Lharries · Communication
Read, search, and send WhatsApp messages through your AI assistant
Memory
Freeby Modelcontextprotocol · Productivity
Knowledge graph-based persistent memory across sessions