This release adds 4 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+5 more
Summary
AI summaryAdds four new MCP tools: store_trade_memory, recall_similar_trades, get_strategy_performance, and get_trade_reflection.
Full changelog
tradememory-protocol v0.2.0
The first MCP memory system built for AI trading agents. Not a dashboard. Not a journal. A protocol layer that gives your trading AI the ability to remember and learn.
New: MCP Server (FastMCP)
4 tools available via MCP protocol:
| Tool | Description |
|------|-------------|
| store_trade_memory | Store a trade decision with full context |
| recall_similar_trades | Find past trades with similar market context |
| get_strategy_performance | Aggregate stats per strategy |
| get_trade_reflection | Deep-dive into a trade's reasoning and lessons |
Install
uvx tradememory-protocol
Use with Claude Desktop / Claude Code
{
"mcpServers": {
"tradememory": {
"command": "uvx",
"args": ["tradememory-protocol"]
}
}
}
Also included
- FastAPI REST API preserved (
tradememory-apicommand) for MT5 sync pipeline - 123 tests passing (12 new MCP tool tests)
- SQLite storage (zero config)
Built by Mnemox AI
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About mnemox-ai/tradememory-protocol
Structured 3-layer memory system (trades → patterns → strategy) for AI trading agents. Supports MT5, Binance, and Alpaca.
Related context
Beta — feedback welcome: [email protected]