Tradememory Protocol

Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.

Connector by mnemox-ai · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1,431

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mnemox-ai-tradememory-protocol

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.

Use cases: agent-memory, finance-accounting

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 11 read · 11 write · 0 delete
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Tools by what they do 22

Read from the source code; the running server may list different tools.

Read 11 · Look things up without changing anything.

brake_status
evaluate_order
evolution_get_log
export_audit_trail
get_agent_state
get_behavioral_analysis
get_strategy_performance
get_trade_reflection
validate_strategy
verify_audit_chain
verify_audit_hash

Write 11 · Create, change, send or run things.

check_active_plans
check_trade_legitimacy
compute_dqs
create_trading_plan
evolution_discover_patterns
evolution_evolve_strategy
evolution_fetch_market_data
evolution_run_backtest
get_daily_root
recall_memories
remember_trade

Files it touches

Any path the agent passes to its tools

Tools (22)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

brake_status
What the brake in front of this broker will and will not let through.
check_active_plans
Check active trading plans against current market context. Queries all active prospective plans, expires any past their expiry date, and matches remaining plans against the provided context. Args: context_regime: Current market regime (trending_up/trending_down/ranging/volatile) context_atr_d1: Current ATR(14) on D1 in dollars
check_trade_legitimacy
Check if the agent has sufficient data and confidence to trade. Call this before making any trade decision. Evaluates sample size, memory quality, regime experience, streak state, and drawdown to determine whether the agent has earned the right to trade at full size. Args: strategy_name: Strategy to evaluate (e.g. "VolBreakout"). symbol: Trading instrument (default "XAUUSD"). current_regime: Current market regime (trending_up/trending_down/ranging/volatile). current_atr_d1: Current ATR(14) on D1 in dollars (informational). Returns: Legitimacy assessment with score, tier …
compute_dqs
Compute Decision Quality Score before executing a trade. Evaluates the quality of the decision *process* (not outcome) across 5 factors: regime match, position sizing vs Kelly, process adherence (OWM similarity), risk state, and historical pattern. Args: symbol: Trading instrument (e.g. "XAUUSD"). strategy_name: Strategy being considered (e.g. "VolBreakout"). direction: Intended direction ("long" or "short"). proposed_lot_size: Planned position size in lots (default 0.1). market_context: Description of current market conditions. context_regime: Market regime (trending…
create_trading_plan
Create a prospective trading plan that activates when conditions are met. Stores a rule-based plan in prospective memory. The plan stays active until triggered, expired, or manually cancelled. Args: trigger_type: Type of trigger (e.g. "market_condition", "drawdown", "time_based") trigger_condition: JSON string describing when to trigger (e.g. '{"regime": "ranging"}') planned_action: JSON string describing what to do (e.g. '{"type": "skip_trade"}') reasoning: Why this plan was created expiry_days: Days until plan expires (default 30) priority: Priority 0-1, higher = ch…
evaluate_order
Ask the brake what it would do with this order, without placing it. Same live reads, same policy, same decision shape as a real order (ALLOW / DENY / ESCALATE with the rule codes). Accepts the fields an advisory layer such as Vibe-Trading's PreTradeAdvisoryInterface sends (notional_usd and friends); the account figures are read live from the broker, not trusted from the caller.
evolution_discover_patterns
Discover trading patterns from market data using LLM analysis. Uses Claude to analyze OHLCV data and generate candidate trading patterns with entry/exit conditions. Each pattern can be backtested afterward. Args: symbol: Trading pair (e.g. "BTCUSDT") timeframe: Bar timeframe — "5m", "15m", "1h", "4h", "1d" count: Number of patterns to generate (default 5) temperature: LLM creativity 0-1 (default 0.7, higher = more diverse) days: Days of history to analyze (default 90)
evolution_evolve_strategy
Run full evolution loop — generate, backtest, select, eliminate. Multi-generation strategy evolution: generates candidate patterns via LLM, backtests on in-sample data, validates survivors on out-of-sample data, eliminates weak hypotheses. Returns graduated strategies and graveyard. Args: symbol: Trading pair (e.g. "BTCUSDT") timeframe: Bar timeframe — "5m", "15m", "1h", "4h", "1d" generations: Number of evolution generations (default 3) population_size: Hypotheses per generation (default 10) days: Days of history to use (default 90)
evolution_fetch_market_data
Fetch OHLCV market data from Binance for evolution analysis. Downloads historical price bars for backtesting and pattern discovery. Use this before discover_patterns or run_backtest to get data. Args: symbol: Trading pair (e.g. "BTCUSDT", "ETHUSDT") timeframe: Bar timeframe — "5m", "15m", "1h", "4h", "1d" days: Number of days of history to fetch (default 90)
evolution_get_logread-only
Get the log of past evolution runs from this session. Returns a list of all evolution runs with their results, including graduated strategies, graveyard, token usage, and backtest counts. Data is in-memory (resets on server restart).
evolution_run_backtest
Backtest a candidate pattern against historical OHLCV data. Takes a pattern dict (from discover_patterns) and runs a vectorized backtest. Returns fitness metrics: Sharpe ratio, win rate, trade count, max drawdown, total PnL. Args: pattern_dict: CandidatePattern as dict (from discover_patterns output) symbol: Trading pair (e.g. "BTCUSDT") timeframe: Bar timeframe — "5m", "15m", "1h", "4h", "1d" days: Days of history to backtest against (default 90)
export_audit_trailread-only
Export Trading Decision Records for audit and compliance review. Provides a complete, tamper-evident record of trading decisions including the memory context (similar trades, beliefs) that informed each decision. Args: trade_id: Get a single TDR by trade ID (e.g., "MT5-7047640363"). If provided, other filters are ignored. strategy: Filter by strategy name (e.g., "VolBreakout"). start: Start date (ISO format, inclusive). E.g., "2026-03-01". end: End date (ISO format, exclusive). E.g., "2026-04-01". limit: Maximum records to return (default 50). Returns: dict w…
get_agent_stateread-only
Get the current agent affective state (confidence, risk, drawdown). Returns confidence level, risk appetite, drawdown percentage, win/loss streaks, equity tracking, and a recommended action based on current drawdown severity.
get_behavioral_analysisread-only
Get behavioral analysis from procedural memory. Returns aggregate trading behavior stats: hold times, disposition ratio, lot sizing variance, and Kelly criterion comparison. Args: strategy_name: Filter by strategy name. Returns all if omitted. symbol: Filter by symbol. Returns all if omitted.
get_daily_root
Get (or rebuild) the daily Merkle root for a UTC date. The Merkle root summarises every audit_chain entry whose `chained_at` falls inside the UTC day. Verifying this single 32-byte root proves the integrity of every TDR for that day without re-walking each one. Args: date: Date in YYYY-MM-DD format (or full ISO datetime). rebuild: If True, recompute and overwrite the stored root. request_tsa: Whether to submit the rebuilt root to the configured RFC 3161 TSA (default freetsa.org) and store the returned TimeStampToken. None (default) follows the TRADEMEMORY_TSA env …

Show 7 more tools

get_strategy_performanceread-only
Get aggregate performance stats per strategy. Use this to evaluate which strategies are working and which need adjustment. Args: strategy_name: Filter by strategy name. Returns all strategies if omitted. symbol: Filter by symbol. Returns all symbols if omitted.
get_trade_reflectionread-only
Get the full context and reflection for a specific trade. Use this to deep-dive into a particular trade's reasoning and lessons. Args: trade_id: The trade ID to look up
recall_memories
Recall memories using OWM outcome-weighted scoring. Queries episodic and semantic memories, scores them by outcome quality, context similarity, recency, confidence, and affective modulation. Returns ranked memories with score breakdown. Use order="losses_first" right before placing a trade: losing trades taken in similar conditions rank first, and the current mood (a losing streak) no longer pushes them down. Args: symbol: Trading instrument (e.g. "XAUUSD") market_context: Current market conditions to match against context_regime: Current market regime (trending_up/trending_down…
remember_trade
Store a trade into OWM multi-layer memory with automatic updates. Writes to episodic memory and automatically updates semantic (Bayesian), procedural (running averages + hold time + Kelly), and affective (EWMA confidence/streaks). Also writes to trade_records for backward compatibility. Args: symbol: Trading instrument (e.g. "XAUUSD") direction: "long" or "short" entry_price: Entry price of the trade exit_price: Exit price of the trade pnl: Profit/loss in account currency strategy_name: Strategy used (e.g. "VolBreakout") market_context: Description of market condi…
validate_strategyread-only
Validate a trading strategy using statistical tests (DSR + Walk-Forward + Regime + CPCV). For educational and research purposes only. Not financial advice. Upload a trade log CSV (QuantConnect format) or daily returns CSV. The tool runs four statistical tests: 1. Deflated Sharpe Ratio (DSR) — detects overfitting from multiple testing 2. Walk-Forward Validation — checks out-of-sample consistency 3. Regime Analysis — performance across bull/bear/crisis markets 4. CPCV — cross-validated Sharpe stability across time periods Args: file_path: Absolute path to the CSV file on your local machin…
verify_audit_chainread-only
Verify the integrity of the audit chain. Walks the chain from `from_seq` (default: 1, the genesis record) to `to_seq` (default: latest), checking that every record's `prev_hash` matches the previous record's `data_hash`, and that each `data_hash` equals SHA256(prev_hash || content_hash). Returns a dict with `verified`, `checked_count`, `first_break_at`, `reason`. A `first_break_at` of None with `verified=True` means the chain is intact across the verified range. Args: from_seq: Starting sequence_num (inclusive). None = from beginning. to_seq: Ending sequence_num (inclusive). None = …
verify_audit_hashread-only
Verify the integrity of a Trading Decision Record. Recomputes the SHA256 data_hash from stored inputs and compares with the hash computed at decision time. A mismatch indicates tampering. Args: trade_id: Trade ID to verify (e.g., "MT5-7047640363"). Returns: dict with 'verified' (bool), 'stored_hash', 'recomputed_hash'.

Compare and alternatives

Alternatives to Tradememory Protocol →

Featured in

Best MCP servers for trading

Signals

Stars: 1,431
Forks: 170
Open issues: 5
Contributors: 3
Weekly downloads: 87
Last commit: Oct 9, 2026 (19 days ago)
Last release: Oct 2, 2026 (26 days ago)
Last package publish: Oct 2, 2026 (26 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.mnemox-ai/tradememory-protocol
Version: 0.5.6
Auth: No auth
Packages: pypi tradememory-protocol
License: MIT
Repository: github.com/mnemox-ai/tradememory-protocol
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql