io.github.mnemox-ai/tradememory-protocol
PYPI · TRADEMEMORY-PROTOCOL · SCANNED SEP 20
Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 30 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 11 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3069 tokens (~153/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the io.github.mnemox-ai/tradememory-protocol MCP server?
io.github.mnemox-ai/tradememory-protocol runs locally as a PyPI package, launched with uvx tradememory-protocol. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · tradememory-protocol
claude mcp add mnemox-ai-tradememory-protocol -- uvx tradememory-protocol
{
"mcpServers": {
"mnemox-ai-tradememory-protocol": {
"command": "uvx",
"args": [
"tradememory-protocol"
]
}
}
} {
"servers": {
"mnemox-ai-tradememory-protocol": {
"command": "uvx",
"args": [
"tradememory-protocol"
]
}
}
} codex mcp add mnemox-ai-tradememory-protocol -- uvx tradememory-protocol
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mnemox-ai-tradememory-protocol": {
"type": "local",
"command": [
"uvx",
"tradememory-protocol"
],
"enabled": true
}
}
} openclaw mcp add mnemox-ai-tradememory-protocol --command uvx --arg tradememory-protocol
mcp_servers:
mnemox-ai-tradememory-protocol:
command: "uvx"
args: ["tradememory-protocol"] {
"McpServers": {
"mnemox-ai-tradememory-protocol": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"tradememory-protocol"
]
}
}
} assistant mcp add mnemox-ai-tradememory-protocol -t stdio -c uvx -a tradememory-protocol
{
"mcpServers": {
"mnemox-ai-tradememory-protocol": {
"command": "uvx",
"args": [
"tradememory-protocol"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 +1
- Stability: 0.97 → pass security
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 14 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- 12 Sept 26 −3
- Stability: pass → 0.80 functional
- 11 Sept 26 +1
- Stability: 0.97 → pass security
- 9 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/tradememory-protocol@0.5.5
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 30 packages
| Packages resolved | 30 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_active_plans Check Active Plans ~81
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.
| Name | Type | Req | Description |
|---|---|---|---|
| context_atr_d1 | – | – | Current ATR(14) on D1 in dollars |
| context_regime | – | – | Current market regime (trending_up/trending_down/ranging/volatile) |
Structured output declared, but exposes no named fields.
No examples provided.
check_trade_legitimacy Check Trade Legitimacy ~142
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.
| Name | Type | Req | Description |
|---|---|---|---|
| current_atr_d1 | – | – | Current ATR(14) on D1 in dollars (informational). |
| current_regime | – | – | Current market regime (trending_up/trending_down/ranging/volatile). |
| strategy_name | string | yes | Strategy to evaluate (e.g. "VolBreakout"). |
| symbol | string | – | Trading instrument (default "XAUUSD"). |
Structured output declared, but exposes no named fields.
No examples provided.
compute_dqs Compute Dqs ~183
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.
| Name | Type | Req | Description |
|---|---|---|---|
| context_atr_d1 | – | – | ATR(14) on D1 in dollars. |
| context_regime | – | – | Market regime (trending_up/trending_down/ranging/volatile). |
| direction | string | yes | Intended direction ("long" or "short"). |
| market_context | string | – | Description of current market conditions. |
| proposed_lot_size | number | – | Planned position size in lots (default 0.1). |
| strategy_name | string | yes | Strategy being considered (e.g. "VolBreakout"). |
| symbol | string | yes | Trading instrument (e.g. "XAUUSD"). |
Structured output declared, but exposes no named fields.
No examples provided.
create_trading_plan Create Trading Plan ~173
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.
| Name | Type | Req | Description |
|---|---|---|---|
| expiry_days | integer | – | Days until plan expires (default 30) |
| planned_action | string | yes | JSON string describing what to do (e.g. '{"type": "skip_trade"}') |
| priority | number | – | Priority 0-1, higher = checked first (default 0.5) |
| reasoning | string | yes | Why this plan was created |
| trigger_condition | string | yes | JSON string describing when to trigger (e.g. '{"regime": "ranging"}') |
| trigger_type | string | yes | Type of trigger (e.g. "market_condition", "drawdown", "time_based") |
Structured output declared, but exposes no named fields.
No examples provided.
evolution_discover_patterns Evolution Discover Patterns ~152
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.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Number of patterns to generate (default 5) |
| days | integer | – | Days of history to analyze (default 90) |
| symbol | string | yes | Trading pair (e.g. "BTCUSDT") |
| temperature | number | – | LLM creativity 0-1 (default 0.7, higher = more diverse) |
| timeframe | string | – | Bar timeframe — "5m", "15m", "1h", "4h", "1d" |
Structured output declared, but exposes no named fields.
No examples provided.
evolution_evolve_strategy Evolution Evolve Strategy ~160
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.
| Name | Type | Req | Description |
|---|---|---|---|
| days | integer | – | Days of history to use (default 90) |
| generations | integer | – | Number of evolution generations (default 3) |
| population_size | integer | – | Hypotheses per generation (default 10) |
| symbol | string | yes | Trading pair (e.g. "BTCUSDT") |
| timeframe | string | – | Bar timeframe — "5m", "15m", "1h", "4h", "1d" |
Structured output declared, but exposes no named fields.
No examples provided.
evolution_fetch_market_data Evolution Fetch Market Data ~115
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.
| Name | Type | Req | Description |
|---|---|---|---|
| days | integer | – | Number of days of history to fetch (default 90) |
| symbol | string | yes | Trading pair (e.g. "BTCUSDT", "ETHUSDT") |
| timeframe | string | – | Bar timeframe — "5m", "15m", "1h", "4h", "1d" |
Structured output declared, but exposes no named fields.
No examples provided.
evolution_get_log Evolution Get Log ~59
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).
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
evolution_run_backtest Evolution Run Backtest ~145
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.
| Name | Type | Req | Description |
|---|---|---|---|
| days | integer | – | Days of history to backtest against (default 90) |
| pattern_dict | object | yes | CandidatePattern as dict (from discover_patterns output) |
| symbol | string | – | Trading pair (e.g. "BTCUSDT") |
| timeframe | string | – | Bar timeframe — "5m", "15m", "1h", "4h", "1d" |
Structured output declared, but exposes no named fields.
No examples provided.
export_audit_trail Export Audit Trail ~162
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.
| Name | Type | Req | Description |
|---|---|---|---|
| end | – | – | End date (ISO format, exclusive). E.g., "2026-04-01". |
| limit | integer | – | Maximum records to return (default 50). |
| start | – | – | Start date (ISO format, inclusive). E.g., "2026-03-01". |
| strategy | – | – | Filter by strategy name (e.g., "VolBreakout"). |
| trade_id | – | – | Get a single TDR by trade ID (e.g., "MT5-7047640363"). If provided, other filters are ignored. |
Structured output declared, but exposes no named fields.
No examples provided.
get_agent_state Get Agent State ~56
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.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
get_behavioral_analysis Get Behavioral Analysis ~66
Get behavioral analysis from procedural memory. Returns aggregate trading behavior stats: hold times, disposition ratio, lot sizing variance, and Kelly criterion comparison.
| Name | Type | Req | Description |
|---|---|---|---|
| strategy_name | – | – | Filter by strategy name. Returns all if omitted. |
| symbol | – | – | Filter by symbol. Returns all if omitted. |
Structured output declared, but exposes no named fields.
No examples provided.
get_daily_root Get Daily Root ~211
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.
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | yes | Date in YYYY-MM-DD format (or full ISO datetime). |
| include_token | boolean | – | If True, include a base64-encoded `tsa_token` in the response (default False — the token can be large). |
| rebuild | boolean | – | 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 setting — ON unless set t… |
Structured output declared, but exposes no named fields.
No examples provided.
get_strategy_performance Get Strategy Performance ~60
Get aggregate performance stats per strategy. Use this to evaluate which strategies are working and which need adjustment.
| Name | Type | Req | Description |
|---|---|---|---|
| strategy_name | – | – | Filter by strategy name. Returns all strategies if omitted. |
| symbol | – | – | Filter by symbol. Returns all symbols if omitted. |
Structured output declared, but exposes no named fields.
No examples provided.
get_trade_reflection Get Trade Reflection ~50
Get the full context and reflection for a specific trade. Use this to deep-dive into a particular trade's reasoning and lessons.
| Name | Type | Req | Description |
|---|---|---|---|
| trade_id | string | yes | The trade ID to look up |
Structured output declared, but exposes no named fields.
No examples provided.
recall_memories Recall Memories ~259
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.
| Name | Type | Req | Description |
|---|---|---|---|
| context_atr_d1 | – | – | Current ATR(14) on D1 in dollars |
| context_regime | – | – | Current market regime (trending_up/trending_down/ranging/volatile) |
| hybrid_alpha | number | – | Vector vs OWM blend weight [0..1] when hybrid is active. 0.0 = pure OWM, 1.0 = pure vector. Default 0.3 (OWM-dominant). |
| limit | integer | – | Max results (default 10) |
| market_context | string | yes | Current market conditions to match against |
| memory_types | – | – | Types to query (default: ["episodic", "semantic"]) |
| strategy_name | – | – | Optional strategy filter |
| symbol | string | yes | Trading instrument (e.g. "XAUUSD") |
| use_hybrid | boolean | – | If True (default), enable vector + OWM hybrid scoring when an embedding backend is available. Falls back to pure OWM silently when sentence-transformers is not installed. |
Structured output declared, but exposes no named fields.
No examples provided.
remember_trade Remember Trade ~333
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.
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | number | – | Agent confidence level 0-1 (default 0.5) |
| context_atr_d1 | – | – | ATR(14) on D1 in dollars |
| context_regime | – | – | Market regime (trending_up/trending_down/ranging/volatile) |
| direction | string | yes | "long" or "short" |
| entry_price | number | yes | Entry price of the trade |
| entry_timestamp | – | – | ISO format entry time. Used to compute hold duration. |
| exit_price | number | yes | Exit price of the trade |
| exit_timestamp | – | – | ISO format exit time. Used to compute hold duration. |
| market_context | string | yes | Description of market conditions |
| max_adverse_excursion | – | – | Maximum adverse excursion during the trade |
| pnl | number | yes | Profit/loss in account currency |
| pnl_r | – | – | P&L as R-multiple (risk units). Improves OWM scoring quality. |
| reflection | – | – | Lessons learned from this trade |
| strategy_name | string | yes | Strategy used (e.g. "VolBreakout") |
| symbol | string | yes | Trading instrument (e.g. "XAUUSD") |
| timestamp | – | – | ISO format timestamp. Defaults to now (UTC). |
| trade_id | – | – | Optional custom ID. Auto-generated if omitted. |
Structured output declared, but exposes no named fields.
No examples provided.
validate_strategy Validate Strategy ~261
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
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Absolute path to the CSV file on your local machine. |
| format | string | – | CSV format — "quantconnect" for trade logs (columns: Entry Time, Exit Time, Direction, Entry Price, Exit Price, Quantity, P&L, Fees, IsWin) or "returns" for daily returns (columns: date,retur… |
| num_strategies | integer | – | How many strategies you tested before picking this one. Higher M = stricter DSR threshold (corrects for selection bias). |
| strategy_name | string | – | Name of the strategy (for the report). |
Structured output declared, but exposes no named fields.
No examples provided.
verify_audit_chain Verify Audit Chain ~157
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.
| Name | Type | Req | Description |
|---|---|---|---|
| from_seq | – | – | Starting sequence_num (inclusive). None = from beginning. |
| to_seq | – | – | Ending sequence_num (inclusive). None = through latest. |
Structured output declared, but exposes no named fields.
No examples provided.
verify_audit_hash Verify Audit Hash ~71
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.
| Name | Type | Req | Description |
|---|---|---|---|
| trade_id | string | yes | Trade ID to verify (e.g., "MT5-7047640363"). |
Structured output declared, but exposes no named fields.
No examples provided.
What is the io.github.mnemox-ai/tradememory-protocol MCP server?
io.github.mnemox-ai/tradememory-protocol is an MCP server listed in the public MCP registry as io.github.mnemox-ai/tradememory-protocol. Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents. This page covers its PyPI package (tradememory-protocol).
Is the io.github.mnemox-ai/tradememory-protocol MCP server safe to use?
io.github.mnemox-ai/tradememory-protocol scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.mnemox-ai/tradememory-protocol MCP server expose?
io.github.mnemox-ai/tradememory-protocol exposes 20 tools: get_strategy_performance, get_trade_reflection, remember_trade, recall_memories, get_behavioral_analysis, and 15 more. Their descriptions and schemas cost roughly 2,896 tokens of context every time the server is loaded.
Is the io.github.mnemox-ai/tradememory-protocol MCP server still maintained?
io.github.mnemox-ai/tradememory-protocol is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.mnemox-ai/tradememory-protocol MCP server under?
io.github.mnemox-ai/tradememory-protocol declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.