TradeMemoryBLOCK
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/tradememory-protocol/) [](https://github.com/mnemox-ai/tradememory-protocol/actions/workflows/ci.yml) [](https://smithery.ai/server/mnemox-ai/tradememory-protocol) [](https://smithery.ai/server/mnemox-ai/tradememory-protocol) [](https://opensource.org/licenses/MIT)
Getting Started | Use Cases | API Reference | OWM Framework | Limitations | 中文版
Project status (August 2026): Feature-complete, in maintenance mode — bug and security reports are still reviewed; no new features or hosted service are planned. For paid work, see Trading Record Analysis.
Your trading AI has amnesia. And regulators are starting to notice.
It makes the same mistakes every session. It can't explain why it traded. It forgets everything when the context window ends. Meanwhile, MiFID II is raising the bar for algorithmic decision documentation (Article 17). The EU AI Act demands systematic logging of AI actions (Article 14). Your competitors' agents are learning from every trade.
The AI trading stack is missing a layer. Ev
17b3c9fa69e2OBSERVED · 2026-09-24Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add tradememory-protocol -- None tradememory-protocol==0.5.5
Exposed tools (20)
17 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check_active_plans | read | Check active trading plans against current market context. |
check_trade_legitimacy | read | Check if the agent has sufficient data and confidence to trade. |
compute_dqs | read | Compute Decision Quality Score before executing a trade. |
create_trading_plan | write | Create a prospective trading plan that activates when conditions are met. |
evolution_discover_patterns | read | Discover trading patterns from market data using LLM analysis. |
evolution_evolve_strategy | write | Run full evolution loop — generate, backtest, select, eliminate. |
evolution_fetch_market_data | read | Fetch OHLCV market data from Binance for evolution analysis. |
evolution_get_log | read | Get the log of past evolution runs from this session. |
evolution_run_backtest | write | Backtest a candidate pattern against historical OHLCV data. |
export_audit_trail | read | Export Trading Decision Records for audit and compliance review. |
get_agent_state | read | Get the current agent affective state (confidence, risk, drawdown). |
get_behavioral_analysis | read | Get behavioral analysis from procedural memory. |
get_daily_root | read | Get (or rebuild) the daily Merkle root for a UTC date. |
get_strategy_performance | read | Get aggregate performance stats per strategy. |
get_trade_reflection | read | Get the full context and reflection for a specific trade. |
recall_memories | read | Recall memories using OWM outcome-weighted scoring. |
remember_trade | read | Store a trade into OWM multi-layer memory with automatic updates. |
validate_strategy | read | Validate a trading strategy using statistical tests (DSR + Walk-Forward + Regime + CPCV). |
verify_audit_chain | read | Verify the integrity of the audit chain. |
verify_audit_hash | read | Verify the integrity of a Trading Decision Record. |
Trust audit
BLOCKgrade F · trust 48/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (7 observation(s))
- Network
- declared (7 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
sqlalchemy.url = postgresql://tradememory:tradememory@localhost:5432/tradememory
python scripts/research/migrate_sqlite_to_pg.py --sqlite data/tradememory.db --pg postgresql://tradememory:tradememory@localhost:5432/tradememory
default="postgresql://tradememory:tradememory@localhost:5432/tradememory",
print(f" {'Sold token Jaccard distance':<35} {td['sold_jaccard_distance']:.4f}")print(f" {'Bought token Jaccard distance':<35} {td['bought_jaccard_distance']:.4f}")print(f" {'Sold token overlap':<35} {', '.join(td['sold_overlap'])}")print(f" {'Bought token overlap':<35} {', '.join(td['bought_overlap'])}")print(f"Using Etherscan API {'with' if args.api_key else 'without'} API key")"http://127.0.0.1",
"http://127.0.0.1:5173",
blueprint.docx
.pre-commit-config.yaml
.env.production
rc1, rc2, rc3, rc4 = st.columns(4)
rc4.metric("Kelly", f"{risk_data.get('kelly_fraction', 0.0):.2%}")import type { BeliefState } from '../../api/types';import type { ReflectionSummary } from '../../api/types';import type { AdjustmentEvent } from '../../api/types';import type { CalibrationPoint } from '../../api/types';import type { DreamSession } from '../../api/types';INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
return hashlib.sha256(bytes.fromhex(a) + bytes.fromhex(b)).hexdigest()
_SHA256_OID_DER = bytes.fromhex("300d06096086480165030402010500")digest = bytes.fromhex(sha256_hex.lower())
expected = hashlib.sha256(bytes.fromhex(a) + bytes.fromhex(b)).hexdigest()
Gates applied: no_behavioural_pass.
17b3c9fa69e2full audit observations/trust-audit/mcp-server/mnemox-ai__tradememory.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-24 | 17b3c9fa69e2 | BLOCK | F | 48 | first audit |
Questions
What is the TradeMemory MCP server?
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.
What tools does TradeMemory expose?
20 in total: 17 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is TradeMemory safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (48/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does TradeMemory need?
It reads ANTHROPIC_API_KEY, BINANCE_API_KEY, BINANCE_API_SECRET, MT5_PASSWORD, SUPABASE_SERVICE_ROLE_KEY and TM_API_KEYS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does TradeMemory run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as dashboard at 0.0.0.
How current is this page?
The grade is for one exact copy of the source (17b3c9fa69e2), read on 2026-09-24. The repository is watched and re-audited when it changes.