convez.ai
MCP ServerFinanceiroAvançado
AlgoChains

AlgoChains MCP Server

AlgoChains/algochains-mcp-server

503 ferramentas de trading e análise de mercado em tempo real para Claude, Cursor e ChatGPT

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que conecta assistentes de IA a infraestrutura de trading em tempo real, expondo 503 ferramentas especializadas para análise de mercado, execução de ordens e validação de estratégias de algo-trading. Integra múltiplos brokers (Tradovate, InteractiveBrokers), dados de mercado (Databento, Polygon, FRED) e fornece acesso a backtesting, detecção de regimes de mercado e health checks de bots ao vivo.

Instalação

$npx convez-ai AlgoChains/algochains-mcp-server

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
1
Acompanhando
1
Saúde
37%
Último commit
há 2 meses
Versão
v22.7.3
Issues abertas
3
Contribuidores
6

Casos de uso

  • Consultar posições e P&L de contas de trading em tempo real
  • Executar backtests e análises walk-forward de estratégias algorítmicas
  • Detectar regimes de mercado e gerar sinais técnicos automaticamente
  • Monitorar saúde de bots de trading live e ajustar parâmetros
  • Integrar múltiplas fontes de dados de mercado (futuros, criptomoedas, fundamentais)

Veredito

Ferramenta especializada e robusta para traders que querem delegar tarefas operacionais e analíticas a assistentes de IA. Excelente integração com Claude via MCP, modo inteligente reduz consumo de tokens significativamente. Requer conhecimento técnico e infraestrutura de trading estabelecida para aproveitar todo potencial.

README

A tradução para o português deste README ainda está na fila.

AlgoChains MCP Server

MCP Tools Version Python License Docs Data


The only MCP server with live futures bots, real fill data, real-time ML inference, and 503 tools across 20 domains — all backed by real APIs, zero synthetic data.

Connect your AI assistant (Claude, Cursor, ChatGPT) to your trading infrastructure in 3 commands. Ask Claude "What's my MNQ P&L today?" — it calls Tradovate, gets the real answer, and tells you.

You ask Claude:                    Claude calls:                    Server calls:
"What's my NQ position?"   →  get_positions()           →  Tradovate API → real data
"Run a backtest on MNQ"    →  run_backtest()             →  Databento tick archive
"Is the market trending?"  →  detect_market_regime()    →  Polygon + FRED → analysis
"Check my MNQ bot health"  →  get_bot_health(bot="MNQ") →  launchd + logs → live state

Quick Install

# 1. Install
pip install algochains-mcp-server

# 2. Connect to your IDE (no credentials needed to start)
python scripts/quickstart.py --generate-config cursor

# 3. Verify
python scripts/quickstart.py --mode demo

That's it. Your AI now has 168 tools (smart mode) available immediately. Add broker credentials for live trading access. See Option C for live credentials.


Smart Mode vs Full Mode

AlgoChains exposes tools in two tiers, controlled by ALGOCHAINS_TOOL_MODE:

ModeTools ExposedToken CostWhen to Use
Smart (default)168 curated~4K tokensCursor, Windsurf (80-tool limit), everyday use
Full (ALGOCHAINS_TOOL_MODE=full)503 tools~40K tokensClaude Code, full agentic sessions

Smart mode includes: all live bot tools, market data, signals, research/backtest, Onyx RAG, prop fund pipeline, position sizing, broker management, and order execution. Everything you need 95% of the time.

Full mode unlocks the remaining 330 tools: advanced DeFi, Kalshi order placement, multi-tenant SaaS, QuantConnect integration, alt-data pipelines, and more.

discover_tools — Find Any Tool Without Full Mode

Even in smart mode, you can find and use any of the 503 tools:

# Ask the server to find the right tool for your task
discover_tools("walk-forward validation with leakage check")
# → Returns: walk_forward_test, run_mcpt_validation, analyze_overfitting

# Then call it
execute_dynamic_tool("walk_forward_test", {"symbol": "MNQ", "lookback_days": 252})

This provides 99.6% token reduction vs exposing all 503 tools (arXiv:2603.20313).


Tool Domains

All 503 tools organized across 21 domains:

#DomainSmartFullKey Tools
1Market Data1422get_quote, get_ohlcv, get_tick_data, get_options_chain, get_footprint_chart, get_dark_pool_volume
2Signals & Analysis1218generate_signal, detect_market_regime, get_ensemble_vote, compute_gex, read_tape, pair_trade_signal
3Research & Backtesting1016run_backtest, walk_forward_test, run_mcpt_validation, validate_strategy_metrics, analyze_overfitting
4Position Sizing68compute_r_multiple_size, compute_volatility_targeted_size, compute_idm, dual_size_conservative
5Options Analytics46compute_option_greeks, find_optimal_strike, get_options_chain, unusual_options_activity
6Prop Fund Pipeline810evaluate_strategy_for_prop_fund, simulate_prop_fund_evaluation, list_prop_funds, check_rithmic_status
7Broker Management615check_all_broker_credentials, connect_broker, get_broker_onboarding_guide, store_api_key
8Subscriber / Copy-Trade99get_my_portfolio, get_signal_stream, get_my_pnl, get_my_fills, get_my_assignments, get_marketplace_listings, place_paper_order, cancel_paper_order, get_my_paper_positions
9Account Protection68check_protection_status, record_stop_event, lock_instrument, check_rate_limit_status
10Order Execution812place_order, place_bracket_order, cancel_order, smart_route_order, execute_twap
11Emergency / Destructive35flatten_all_positions, cancel_all_orders, emergency_stop, trip_circuit_breaker
12Intelligence (Onyx + Macro)1014onyx_ask, onyx_search, get_macro_signals, get_us_economic_indicators, get_fed_policy_signals
13Prediction Markets812get_prediction_markets, search_prediction_markets, get_kalshi_settlements, place_kalshi_order
14Skills Bridge55list_skills, get_skill_detail, search_skills, get_skills_for_task, invoke_moltbook_debate
15Agent Memory68get_openclaw_memory, store_trade_lesson, get_current_regime, get_openclaw_state_summary
16Live Bot Intelligence1218get_bot_health, get_live_bot_metrics, get_bot_position_state, get_ai_pipeline_health, restart_trading_bot
17Desktop Tower / Dispatch48dispatch_tower_job, get_tower_job_status, run_tower_backtest, sync_to_tower
18Performance Reporting46generate_bot_tearsheet, get_bot_metrics_full, run_mcpt_pipeline, capture_learning_signal
19Billing & Subscription1212get_started, get_pricing, get_checkout_url, accept_subscriber_terms, get_my_usage, create_referral_code, get_referral_earnings, create_creator_onboarding_link, get_my_creator_earnings, run_creator_payouts, get_my_realized_pnl, get_system_status
20Platform / SaaS820join_waitlist, create_support_ticket, track_platform_event, get_analytics_summary
21AlphaLoop / Evolution1222run_alphaloop_cycle, get_alphaloop_results, get_algochains_telos, send_ntfy_notification

Live Bot Showcase

AlgoChains runs 4 live futures bots on Tradovate. Their state, fills, ML pipeline health, and brackets stream through this MCP server in real time.

BotSymbolStrategyLive SinceKey MCP Tool
MNQ_Upgraded_ScalperMNQ7-AI ensemble, 5-min barsDec 2024get_bot_health(bot="MNQ")
CL_Swing_ScalperCLFinBERT sentiment + momentumJan 2025get_bot_health(bot="CL")
MES_EMA_SwingMESEMA pullback + regime detectionFeb 2025get_bot_health(bot="MES")
NQ_EMA_SwingNQTrend following + foundation modelFeb 2025get_bot_health(bot="NQ")

get_bot_health — Full e2e Signal→Order→Fill Trace

# Returns: process state, position, bracket status, AI pipeline health,
#          ml_env_flags (MASSIVE_NEWS_FEATURES, MASSIVE_PCR_FEATURES, MASSIVE_HALT_GUARD),
#          cc_health (Command Center last-seen, WS status, Databento live feed age),
#          signal_health (params, risk_bootstrap, bot_version, trading_mode),
#          e2e_sentinel (signal→order→bracket→fill lifecycle state)
health = get_bot_health(bot="MNQ")
# All 4 bots in one call
status = get_all_bot_ops_status()
# Returns: process + position + bracket + pipeline snapshot for MNQ/CL/MES/NQ

No credentials needed if you have ALGOCHAINS_BRIDGE_API_KEY. Read-only.


Subscriber Onramp — Try It Free (No Broker Required)

The fastest way to get value from this server is as a subscriber: sign up at algochains.ai, get a free hosted virtual paper account, and start copy-trading the live MNQ bot's signals in seconds. No Tradovate credentials. No Alpaca account. No real money.

How it works

  1. Sign up at algochains.ai — free paper account provisioned automatically
  2. Dashboard shows your sub_live_… subscriber key — copy it
  3. Set ALGOCHAINS_SUBSCRIBER_KEY=sub_live_… in your shell or .env
  4. Claude now has 9 subscriber-scoped tools available:
ToolWhat it does
get_my_portfolioPaper balance + active bot assignments + open signals + 7-day P&L in one call
get_signal_streamUnread copy-trade signals for the bots you follow (MNQ by default)
get_my_pnlToday's P&L and 7-day P&L from your paper fills
get_my_fillsPaginated fill history — symbol, side, qty, fill price, P&L per trade
get_my_assignmentsWhich bots you're subscribed to and their risk caps
get_marketplace_listingsBrowse all approved bots available to subscribe to
place_paper_orderPlace a self-directed paper order (filled at real quotes)
cancel_paper_orderCancel a pending paper order
get_my_paper_positionsOpen and recently filled self-directed paper orders

All 9 tools require only the sub_live_… key — no OWNER_API_TOKEN, no broker credentials.

Subscriber key format

Keys always start with sub_live_ (production) or sub_test_ (sandbox). Set the key as ALGOCHAINS_SUBSCRIBER_KEY in your .env — the server resolves your subscriber_id server-side via Supabase. Your key never touches this repo.

Subscriber quick-start prompts

Portfolio snapshot:
"Run get_my_portfolio. What's my paper balance and how did the MNQ bot do today?"

Signal stream:
"Call get_signal_stream. What signals has the MNQ bot fired in the last hour?"

Fill history:
"Run get_my_fills with limit=20. List the last 20 fills with P&L per trade."

Marketplace browse:
"Run get_marketplace_listings. Which bots are available to subscribe to?"

Paper trade:
"I want to paper-trade 1 MES long at market. Use place_paper_order."

Bot owners: See MARKETPLACE_CREATOR_GUIDE.md and check_propagation_health / test_signal_propagation for the copy-trade pipeline health tools (requires OWNER_API_TOKEN).


Billing & Subscription Funnel (Fully Programmatic)

Every billing action is available as an MCP tool — no browser required after the initial Stripe checkout. An agent or a user can go from zero to copy-trading MNQ signals in one conversation thread.

New-user discovery (no auth, always available)

get_started(goal="subscriber")   # guided next-step map for new users
get_pricing()                    # transparent tiers, referral %, creator share
get_system_status()              # platform health, bot roster, live tool count

Subscribe programmatically

# 1. Get a Stripe-hosted checkout URL (one call — no browser needed after this)
get_checkout_url(email="you@example.com", tier="paper")
# → returns a checkout_url the user visits once to enter payment details
# → sub_live_... key is emailed automatically after payment

# 2. Set the key and accept the CFTC risk disclosure (required before signals)
accept_subscriber_terms(
    subscriber_id="sub_...",
    acknowledgment="I have read and understand the risk disclosure above. I accept full responsibility for my trading decisions."
)

# 3. Subscribe to MNQ copy-trade signals (published for you to review and act on)
join_bot(subscriber_id="sub_...", bot="MNQ", size_multiplier=1.0)

# 4. Check your status and see signals
get_subscriber_status(subscriber_id="sub_...")
get_signal_stream()

Usage metering

get_my_usage(subscriber_id="sub_...")
# → calls_this_month, included_quota, overage_calls, projected_overage_usd

Referral program

create_referral_code(subscriber_id="sub_...")   # → code: "AC-X7K2NP"
get_my_referrals(subscriber_id="sub_...")        # attributed sign-ups + commission
get_referral_earnings(subscriber_id="sub_...")   # total earned, pending payout

Creator revenue (strategy publishers)

create_creator_onboarding_link(creator_id="cr_...", creator_email="you@example.com")
# → Stripe Connect Express onboarding URL (KYC, bank account)

get_my_creator_earnings(creator_id="cr_...")
# → accrued_usd, paid_usd, pending_payout_usd, next_payout_date

# Owner-gated payout run (requires OWNER_API_TOKEN)
run_creator_payouts(dry_run=True)   # preview
run_creator_payouts(dry_run=False, owner_token="tok_...")  # execute transfers

Realized P&L (live-tier subscribers)

get_my_realized_pnl(subscriber_id="sub_...")
# → realized_pnl_usd, trade_count, period, disclaimer (CFTC 4.41(b))
ToolAuthTier gate
get_startedNonePublic
get_pricingNonePublic
get_system_statusNonePublic
get_checkout_urlNonePublic (Stripe handles billing)
accept_subscriber_termssub_live_* keyPaper / Live
get_my_usagesub_live_* keyPaper / Live
create_referral_codesub_live_* keyPaper / Live
get_my_referralssub_live_* keyPaper / Live
get_referral_earningssub_live_* keyPaper / Live
get_my_realized_pnlsub_live_* keyLive
create_creator_onboarding_linkOWNER_API_TOKENOwner
get_my_creator_earningsOWNER_API_TOKENOwner
run_creator_payoutsOWNER_API_TOKENOwner

Signals are published for the subscriber to review and act on — no automated execution. Past performance is not indicative of future results. See accept_subscriber_terms for the full CFTC risk disclosure.


Desktop Tower Dispatch

Heavy ML workloads (hyperparameter sweeps, walk-forward validation, feature importance) run on the desktop tower (configured via ALGOCHAINS_TOWER_HOST) via dispatch_tower_job. The Mac stays clean.

# Dispatch a backtest or ML job to the GPU tower
dispatch_tower_job(
    job_type="backtest",
    params={"strategy": "mnq_scalper", "lookback_days": 252, "wfv_windows": 12}
)

# Check job status
get_tower_job_status(job_id="job_abc123")

From the CLI (ac command):

# Not yet in ac — see CLI_GAP_ANALYSIS.md for ac tower subcommand roadmap
python3 -c "
from algochains_mcp.algoclaw.desktop_tower import dispatch_tower_job
dispatch_tower_job('backtest', {'strategy': 'mnq_scalper', 'lookback_days': 90})
"

What runs where:

ComponentMacBook (execution)Desktop Tower (ML/GPU)
Live bots (MNQ/CL/MES/NQ)✅ launchd—
Token Guardian, Kalshi daemon✅ launchd—
Command Center (:3333)✅ cloudflared tunnel—
Onyx RAG ($ALGOCHAINS_TOWER_HOST:8085)—✅
GPU/ML: FinBERT, Kronos, vLLM—✅
Heavy backtests via dispatch_tower_jobsends job →✅ executes

Security

Authentication Tiers

ScopeHow to AuthenticateWhat's Allowed
Public / demoNo credentialsMarket data, Onyx search, regime detection
TeamALGOCHAINS_BRIDGE_API_KEYBot metrics, positions (read-only)
OwnerOWNER_API_TOKENOrder execution, bot restart, emergency stop

Localhost-Only Services

The following services bind to 127.0.0.1 only and are never exposed publicly:

  • MCP server HTTP bridge (port 8765 / stdio)
  • Command Center dev server (port 3333) — external access via Cloudflare Access tunnel only
  • Onyx RAG stack (tower port 8085) — accessible via Tailscale VPN only

Hard-Coded Safety Limits

These cannot be overridden by any AI agent:

Daily loss limit:      $500   (hard stop, all orders blocked until midnight)
Max drawdown:          15%    (circuit breaker trips at 15% peak-to-trough)
Human confirmation:    required for all orders above $10K notional
AI loop detection:     5 identical calls in 60s → 30-minute order block
VIX gate:             all trades blocked when VIX > 35

Full safety documentation: SAFETY_MODEL.md

OWNER_API_TOKEN — Mutation Gating

Tools in danger tier 2 (order execution) and tier 3 (destructive) require OWNER_API_TOKEN in the request header. The HTTP bridge verifies this before dispatching. AI agents that do not supply it get a policy_denied error — not a soft warning.

# Set in .env (never commit)
OWNER_API_TOKEN=your-owner-token-here

What's New in v22.x

v22.4 (2026-04-06) — UX & Team Onboarding

  • Complete README rewrite (plain English, team access)
  • scripts/quickstart.py — interactive setup wizard with health checks
  • SAFETY_MODEL.md — answers "is this safe?" for every failure mode
  • tool_danger_tiers.py — machine-readable danger classification (0–3) for the documented 503-tool surface
  • HTTP bridge /tools endpoint now returns danger_tier, safe_in_demo_mode, etc.
  • get_bot_health includes e2e_sentinel, desktop inference SLO, and decision latency SLO slices for signal-to-fill traceability

v22.3 (2026-04-06) — Proprietary Data Ingestion

  • ingest_csv_data — validate and ingest real OHLCV CSV files into state/custom_data/
  • ingest_json_signals — import pre-computed signals, ML features, labels, and regime tags
  • connect_onyx_docs — index local research docs into Onyx for onyx_ask() / onyx_search()
  • register_strategy and list_ingested_data — register custom strategy specs and audit imported data

v22.2 (2026-04-21) — Kalshi Pipeline + Model Integrity

  • Kalshi prediction markets — AI ensemble → Kelly sizing → order execution
  • Subscriber tools — JWT tier auth, get_subscriber_portfolio, get_marketplace_listings
  • Unified path resolver (paths.py) — default_control_tower() works on Mac + WSL tower
  • Data backend chain — Databento → Massive S3 (back to 2003) → Polygon → yfinance
  • SHA-256 model integrity — startup check raises on tampered .pkl, XGBoost JSON companion, model_manifest.json
  • Drawdown Triple Penance — drawdown_start_ts auto-logged on first daily loss hit (Bailey & LdP 2015)

v22.0 (2026-04-05) — MCP 2025-11-25 Full Compliance

  • Elicitation (human confirmation for high-value trades)
  • Durable Tasks (background backtest/optimization jobs)
  • SSE streaming transport
  • OIDC discovery endpoint
  • Trading guardrails with circuit breakers
  • AlphaLoop evolution daemon

See the full CHANGELOG.md for v21.x, v22.x, and legacy v26 audit entries.


Quick Setup Options (Pick Your Path)

PathCredential neededBest for
ADemo modeNoneMarket data, regime detection, tools exploration
BAlgoChains hosted papersub_live_… key (free signup)Copy-trade MNQ bot, zero broker setup
B-2Alpaca paperAlpaca paper API keyYour own paper equity account
CFull liveTradovate + othersReal futures/equities trading

Option A — Demo Mode (No Credentials, 1 Minute)

pip install algochains-mcp-server
python scripts/quickstart.py --mode demo

Available immediately (no credentials):

  • get_quote("AAPL") — live price for any symbol
  • detect_market_regime() — trending / ranging / choppy
  • get_macro_signals() — macro environment analysis
  • discover_tools() — find any of the 503 tools
  • onyx_ask("any question") — knowledge base search

Option B — AlgoChains Hosted Paper (Free, No Broker Needed)

No Tradovate account. No Alpaca account. No broker credentials at all.

  1. Sign up at algochains.ai — free hosted virtual paper account
  2. Copy your subscriber key from the dashboard (sub_live_…)
  3. Set it and run:
export ALGOCHAINS_SUBSCRIBER_KEY=sub_live_your_key_here
python scripts/quickstart.py --mode paper

What unlocks immediately: all 9 subscriber tools — copy-trade signals from the live MNQ bot, real P&L tracking, fill history, and self-directed paper orders filled at real quotes. See the Subscriber Onramp section above.

Option B-2 — Alpaca Paper (Your Own Broker)

export ALPACA_API_KEY=your-paper-key
export ALPACA_SECRET_KEY=your-paper-secret
export ALPACA_PAPER=true
python scripts/quickstart.py --mode paper

Option C — Full Live Setup

cp .env.example .env
# Edit .env with Tradovate, Polygon, Databento, Slack credentials
python scripts/quickstart.py --health-check --mode live

Generate IDE Config

python scripts/quickstart.py --generate-config cursor         # Cursor
python scripts/quickstart.py --generate-config claude-desktop # Claude Desktop
python scripts/quickstart.py --generate-config windsurf       # Windsurf

Data Backends

AlgoChains uses a priority chain — best available source wins automatically:

PriorityBackendCoverageUse Case
1DatabentoXNAS.ITCH + XNYS.PILLAR; OHLCV-1d + OHLCV-1mFutures tick data, live streaming
2Massive S3us_stocks_sip/day_aggs_v1/ back to 2003Historical equity backtests, survival-bias-free universe
3PolygonREST bars + news snapshotsNews features, intraday bars
4yfinanceFree, ~5yr historyDev fallback, swing bots

Force a specific backend: DATA_BACKEND=databento|massive|polygon|yfinance in .env.


Command Center

URLStatusNotes
https://cc.algochains.ioLiveCloudflare Access — authenticate with your @algochains.io account
http://localhost:3333Local devAlways accessible without auth

Run locally:

cd algochains-command-center
npm run dev   # starts on :3333

Start Cloudflare tunnel:

cloudflared tunnel run <your-tunnel-id> >> logs/cloudflared_cc.log 2>&1 &

Dashboard panels (V22):

  • Bot Status Cards — process state, uptime, last signal, AI confidence
  • P&L Chart + Positions Table + Risk Dashboard
  • Bracket Status Panel + AI Ensemble Health + Live Trade Validation Feed (SSE)
  • Subscriber Protection Panel + System Health

Agentic Quick-Start Prompts

Copy these directly into Claude or Cursor:

Subscriber prompts (free, no broker needed)

Portfolio snapshot:
"Run get_my_portfolio. What's my paper balance and P&L today?"

Signal stream check:
"Call get_signal_stream for the MNQ bot. What signals fired in the last 2 hours?"

Weekly fill review:
"Run get_my_fills with limit=50. Break down P&L by day."

Marketplace discovery:
"Run get_marketplace_listings. What bots are available and what's each bot's asset class?"

Live bot / operator prompts

Morning brief:
"Run get_macro_signals and get_live_bot_metrics. Summarize market conditions and P&L."

Bot health check:
"Run get_bot_health for all 4 bots. Flag anything that needs attention."

Pre-trade regime check:
"Before I place any orders, run detect_market_regime and check VIX. Should I trade today?"

Validate a backtest:
"Run validate_strategy_metrics: Sharpe 2.4, MaxDD 9%, WinRate 58%, 180 trades.
 Does it pass the MCPT gate? What's the DSR?"

Prop fund compatibility:
"Use evaluate_strategy_for_prop_fund: MNQ scalper, $600 max daily loss, $2500 max DD,
 $120 avg daily profit, holds overnight. Which fund should I target?"

Emergency system check:
"Run check_all_broker_credentials and check_rithmic_status. What's ready, what's missing?"

Tower dispatch:
"Dispatch an overnight Optuna sweep for MNQ to the desktop tower. 200 trials, Sharpe objective."

Supported Brokers

BrokerAsset ClassesStatus
TradovateFutures (MNQ, CL, MES, NQ, ES, GC)✅ Live
AlpacaEquities, ETFs, Options, Crypto✅ Live + Paper
OANDAForex (50+ pairs)✅ Live
Interactive BrokersStocks, Futures, Options, Forex✅ Live (ib_async)
KalshiPrediction markets (US events)✅ Live
E*TRADEEquities, Options, ETFs✅ OAuth 1.0a
RithmicFutures via prop fund platforms⏳ DRY_RUN (vendor NDA pending)
Charles SchwabEquities, Options, Futures⚠️ Stubs (OAuth 2.0 PKCE)
# Check all broker credential status at once
check_all_broker_credentials()   # masked — never exposes values

Architecture

Your AI (Claude / Cursor / ChatGPT)
         │
         │ MCP 2025-11-25 (stdio or HTTP + SSE)
         ▼
AlgoChains MCP Server
  ├── 503 tools / 168 smart-mode (20 domains)
  ├── Trading Guardrails (hard-coded limits, AI loop detection)
  ├── Account Protection (12 pre-trade guards)
  ├── Onyx RAG (semantic search — 400+ docs + 472 skills)
  └── Circuit Breakers (per-tool rate limits, daily loss stops)
         │
         ├── Tradovate     (MNQ, CL, MES, NQ futures — live fills)
         ├── Alpaca        (equities, crypto, options)
         ├── OANDA         (forex)
         ├── Databento     (tick-level data — XNAS.ITCH)
         ├── Massive S3    (day bars back to 2003)
         ├── Polygon       (real-time bars, news)
         └── FRED, CBOE, Kalshi, Polymarket  (macro / alt data)

Data policy: No synthetic data. No mock fills. No placeholder values. Every tool connects to a real API or fails closed with an explicit error.


Docs

FilePurpose
SAFETY_MODEL.mdIs this safe? Failure modes, guardrails, team access
CHANGELOG.mdFull version history
docs/GOTCHAS_AND_BUGS.mdConfirmed bugs, gotchas, operational surprises
docs/DEVELOPER_TIER_ONBOARDING.mdDeveloper key setup, scopes, and bridge auth constraints
docs/NUMERAI_TOURNAMENT.mdNumerai tournament tool sequence, upload gates, and troubleshooting
docs/TRADOVATE_PARITY.mdTradovate endpoint mapping vs community server
docs/CLI_GAP_ANALYSIS.mdac CLI current commands + 10 missing subcommands roadmap
LATENCY_GUIDE.mdMeasured tool call latencies (Mac M3 Max, real calls)
MARKETPLACE_CREATOR_GUIDE.mdPublish a validated bot; subscriber copy-trade pipeline setup
algoclaw/README.mdAlgoClaw agent skill system

Built by Tyler Reynolds — experimental AI trading infrastructure.

Safety · Changelog · Command Center · Marketplace

Experimental software connected to live trading accounts. Use at your own risk.

Ver o original no GitHub

Bom para

Relacionados