Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sentinel Add NVIDIA to my watchlist and check it against my risk limits"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A production-grade algorithmic trading control plane exposed as an MCP server — so Claude can manage watchlists, classify market regimes, validate risk, and submit paper orders through natural language.
Sentinel is a two-package monorepo:
Package | Language | Role |
| Python 3.12 / FastAPI | All trading logic: risk checks, regime classification, order lifecycle, audit journal, strategy governance |
| TypeScript / Node 20 | Thin MCP server that routes 40+ tools to the engine via HTTP. Zero trading logic lives here. |
Claude (or any MCP-compatible agent) talks to the MCP server. The MCP server talks to the engine. The engine owns the database and cache.
Related MCP server: Alpaca MCP Server
Claude Desktop (or any MCP agent)
│
│ MCP protocol (stdio or SSE)
▼
┌─────────────────────────┐
│ MCP Server │ TypeScript · Zod validation · tool routing
│ (packages/mcp) │
└────────────┬────────────┘
│ HTTP REST (localhost:8100)
▼
┌─────────────────────────┐
│ Engine API │ Python · FastAPI · all trading logic
│ (packages/engine) │
└──────────┬──────────────┘
│
┌───────┴────────┐
▼ ▼
PostgreSQL Redis
(orders, (kill switch,
positions, rate limits,
strategies, cache)
audit log)If the engine is unavailable, every MCP tool call returns an error immediately. There is no fallback or partial execution.
The fastest way to get running. Requires Docker and Node.js 20+.
# 1. Clone and configure
git clone https://github.com/rohith1125/sentinel-execution-mcp.git
cd sentinel-execution-mcp
cp .env.example .env # defaults work out of the box — no edits needed
# 2. Start Postgres + Redis + engine (runs migrations automatically)
docker compose -f docker/docker-compose.yml up -d db redis engine
# Wait ~10 seconds, then verify the engine is healthy:
curl http://localhost:8100/health
# {"status": "ok", "provider": "mock", ...}
# 3. Build the MCP server (one-time)
cd packages/mcp
npm install
npm run buildThen add Sentinel to Claude Desktop (see Connect Claude Desktop below) and restart Claude. That's it — all 40 tools are live.
Use this if you have Postgres and Redis already running locally.
Prerequisites:
Dependency | Minimum version | Notes |
Python | 3.12 | Engine runtime — check with |
Node.js | 20 | MCP server runtime |
PostgreSQL | 15+ | Primary data store |
Redis | 7+ | Kill switch and cache |
git clone https://github.com/rohith1125/sentinel-execution-mcp.git
cd sentinel-execution-mcp
cp .env.example .env
# Default values work for local paper-trading development — no edits requiredcd packages/engine
python3.12 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e ".[dev]"# From packages/engine with the venv active
alembic upgrade headuvicorn sentinel.api:app --reload --port 8100Verify it is running:
curl http://localhost:8100/health
# {"status": "ok", "env": "paper"}Open a second terminal:
cd packages/mcp
npm install
npm run build
npm run dev # stdio transport — for direct Claude Desktop integrationAdd the following to your Claude Desktop configuration file.
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Get the correct path by running this in your terminal:
echo "$(pwd)/packages/mcp/dist/index.js"Then paste it into the config:
{
"mcpServers": {
"sentinel": {
"command": "node",
"args": ["/absolute/path/to/sentinel-execution-mcp/packages/mcp/dist/index.js"],
"env": {
"ENGINE_BASE_URL": "http://localhost:8100",
"APP_ENV": "paper"
}
}
}
}Restart Claude Desktop after saving. You should see a hammer icon (🔨) in the chat input — click it to confirm Sentinel's 40 tools are loaded.
Sentinel exposes 40+ tools across nine categories. The MCP server name is sentinel.
Category | Tool | Description |
Watchlist |
| Add symbols to the trading watchlist, optionally assigned to a group |
| Remove symbols; they will no longer appear in strategy scans | |
| List active symbols, optionally filtered by group | |
| Get details for a single symbol | |
| List all named watchlist groups | |
| Update notes or group assignment for a symbol | |
Market Data |
| Latest quote and trade data for one or more symbols |
| OHLCV bar history with configurable timeframe | |
| Real-time bid/ask spread for a symbol | |
| Check market data provider connectivity | |
Regime |
| Classify current market regime using ATR, ADX, RSI, Bollinger Width, Hurst Exponent, VWAP, and Price Efficiency |
| Retrieve historical regime snapshots for a symbol | |
Strategy |
| Scan the watchlist for signals across one or more strategies |
| Evaluate a single symbol against a specific strategy | |
| List all registered strategies and their current state | |
Risk / Kill Switch |
| Run all 13+ risk checks against a proposed trade before submission |
| Get the current state of all kill switches | |
| Enable a kill switch globally, per-strategy, or per-symbol | |
| Disable a kill switch (requires explicit reason) | |
| Current gross and net exposure summary | |
| Current daily drawdown against configured limits | |
Portfolio |
| Full account overview: value, cash, equity, P&L, buying power |
| All open positions with unrealized P&L | |
| Closed position history with realized P&L | |
Execution |
| Submit a paper trading order (market, limit, stop, stop-limit) |
| Cancel a pending or partially filled order by ID | |
| Get the current state of a specific order | |
| List orders filtered by status, symbol, or date range | |
| Trigger a manual reconciliation between engine state and broker | |
Governance |
| Register a new strategy in |
| Advance a strategy: Draft → Research → Backtest → Paper → Live | |
| Suspend a live or paper strategy immediately | |
| List all strategies with their current lifecycle state | |
| Check whether a strategy meets criteria for promotion | |
Audit |
| Full human-readable explanation for a trade decision by audit event ID |
| Most recent audit events, filterable by symbol or strategy | |
| Completed trade history with outcomes | |
| Raw decision log entries for a time window | |
| Aggregate statistics: win rate, average P&L, Sharpe proxy | |
| Export audit records as CSV for a date range |
Full tool documentation with parameter schemas: docs/mcp-tools.md
packages/engine/.env)Variable | Default | Description |
|
|
|
|
| PostgreSQL connection string |
|
| Redis connection string |
|
|
|
| (empty) | Required when |
| (empty) | Required when |
|
| Use |
|
| Maximum position size as a fraction of account equity (5%) |
|
| Hard daily loss limit (2%); trading halts if breached |
|
| Maximum gross exposure across all positions (80%) |
|
| Maximum number of simultaneously open positions |
|
| Maximum risk per individual trade (1%) |
|
| Simulated fill latency in paper trading mode |
|
| Simulated slippage in basis points |
|
| Set to |
| (empty) | Generate with |
| (empty) | JSON array of additional client key records |
packages/mcp/.env)Variable | Default | Description |
|
| Base URL of the running engine service |
See .env.example at the repo root for the complete annotated reference.
# 1. Add symbols
watchlist.add(symbols=["NVDA", "MSFT", "AAPL"], group="tech")
# 2. Classify regime
regime.evaluate(symbol="NVDA", timeframe="1Day")
# 3. Scan for signals
strategy.scan(group="tech", strategy="momentum_v1")
# 4. Validate before submitting
risk.validate_trade(symbol="NVDA", side="buy", qty=10, order_type="market")
# 5. Submit paper order
execution.paper_order(symbol="NVDA", side="buy", qty=10, order_type="market")
# 6. Review portfolio
portfolio.status()
# 7. Inspect the audit trail
audit.recent_events(symbol="NVDA", limit=1)
audit.explain_trade(audit_event_id="evt-...")cd packages/engine
source .venv/bin/activate
pytest tests/ -vcd packages/mcp
pnpm test# From repo root
make checksentinel-execution-mcp/
├── packages/
│ ├── engine/ # Python FastAPI trading engine
│ │ ├── sentinel/ # Application source
│ │ ├── tests/ # Pytest test suite
│ │ └── alembic/ # Database migrations
│ └── mcp/ # TypeScript MCP server
│ └── src/
│ └── tools/ # One file per tool category
├── docker/ # Dockerfiles and docker-compose
├── docs/ # Architecture, tool reference, risk model
├── scripts/ # Setup and reset helpers
└── .env.example # Annotated environment variable referenceThis software is for paper trading and research only unless you fully understand every component. Setting APP_ENV=live with real Alpaca credentials will place real orders with real money. The hard-coded risk limits are conservative defaults — verify they match your own risk tolerance before use. The authors accept no liability for financial losses.
MIT. See LICENSE.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Trade Robinhood through natural language in Claude Code.
Global stock research, ML forecasts, valuation signals, screeners & portfolio tracking in Claude
Build, backtest, and deploy quantitative trading strategies from your AI agent.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rohith1125/sentinel-execution-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server