Skip to main content
Glama
laukikk

Alpaca Trading MCP Server

by laukikk

place_stop_order

Place a stop order to buy or sell stocks automatically when a specified price is reached, using the Alpaca Trading MCP Server.

Instructions

Place a stop order to buy or sell a stock when it reaches a specified price.

Args: symbol: Stock symbol (e.g., 'AAPL') quantity: Number of shares to buy or sell (can be fractional) side: Either 'buy' or 'sell' stop_price: Price that triggers the order time_in_force: Order duration - 'day', 'gtc' (good till canceled)

Returns: Order confirmation details

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYes
quantityYes
sideYes
stop_priceYes
time_in_forceNoday

Implementation Reference

  • The primary handler function for the 'place_stop_order' MCP tool. It handles input validation using enums, constructs an AlpacaOrderRequest with STOP order type, delegates to calls.place_order for execution, and formats the response.
    @mcp.tool()
    def place_stop_order(
        symbol: str, 
        quantity: float, 
        side: str, 
        stop_price: float,
        time_in_force: str = "day"
    ) -> str:
        """
        Place a stop order to buy or sell a stock when it reaches a specified price.
        
        Args:
            symbol: Stock symbol (e.g., 'AAPL')
            quantity: Number of shares to buy or sell (can be fractional)
            side: Either 'buy' or 'sell'
            stop_price: Price that triggers the order
            time_in_force: Order duration - 'day', 'gtc' (good till canceled)
        
        Returns:
            Order confirmation details
        """
        # Validate side
        try:
            order_side = AlpacaOrderSide(side.lower())
        except ValueError:
            return f"Invalid side: {side}. Must be 'buy' or 'sell'."
        
        # Validate time in force
        try:
            order_tif = AlpacaTimeInForce(time_in_force.lower())
        except ValueError:
            return f"Invalid time in force: {time_in_force}. Valid options are: day, gtc"
        
        # Create order request
        order_request = AlpacaOrderRequest(
            symbol=symbol,
            qty=float(quantity),
            side=order_side,
            type=AlpacaOrderType.STOP,
            time_in_force=order_tif,
            stop_price=float(stop_price)
        )
        
        try:
            order = calls.place_order(trading_client, order_request)
            
            return (
                f"Stop order placed successfully!\n\n"
                f"Order ID: {order.id}\n"
                f"Symbol: {order.symbol}\n"
                f"Side: {order.side.value}\n"
                f"Type: {order.type.value}\n"
                f"Quantity: {order.qty}\n"
                f"Stop Price: ${order.stop_price:.2f}\n"
                f"Time in Force: {order.time_in_force.value}\n"
                f"Status: {order.status.value}\n"
                f"Created At: {order.created_at}\n"
            )
        except Exception as e:
            return f"Error placing stop order: {str(e)}"
  • Pydantic model defining the structure and validation for order requests, including the stop_price field used by stop orders. Provides type safety and validation for the tool's inputs.
    class AlpacaOrderRequest(BaseModel):
        symbol: str
        qty: Union[int, float]
        side: AlpacaOrderSide
        type: AlpacaOrderType
        time_in_force: AlpacaTimeInForce
        limit_price: Optional[float] = None
        stop_price: Optional[float] = None
        client_order_id: Optional[str] = None
        extended_hours: Optional[bool] = False
  • Helper function that translates the generic AlpacaOrderRequest into Alpaca-specific StopOrderRequest for STOP orders and submits it to the trading client via submit_order.
    def place_order(client: TradingClient, order_details: AlpacaOrderRequest):
        """
        Place an order with flexible order types
        
        :param client: Alpaca trading client
        :param order_details: Order request details
        :return: Placed AlpacaOrder
        """
        # Map Pydantic model to Alpaca order request based on order type
        if order_details.type == AlpacaOrderType.MARKET:
            order_request = MarketOrderRequest(
                symbol=order_details.symbol,
                qty=order_details.qty,
                side=order_details.side,
                time_in_force=order_details.time_in_force
            )
        elif order_details.type == AlpacaOrderType.LIMIT:
            if not order_details.limit_price:
                raise ValueError("Limit price is required for limit orders")
            order_request = LimitOrderRequest(
                symbol=order_details.symbol,
                qty=order_details.qty,
                side=order_details.side,
                time_in_force=order_details.time_in_force,
                limit_price=order_details.limit_price
            )
        elif order_details.type == AlpacaOrderType.STOP:
            if not order_details.stop_price:
                raise ValueError("Stop price is required for stop orders")
            order_request = StopOrderRequest(
                symbol=order_details.symbol,
                qty=order_details.qty,
                side=order_details.side,
                time_in_force=order_details.time_in_force,
                stop_price=order_details.stop_price
            )
        elif order_details.type == AlpacaOrderType.STOP_LIMIT:
            if not (order_details.stop_price and order_details.limit_price):
                raise ValueError("Both stop and limit prices are required for stop-limit orders")
            order_request = StopLimitOrderRequest(
                symbol=order_details.symbol,
                qty=order_details.qty,
                side=order_details.side,
                time_in_force=order_details.time_in_force,
                stop_price=order_details.stop_price,
                limit_price=order_details.limit_price
            )
        else:
            raise ValueError(f"Unsupported order type: {order_details.type}")
    
        # Submit order
        order = client.submit_order(order_request)
        return AlpacaOrder(**order.__dict__)
  • Enum defining order types, including STOP used in the tool.
    class AlpacaOrderType(str, Enum):
        MARKET = 'market'
        LIMIT = 'limit'
        STOP = 'stop'
        STOP_LIMIT = 'stop_limit'
        TRAILING_STOP = 'trailing_stop'
  • src/server.py:377-377 (registration)
    The @mcp.tool() decorator registers the place_stop_order function as an MCP tool.
    @mcp.tool()
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions the tool 'places' an order (implying a write/mutation) but doesn't disclose behavioral traits like whether it requires authentication, has rate limits, what happens on execution failure, or confirmation details format. The description adds minimal behavioral context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and well-structured with clear sections for purpose, args, and returns. Each sentence earns its place, though the 'Returns' section is vague ('Order confirmation details') and could be more specific.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (financial order placement with 5 parameters), no annotations, and no output schema, the description is moderately complete. It covers parameters well but lacks behavioral context (e.g., auth, errors) and output details, leaving gaps for a mutation tool in a financial context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates by explaining all 5 parameters in detail: symbol (with an example), quantity (including fractional shares), side (with valid values), stop_price (its role), and time_in_force (with options and default). It adds meaning beyond the bare schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Place a stop order'), the resource ('to buy or sell a stock'), and the condition ('when it reaches a specified price'). It distinguishes this tool from siblings like place_limit_order and place_market_order by specifying it's a stop order triggered by price.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context through the tool name and description, suggesting it's for placing stop orders. However, it doesn't explicitly state when to use this versus alternatives like place_stop_limit_order or place_limit_order, nor does it mention prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/laukikk/alpaca-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server