MCP tool place_stock_order fails with type validation error when passing qty or notional

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

The Alpaca MCP server's place_stock_order tool fails with a pydantic validation error when qty or notional are passed, even as string values. The tool's Python source correctly types these as Optional[str], but the MCP client layer appears to coerce the values to int/float before validation.

What Should Happen?

The order should be placed successfully

Error Messages/Logs

1 validation error for call[place_stock_order]
qty
  Input should be a valid string [type=string_type, input_value=1, input_type=int]

Steps to Reproduce

Configure the Alpaca MCP server (uvx alpaca-mcp-server)
Ask Claude to place a stock order with qty=1

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.296

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

PowerShell

Additional Information

Actual: Pydantic validation error — qty must be a string but receives an int

Workaround: Call the Alpaca REST API directly via Python/curl, bypassing the MCP tool.

Environment: Claude desktop app, Windows 11, alpaca-mcp-server v2.4.0