MCP server for calculating customs taxes, tariffs, and landed costs for cross-border e-commerce transactions
Single tool 'execute_skill_action' has a reasonable name starting with verb, but the implementation is severely deficient. The tool definition exists in mcp_server.py with a schema, but the actual MCP server code is non-functional, it only prints a JSON status message and does not implement the MCP protocol at all. No request/response handling, no tool invocation logic, no error handling. The schema is present with 4 parameters (order_subtotal_usd, origin_country_iso, destination_country_iso, hs_tariff_code), all with type and description. However, the tool description is generic (41 chars) and lacks context on when/why to use it. Parameter descriptions are minimal (e.g., 'ISO country code of origin (e.g., 'US')', includes example value, which violates pattern:tool-description). No output schema documented. The client.py and example_usage.py are mock implementations with hardcoded responses, not integrated with the MCP server. This is a skeleton project, not a working MCP server.
Execute cross-border tax and duty calculation skill action
MCP server does not implement the protocol. mcp_server.py only prints a static JSON message and exits. No request parsing, tool invocation, or response handling. The server cannot receive or process tool calls.
Tool description is too generic (41 chars) and lacks context. 'Execute cross-border tax and duty calculation skill action' does not explain WHEN to use it, WHAT it returns, or WHY it exists. Minimum 50-200 chars recommended.
Parameter descriptions include example values (e.g., 'ISO country code of origin (e.g., 'US')'). LLMs reuse examples literally. Replace with enum constraints or format declarations.
No output schema documented. Callers cannot know what fields to expect (tax_calculation_id, vat_tax_amount_usd, etc.). LLMs need structured output definitions to plan downstream calls.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 37 | 2026-07-28+ | v2 |
No error handling or recovery guidance. Tool will fail silently or return mock data. No validation of ISO country codes or HS tariff codes. No guidance for LLM on what to do if calculation fails.