A cookiecutter template for creating MCP servers with FastMCP, security governance, and containerized deployment
This is a cookiecutter template for MCP servers, not a production server itself. The three tools (list_records, get_record, delete_record) have basic descriptions and schemas, but lack depth. Descriptions are minimal (10-30 chars), parameter descriptions are sparse, and output schemas are not documented. No error handling guidance, no pagination support for list_records, and delete_record lacks confirmation/dry-run patterns. Tool naming follows verb_noun convention (good), but parameter documentation is insufficient for LLM reasoning.
Permanently delete a record stored by this MCP server.
Read a record stored by this MCP server.
List records stored by this MCP server.
list_records lacks pagination (limit, offset, page_size) and total count in output. Returning unbounded lists will exhaust context windows.
delete_record has no confirmation/dry-run pattern and no error guidance. Destructive operations should support confirmation before execution.
Tool descriptions are too brief (10-30 chars). Descriptions should be 50-200 chars and answer WHAT, WHEN, and WHAT IT RETURNS for LLM selection.
Output schemas are not documented. LLMs cannot plan downstream calls or extract data without knowing what fields to expect.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | 2026-07-28+ | v2 |
No error handling guidance. Error responses should tell LLMs what to do next (retry, ask user, or fail). Raw errors are useless to agents.