MCP server: look up MIME content types from file extensions and vice versa.
Two simple, read-only tools with clear naming and basic schemas. Both tools have descriptions and input schemas with type definitions. However, parameter descriptions are minimal (ext and content_type lack detail on format/constraints), output schemas are undocumented, and error handling is generic. The server is functional but lacks LLM-optimization patterns: no guidance on when to use each tool, no format constraints, no examples of valid input ranges, and no structured output documentation. Naming follows verb_noun convention (from_extension, to_extension) which is good, but descriptions could be more actionable for LLM selection.
Look up the MIME content-type for a file extension or filename. Returns null if unknown.
Return the best-guess file extension for a MIME content-type (e.g. "application/json" → "json"). Returns null if unknown.
Parameter descriptions lack format guidance. 'ext' parameter has no detail on accepted formats (bare extension vs filename vs dotted extension). 'content_type' has no description at all.
Output schema is undocumented. Tool descriptions do not specify what fields are returned (content_type, ext, null handling). LLMs cannot plan downstream calls without knowing the response structure.
Tool descriptions lack context for LLM selection. No explanation of when to use from_extension vs to_extension, or what 'best-guess' means for to_extension (ambiguity in MIME-to-extension mapping).
No input validation constraints documented. No mention of case sensitivity, maximum string length, or handling of edge cases (empty string, null, non-ASCII).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
Error messages are generic ('mime tool failed'). No recovery guidance for LLM when a lookup fails (e.g., unknown extension or MIME type).