Bilingual AI prompts library, MCP registry & developer workbench — Public showcase with type-safe mock layer and C4 architecture.
This is a mock/showcase library, not a functional MCP server. The three tools (create_or_update_file, get_hackathon_overview, search_notion) are defined in src/mocks/index.ts as data structures within MOCK_MCP_SERVERS array, not as actual MCP tool implementations. No tool registration, no handler functions, no actual protocol implementation visible. Descriptions are present but generic (34 - 72 chars, below the 50 - 200 char LLM-optimized baseline). Schemas are partially visible in the mock data structure but lack proper JSON Schema format with explicit type declarations. No error handling, no output schema documentation, no parameter validation. This is a reference/documentation artifact, not a production MCP server.
Creates or updates a single file in a GitHub repository
Fetches detailed hackathon description and rules
Search pages and databases across Notion workspace
No actual MCP tool implementation, tools exist only as mock data structures in src/mocks/index.ts. No tool handlers, no protocol message routing, no actual server logic.
Descriptions are too short (25 - 72 chars) and lack LLM-optimized context. 'Fetches detailed hackathon description and rules' does not explain WHEN to use this tool vs alternatives, what it returns, or prerequisites.
Parameter schemas lack proper JSON Schema format. 'type' and 'required' are present but no 'format', 'minLength', 'maxLength', 'enum', or other constraints. Descriptions are minimal (5 - 20 chars).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
No output schema documentation. Callers cannot know what fields to expect from each tool, breaking downstream tool chaining and forcing LLMs to guess response structure.
No error handling guidance. No recovery hints, no categorization of retryable vs fatal errors, no actionable error messages for LLM self-correction.