Loading ToolBench
Scaffold a new MCP server with OAuth 2.1 already wired up, via mcpauth.
This is a scaffolding CLI tool, not a production MCP server. The single 'echo' tool has a valid schema and basic description, but the server itself is a template generator. The echo tool is minimal and serves only as a placeholder example. No real business logic, no error handling guidance, no parameter descriptions, and no output schema documentation. The template demonstrates HTTP+Streamable transport correctly, but the tool quality is far below production baseline.
Echoes back text.
Tool description is trivial (11 chars: 'Echoes back text.'). Does not explain when to use it, what it returns, or any prerequisites. LLMs cannot determine selection criteria from this.
Input parameter 'text' has no description. LLMs cannot infer what format, length, or content is expected.
Output schema is not documented. The response structure (content array with type and text fields) is inferred from code but not declared in tool metadata. LLMs need explicit output schema to plan downstream calls.
No error handling or recovery guidance. If the tool fails, the LLM has no actionable next step. No validation of input length, no timeout handling, no error categorization.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
Tool name 'echo' is generic and does not follow verb_noun convention. 'echo_text' or 'repeat_message' would be clearer. Generic names like 'echo' or 'process' reduce LLM disambiguation when many tools are available.