An MCP server scaffold for Apify Actors with FastMCP framework, supporting both cloud (Apify Standby) and self-hosted deployment
Single placeholder tool with basic structure. Tool has a description (good), but it is generic and template-oriented rather than production-ready. Input schema is present with type and description for the 'name' parameter. Output is documented in code but not in formal schema. The tool is intentionally a scaffold, not a real implementation, which limits assessment. Naming is clear (hello_world), but the description reads as boilerplate ('A placeholder tool. Replace this with your domain logic.') rather than actionable guidance. No error handling, no pagination, no complex composition patterns to evaluate. Tool annotations are present (readOnlyHint, destructiveHint, idempotentHint), which is a positive signal for current spec alignment.
A placeholder tool. Replace this with your domain logic. Args: name: Who to greet. Returns a greeting. In a real Actor this is where you'd call Actor.charge('heavy-call') and return your analysis results.
Tool description is generic boilerplate ('A placeholder tool. Replace this with your domain logic.') rather than production-ready guidance. Does not explain WHEN to call it, WHAT it returns, or WHY an LLM should select it.
Output schema not formally documented. Code shows return dict with 'type', 'text', and 'structuredContent' fields, but no JSON Schema definition visible for the tool's output. LLMs cannot infer downstream field availability.
No error handling or recovery guidance. Tool has no documented failure modes, retryability, or actionable error messages. If Actor.charge() fails or input validation fails, LLM receives no guidance.
Tool is intentionally a placeholder/scaffold. Real domain logic is absent. Assessment is limited to structure, not production readiness. This is by design, but limits overall quality score.
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2025-06-18+ | v2 |