Server has 6 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (10-100 chars, mostly adequate), and input schemas are present with type definitions. However, parameter descriptions are sparse or missing entirely. Output schemas are undocumented, LLMs cannot predict response structure. Error handling is absent; no recovery guidance or actionable error messages. Tool naming follows verb_noun convention (get_, create_, publish_) which is good, but composition issues exist: create_mcp_from_github_link conflates GitHub URL parsing, MCP server creation, and optional Phala hosting into one tool. No tool annotations (readOnlyHint, destructiveHint) despite clear read/write distinctions. Parameter constraints lack detail (e.g., env_string format is vague). Average tool score: 48/100.
Clones a published flow template on MOOF using its flow ID.
Create a new MCP server from a public GitHub repository link (supports Phala deploy & custom environment).
Fetches published flow list from MOOF.
Fetch the 5 most recent flows created by the authenticated user (requires x-api-key).
Set access_type of a flow to PUBLIC (visible in store). Requires x-api-key.
Set access_type of a flow to PRIVATE (hide from store). Requires x-api-key.
Output schemas completely undocumented. LLMs cannot predict response structure, field names, or types for any tool. Breaks downstream tool chaining and forces agents to guess at response format.
No error handling or recovery guidance. Tools provide no actionable error messages, categorization (retryable vs fatal), or next-step hints. Agents cannot self-correct on failures.
create_mcp_from_github_link conflates three concerns: GitHub URL parsing, MCP server creation, and optional Phala hosting. Should split into separate tools (create_mcp_server, configure_phala_hosting) for composability.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 52 | <=2025-11-25 | v2 |
Parameter descriptions missing or vague. env_string format is described as 'plain string' with example 'RPC_URL=https://... API_KEY=abc123' but no formal constraint (regex, length limit, or validation rules). LLMs cannot reliably construct valid input.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Tools marked as READ_ONLY or WRITE in metadata but not exposed to LLM via schema. Agents cannot reason about side effects or retry safety.