Free client for the PurrPlan MCP at https://app.purrplan.ai/api/mcp
Critical failures across all dimensions. Source code shows only tool names and scopes in src/tools.ts with NO input schemas, NO descriptions, and NO output documentation. Tool definitions are inferred from names alone. The example server.js demonstrates HTTP transport but does not show MCP protocol implementation. No evidence of parameter validation, error handling guidance, or schema definitions. This is a client library, not a fully-fledged MCP server with proper tool definitions.
No tool descriptions present. All 18 tools lack descriptions required by pattern:tool-description. LLMs cannot determine when or why to select tools without descriptions.
No input schemas visible in source code. Tools are defined as name+scope pairs only. Cannot verify parameter types, constraints, or descriptions. Violates pattern:constrained-input and pattern:tool.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 27 | 2026-07-28+ | v2 |
Destructive operations (delete_post) lack confirmation or dry-run support. No evidence of pattern:confirmation-request implementation. Agents can delete posts without safeguards.
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., post_id from create_draft_post for use in update_draft_post). Violates pattern:tool and pattern:tool-chain.
No error handling guidance visible. No evidence of pattern:recovery-guide or pattern:error-classification. LLMs cannot determine if errors are retryable or what corrective action to take.