MCP server for WordPress integration
Three tools with complete input schemas and basic descriptions, but significant gaps in parameter documentation and output schema specification. All tools expose credentials as parameters (critical security flaw), violating pattern:secret-injection. Descriptions are minimal (10-30 chars) and lack context for LLM selection. No output schemas documented. Error handling present but generic. Tool naming follows verb_noun convention correctly.
Create a new WordPress post
Get WordPress posts
Update an existing WordPress post
Credentials exposed as tool parameters (siteUrl, username, password). Violates pattern:secret-injection, agent traces log all parameters, leaking secrets into logs and prompt history.
Tool descriptions are 10-30 characters, below the 34-char p10 baseline. Descriptions lack context for when/why to use each tool and what it returns. LLMs cannot distinguish between tools or plan multi-step workflows.
No output schemas documented. LLMs cannot predict response structure, plan downstream tool calls, or extract required fields. Violates pattern:tool baseline (100% of A+ tools document return types).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
Parameter descriptions missing or trivial. 'Post status (draft, publish, etc.)' lacks format constraints. 'Number of posts per page' omits min/max bounds. Violates pattern:constrained-input and pattern:tool-description.
No idempotency guarantees or confirmation step for destructive operations (create_post, update_post). Agents retrying on ambiguous failures risk duplicate posts or unintended updates.