MCP server to search & investigate glp1forum.com (XenForo) with no API keys
Strong tool naming (all verb-first: search_, get_, list_), comprehensive parameter descriptions with actionable guidance (e.g., 'AND-matched: every word must appear'), and explicit schema definitions using Zod. Tool descriptions are detailed (194 - 392 chars, well above baseline 194 avg) and include recovery hints ('wait ~60s before retrying', 'drop a term, never add one'). All 5 tools have input schemas with typed parameters. However, output schemas are not documented, responses are JSON-stringified without field-level documentation, forcing LLMs to infer structure. Error handling is mentioned in descriptions but not formalized in tool responses. Composition is clean: each tool has one responsibility, and search_forum output includes URLs that feed into get_thread/get_thread_images.
Read a thread's posts (paginated) for full context.
Opt-in: download a thread's image attachments at full size so their text (pricing tables, per-warehouse stock boards, COA purity figures, payment pages) is readable by vision. Much of the vendor pricing on glp1forum is image-only and invisible to get_thread's text. Returns a summary plus the images as blocks; use max to cap how many download (default 4, max 5). Costs one throttled request per image.
List forum sections with numeric node IDs (feed these to search_forum.nodes).
Browse a forum section's threads (use list_forums for nodeIds).
Full-text search glp1forum.com with granular XenForo filters. Multi-word keywords are AND-matched (all terms must appear). Category/parent nodes (e.g. 45 Vendor Connection) return nothing unless includeChildNodes: true. A rate-limit error means wait ~60s before retrying. Result has truncated: true when more result pages exist than were fetched — re-search with a higher maxPages (max 3) to get the rest.
Output schemas not documented. Tools return JSON-stringified text without field-level documentation. LLMs cannot infer which fields are present, their types, or how to chain results to downstream tools.
Error handling not formalized in tool responses. Descriptions mention rate limits and truncation, but tools do not return structured error objects with recovery guidance. LLMs cannot distinguish retryable vs. fatal failures.
list_forums and list_threads descriptions are minimal (50 - 60 chars, below 100-char baseline). They lack context on when to call them or what structure they reveal. 'List forum sections' does not explain that output feeds into search_forum.nodes.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 58 | 2026-07-28+ | v2 |
get_thread description lacks pagination guidance. It mentions 'page 1 then re-fetch page: lastPage' but does not explain what lastPage is or how to detect it in the response. Agents cannot determine when to stop paginating.
search_forum accepts both url and threadId as alternatives, but no mutual-exclusivity guidance. Description does not state 'pass one or the other, not both' or what happens if both are provided.