MCP server providing Warhammer 40k Aeldari rules data for LLM-powered gameplay decisions and list building
Server has 5 tools with reasonable naming (verb_noun pattern) and descriptions. All tools are READ_ONLY, reducing risk. However, parameter descriptions are sparse or missing for several tools. The validate_list tool has NO description at all. Output schemas are not documented in the source. Error handling and recovery guidance are absent. Descriptions average ~120 chars, which is acceptable but could be more specific about when to use each tool vs. alternatives.
Compare two Warhammer 40k units side-by-side, showing stats, weapons, abilities, and points differences. Works across all factions.
Get the full datasheet for a Warhammer 40k unit including stats, weapons, abilities, points, and keywords. Supports exact and partial name matching. Optionally filter by faction.
List Warhammer 40k stratagems, optionally filtered by faction, detachment, type, or keyword search. Returns stratagem names, CP costs, timing, targets, and effects.
Semantic search over all Warhammer 40k rules, unit data, stratagems, enhancements, and abilities across all factions. Uses vector embeddings for natural language queries like 'best anti-tank weapons' or 'units that can deep strike'.
validate_list tool has NO description and NO visible input schema in source code. Cannot assess what it does or how to call it.
Output schemas are not documented anywhere in the source. LLMs cannot plan downstream tool calls or extract structured data without knowing what fields each tool returns.
No error handling or recovery guidance visible. If a unit name is not found or a search returns no results, the tool provides no actionable next steps for the LLM.
compare_units tool description does not explain when to use it vs. get_unit called twice. LLMs may not recognize it as a specialized comparison tool.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2026-07-28+ | v2 |
search_rules accepts 'type' enum with 9 values but no guidance on which type to use for common queries (e.g., 'best anti-tank weapons' → unit_weapons vs. stratagem).