No user-submitted related servers found.
Scored across 24 tools
The asset_generate_* family is clearly separated by output artifact, and the processing, ingestion, validation, and export tools have mostly distinct jobs. The main ambiguity is between asset_doctor and asset_capabilities, which both report currently available execution modes, and asset_export_bundle vs asset_save_inline_svg both create platform bundles from different input types.
All tools share the asset_ prefix and snake_case, so the surface is readable, but the internal convention is inconsistent: verb-first names like asset_generate_logo and asset_init_brand coexist with object-first names like asset_models_list, asset_models_inspect, and asset_brand_bundle_parse, plus noun-only names like asset_sprite_sheet and asset_capabilities. The asset_generate_* subfamily is consistent, but the rest does not follow one clearly predictable pattern.
At 24 tools, the set is at the heavy/borderline end for an MCP server: each tool has a real purpose, but several generate_* variants and model/doctor helpers could be consolidated or parameterized to make the surface easier for an agent to discover. The count is not egregious, but it is above the ideal compact size.
The tool surface covers the full lifecycle from brand ingestion and prompt enhancement through generation, saving/ingestion, validation, vectorization, upscaling, background removal, platform export, sprite sheets, 9-slice config, model inspection, and environment diagnosis. Every execution mode has a clear follow-up path, so the workflow does not end in a dead end.