Loading ToolBench
MCP server for AI-powered 3D model and environment generation via the Meshy API — use inside Claude Desktop or any MCP-compatible client
Strong tool definitions with comprehensive descriptions and well-structured schemas. All 6 tools have clear, action-verb names (generate_, refine_, add_, check_, list_) and detailed descriptions (150-400 chars). Input schemas are complete with typed parameters and enums. However, output schemas are not formally documented in the code, and error handling lacks recovery guidance. Tool composition is sound, each tool has a single responsibility and outputs chain naturally (e.g., generate_3d_model → refine_3d_model → add_texture). Parameter descriptions are thorough and include constraints (e.g., polycount ranges, enum values). No security issues detected (API key injected server-side). Minor gaps: descriptions could be more concise (some exceed 400 chars), and output structure is only documented in prose, not as formal JSON Schema.
Apply AI-generated textures to an existing 3D model using Meshy AI. Takes a GLB or OBJ model URL and generates: • Base color map • Metallic map • Roughness map • Normal map (for surface detail without extra polygons) Returns a fully textured GLB/FBX ready for Three.js, Babylon.js, Unity, Unreal Engine, or Blender. Use cases: • Apply brand-specific textures to clothing 3D models • Add realistic material finishes (leather, fabric, metal, wood) • Generate texture variants for A/B testing product visuals • Style website 3D environments with custom looks
Check the status and progress of any Meshy generation task. Returns current status (PENDING, IN_PROGRESS, SUCCEEDED, FAILED), progress percentage, and download links once complete. Use this when you started a task with wait_for_completion: false, or to check on a previously started generation.
Turn any image into a 3D model using Meshy AI. Best inputs: • Product photos (sneakers, bags, furniture, clothing items) • Objects on white or clean backgrounds • Front-facing or 3/4-view photos • Logos or illustrations to extrude into 3D Returns GLB, FBX, OBJ, and USDZ download links with optional PBR textures. Use cases: • Turn a clothing brand's product photo into a 3D asset • Generate 3D models from design mockups or sketches • Convert reference images into scene props
Generate a 3D model from a text description using Meshy AI. Returns download links for GLB, FBX, OBJ, and USDZ formats, plus a thumbnail and turntable video preview. Use cases: • Product 3D assets for e-commerce or AR • Game and scene props • Architectural models • Fashion and clothing items • Characters and creatures After generating a preview, call refine_3d_model for production-quality output, or add_texture to apply custom textures.
Output schemas not formally documented. Tool descriptions mention return fields (GLB/FBX/OBJ URLs, task IDs, status, progress) but no JSON Schema is visible in code. LLMs cannot reliably parse unstructured responses or plan downstream calls.
Error handling lacks recovery guidance. Tool implementations catch errors and return '❌ Error: {message}' but do not categorize errors (retryable vs. user-fixable vs. fatal) or suggest next steps. E.g., 'API rate limit exceeded. Retry in 60 seconds.' or 'Invalid image URL. Ensure the URL is publicly accessible.'
Tool descriptions exceed recommended length (150-200 chars). generate_3d_model description is ~350 chars with embedded use cases and follow-up guidance. While informative, this wastes tokens and buries key details. Condense to core action + when to use.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 62 | 2026-07-28+ | v2 |
List your recently generated 3D models from Meshy. Returns task IDs, prompts, statuses, and download links for your most recent text-to-3D generations.
Refine a preview 3D model to production quality using Meshy AI. Run this after generate_3d_model to get: • Higher polygon detail • PBR texture maps (base color, metallic, roughness, normal) • Production-ready GLB/FBX/OBJ files suitable for Unreal Engine, Unity, Blender, Three.js, or AR Requires a completed preview task ID from generate_3d_model.
list_3d_models has no required parameters but description is vague ('List your recently generated 3D models'). Does it return all models, only completed ones, or only text-to-3D? Does it support filtering by status or date? Clarify scope and add optional filter parameters.
Pagination not implemented. list_3d_models accepts a 'limit' parameter but no offset/cursor. If a user has 100+ models, the tool returns only the first 10 (default). No way to fetch older models. Add offset or cursor-based pagination.