topopt
Related Servers
Alternatives to topopt
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to design, modify, and verify exact B-rep 3D CAD models by running build123d scripts on an OpenCascade kernel, with live three.js preview, collision and FDM printability checks, text-based spatial perception, user notes/sketch annotations, version history, and one-click export to OrcaSlicer.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to convert raw STL mesh files into production-grade STEP AP242 solid B-Rep models and compact semantic CAD Features JSON, with sub-second deterministic processing and high mathematical fidelity.28PolyForm Noncommercial 1.0.0
- AlicenseAqualityAmaintenanceEnables MCP clients to design, verify, and export FDM 3D-printable parts by running model-written build123d scripts in a sandbox, rendering previews and cross-sections, running print checks, and exporting STEP, STL, 3MF, or PNG. It supports workflows from photos or caliper readings to finished part files through natural language.331,776 PyPI1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to drive desktop CAD software through natural language with verified execution, failure recovery, and traceable results across modeling, assemblies, drawings, exports, motion, FEA, and related engineering workflows.MIT
- AlicenseAqualityAmaintenanceEnables an LLM to design parametric 3D parts in pure NumPy and verify they are actually printable before exporting them. Provides topology checks (watertightness, genus, shell count, wall thickness), self-rendered views, and gated STL/OBJ export that refuses broken solids.7MIT
- AlicenseNot gradedqualityBmaintenanceLets an AI assistant check and repair STL/3MF meshes stored on your own computer, reporting holes, flipped faces, inside-out shells, non-manifold edges and duplicate triangles and writing a fixed copy beside the original. Everything runs locally, so the files are never uploaded and the original is never overwritten.334 npmMIT
TDQS
Scored across 32 tools
Most tools map cleanly to one workflow stage (setup, run control, verification, print, materials, cleanup), so an agent can usually pick correctly. The only plausible hesitation points are run_status vs run_result and check_problem vs show_problem, and their descriptions explicitly distinguish the pairs.
All names use consistent lowercase snake_case, mostly in verb_noun form or clear domain noun form. Family prefixes such as run_, verify_, ratchet_, and save_ are used coherently.
32 tools is above the heavy range and imposes real navigation burden even for this broad domain. Each tool covers a real step, but the set is large enough that an agent must search across many adjacent lifecycle operations.
The surface covers the full lifecycle: problem construction and checking, run start/stop/status/result, comparison and history, independent verification, print checks, materials and printer lookup, marks/cleanup/ratchet workflows, rendering, and STEP export. No obvious dead end or missing core operation is apparent.