mesh-prep-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mesh-prep-mcp
An MCP server that lets an LLM agent turn a raw 3D asset into an experience-ready one — inspect, repair, decimate, rescale and export triangle meshes through the Model Context Protocol, with a small C++17 core for the numbers the agent bases its decisions on.
Why
Getting a scan or CAD export into a real-time scene is a chain of small judgement calls: is it watertight? are these millimetres? how far can I decimate before the silhouette suffers? Those calls are usually made by hand. This project exposes the underlying operators to an agent as MCP tools, returns before/after statistics for every step, and lets the agent decide — and explain — what it did. It is deliberately small: a rehearsal of agent-driven 3D data preparation, not a product.
Related MCP server: openscad-mcp
What the agent gets
Tool | What it does |
| Loads OBJ / STL / PLY / GLB / glTF / OFF / 3MF …, registers it, returns a first inspection |
| Bounds, extent, area, volume, face/vertex counts, degenerate faces, boundary & non-manifold edges, duplicate vertices, plus an issue list with the operator that fixes each one |
| Welds duplicates, drops degenerate/duplicate faces and fold-overs, fixes winding, fills small holes → new id, before/after |
| Quadric-error decimation to a face budget → new id, reduction %, surface-area drift |
| Unit conversion (e.g. mm → m) → new id |
| OBJ / GLB / glTF / STL / PLY / OFF |
| Everything in the session with full provenance |
resource | Markdown report of one mesh |
prompt | A guided full preparation pass |
Every operator returns a new mesh_id; earlier ids stay valid, so the agent can compare, branch or roll back without any undo logic.
Demo (no LLM needed)

$ python scripts/make_sample_mesh.py # 82k-face noisy "scan" in millimetres, with holes and degenerate faces
$ python scripts/demo_client.py # talks to the server over stdio, like Claude Desktop does
tools: load_mesh, inspect_mesh, repair_mesh, decimate_mesh, scale_mesh, export_mesh, list_meshes
[load_mesh] m1: 81,920 faces, 40,962 verts, extent (502, 501, 502), backend=cpp
issue: 3 degenerate (zero-area or collapsed) faces -> repair_mesh
issue: open surface: 9 boundary edges (not watertight) -> repair_mesh fills small holes; ...
[repair_mesh] m1: 81,920 faces, 40,962 verts, watertight=False, issues=2
-> m2: 81,920 faces, 40,962 verts, watertight=True, issues=0
[decimate_mesh] m2: 81,920 faces, 40,962 verts, watertight=True, issues=0
-> m3: 20,000 faces, 10,002 verts, watertight=False, issues=1
75.6% fewer faces, surface area -0.49%
issue: 1 non-manifold edges (shared by 3+ faces)
[repair_mesh] verify after decimation
-> m4: 19,998 faces, 10,001 verts, watertight=True, issues=0
[scale_mesh] x0.001 (mm -> m): extent (0.501, 0.501, 0.502)
[export_mesh] examples/output/sample_scan_ready.glb (360,752 bytes)Note the step after decimation: quadric collapse can leave a fold-over, so the client inspects the result and repairs once more before exporting — the agent gets numbers, not "done", precisely so it can make that call. With Claude Desktop the same run is one sentence: "Prepare examples/sample_scan.obj for a real-time scene with a 20k-face budget and explain what you changed."
Architecture
Claude Desktop / Claude Code
│ MCP (stdio, JSON-RPC)
▼
src/mesh_prep_mcp/server.py tools · resource · prompt (mcp SDK, 1.x and 2.x)
│
src/mesh_prep_mcp/ops.py load / inspect / repair / decimate / scale / export (trimesh, fast-simplification)
│
cpp/ meshstats C++17: bounds, area, signed volume, degenerate faces,
└─ bindings.cpp boundary & non-manifold edges, duplicate vertices (pybind11)The C++ backend is optional: if the extension is not built, ops.inspect falls back to a NumPy implementation and reports backend: "python". The C++ library has no Python dependency and its own tests (ctest).
Quick start
git clone https://github.com/Horuspokus/mesh-prep-mcp && cd mesh-prep-mcp
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
# C++ core + pybind11 module (optional but recommended)
cmake -S cpp -B build -DCMAKE_BUILD_TYPE=Release
cmake --build build
ctest --test-dir build --output-on-failure
pytest -q # Python tests
python scripts/make_sample_mesh.py && python scripts/demo_client.pyIf
import mesh_prep_mcpfails after the editable install (seen once on macOS with Python 3.14 in an iCloud-synced folder), install it non-editable instead:python -m pip install --force-reinstall --no-deps .— and re-run that after editing files undersrc/.
Claude Desktop
Copy examples/claude_desktop_config.json into your claude_desktop_config.json and replace the two absolute paths. MESH_PREP_ROOT sandboxes file access to one directory (recommended).
Claude Code
claude mcp add mesh-prep -e MESH_PREP_ROOT=$PWD/examples -- $PWD/.venv/bin/mesh-prep-mcpDesign notes
Immutable results. Operators never mutate a registered mesh; they add a new one with its provenance (
history). Cheap, and it makes "compare budgets A and B" or "go back to the repaired version" trivial for the agent.Numbers, not adjectives. Every tool returns measured before/after values (face count, surface-area drift, watertightness) so the agent's explanation to the user is grounded.
Issue → operator mapping.
inspect_meshdoes the triage once, in code; the agent only has to follow the recommendation or argue with it.Safety.
MESH_PREP_ROOTrejects paths outside one directory; exports never overwrite the input by default naming.C++ where it pays. The statistics pass is the one thing that runs on every step and on every mesh size, so it lives in C++ with the GIL released; everything else stays in Python for readability.
Roadmap
IFC input through IfcOpenShell (element-level preparation, properties kept as metadata)
glTF LOD chains (
decimate_chain(budgets=[200k, 50k, 10k]))Material / texture checks (missing UVs, oversized textures)
Scene assembly: place several prepared assets into one glTF scene
Streamable-HTTP transport for use behind a web app
License
MIT — Gökhan Dönmez, 2026.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
6 3D/CAD MCP tools: STL repair, OBJ/GLB/SVG conversion, slicing, G-code M600, SVG optimize.
Parametric 3D CAD for AI agents: build print-ready parts, check them, export STL, 3MF or STEP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read, inspect, and manipulate OpenUSD 3D scenes, including scene graph traversal, property querying, mesh export, and variant switching.10MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to create and manipulate 3D models using OpenSCAD through MCP tools for code-based modeling, preview, and export.1MIT
- FlicenseNot gradedqualityDmaintenanceConverts GeoJSON geometries into 3D triangulated meshes using a local LLM (Ollama), exposing an MCP tool for mesh generation.-
- AlicenseAqualityCmaintenanceEnables AI agents and MCP clients to perform 3D asset creation and verification: exact b-rep CAD, GLB validation with embedded certificates, mesh inspection, and physics scenes, with most tools running without Blender.3648 npmMIT