Skip to main content

mesh2cad

ci emirmrkaljevic/mesh2cad MCP server

Turn 3D meshes (STL/OBJ/PLY) into real, editable CAD (STEP) — fitted planes, cylinders, spheres, and cones instead of triangle soup. CLI + MCP server for AI agents. MIT, pure Python on top of OpenCascade.

demo

before/after

Left: 21k-triangle mesh with 0.1 mm noise. Right: the STEP mesh2cad writes — 10 planes + 2 cylinders, max deviation 0.05 mm from the true part.

Install

pip install mesh2cad              # CLI + STEP
pip install "mesh2cad[mcp]"       # + MCP server
pip install "mesh2cad[cadquery]"  # + run/verify generated CadQuery scripts

Use

mesh2cad convert part.stl -o part.step --tol 0.1 --report report.md
mesh2cad report part.stl --json

--tol ≈ the noise / accuracy of your mesh in model units (default 0.1 % of the bounding-box diagonal).

Output: STEP + fidelity report — method (exact / faceted-hybrid / faceted), face types, solid validity, two-sided Hausdorff / RMS deviation, volume error, % area per surface type.

Editable parametric CadQuery script

For simple prismatic parts mesh2cad can also write a CadQuery Python script where every dimension is a named parameter, so you change a number and re-run instead of editing B-rep faces:

mesh2cad convert bracket.stl --cadquery bracket.py   # add -o bracket.step to also write STEP
python bracket.py                                    # -> bracket.step
# --- parameters ---
base_x           = 40.0  # base length (X)
base_y           = 30.0  # base width (Y)
base_t           = 6.0  # base thickness (Z)
...
hole_1_d         = 6.0  # diameter
hole_1_x         = 0.0
hole_1_y         = 0.0
hole_1_csk_d     = 12.0  # countersink diameter
hole_1_csk_angle = 90.0  # countersink angle

Make the hole 2 mm bigger: set hole_1_d = 8.0 and run it again.

Supported: Z-up box/plate base, rectangular pads on the top face, vertical holes (through, blind, countersunk) and vertical bosses (straight, drafted, chamfered). Values are rounded to clean numbers (5.997 → 6.0) when that stays within --tol. Before writing, the script is executed and compared with the mesh (needs cadquery installed); if the part is outside this vocabulary or the script deviates, nothing is written and the command exits with code 2 and the reason. Use STEP output for everything else.

MCP server (Claude Desktop, Cursor, …)

{ "mcpServers": { "mesh2cad": { "command": "mesh2cad", "args": ["mcp"] } } }

Tools: convert(input_path, output_path?, tol?, cylinders?, spheres?, cones?), analyze(input_path, tol?, cylinders?, spheres?, cones?), report(input_path, tol?, cylinders?, spheres?, cones?), to_cadquery(input_path, output_path?, tol?) (returns the parameters and measured deviation). spheres and cones default on.

Listed on Glama and the TensorBlock MCP catalog.

How it works

  1. Load + clean mesh (trimesh); Taubin-smoothed copy for normals.
  2. Region growing into planes; strip chains and leftovers are fitted as cylinders, spheres, or cones (normal-ray / algebraic / constant-normal-angle fits, robust nonlinear refinement). A coaxial cylinder + cone component (countersink, chamfered pin) is split by normal-to-axis angle first. Small noisy patches that tile a sphere are merged into one spherical region. Split/redundant regions are merged and absorbed.
  3. Exact B-rep (OCP / OpenCascade): plane polygons from triple-plane intersections, circles from plane ∩ cylinder and plane ∩ sphere, plane ∩ cone, cylindrical faces, spherical caps and zones, conical frustums, sewn into a solid and validated.
  4. Fallbacks: hybrid faceted solid (vertices snapped to fitted surfaces, coplanar triangles merged), then raw faceted solid.
  5. Fidelity report against the input mesh.

Self-test benchmark

Ground-truth cadquery parts → tessellated + subdivided (≤ 2 mm edges) → Gaussian vertex noise → mesh2cad → compared with the truth. 3 seeds, worst case shown (python benchmarks/run.py); the same cases run in CI.

part noise σ (mm) exact faces (plane/cyl[/sph[/cone]]) Hausdorff (mm) RMS (mm) vol err % time s
cube 0.0 3/3 6/0 0.000 0.000 0.00 0.6
cube 0.05 3/3 6/0 0.019 0.006 0.07 0.6
cube 0.2 3/3 6/0 0.075 0.026 0.34 0.6
l_bracket 0.0 3/3 8/0 0.000 0.000 0.00 0.9
l_bracket 0.05 3/3 8/0 0.040 0.006 0.03 0.9
l_bracket 0.2 3/3 8/0 0.216 0.026 0.15 0.8
stepped_block 0.0 3/3 11/0 0.000 0.000 0.00 2.0
stepped_block 0.05 3/3 11/0 0.032 0.006 0.02 2.0
stepped_block 0.2 3/3 11/0 0.136 0.022 0.07 1.9
plate_with_hole 0.0 3/3 6/1 0.015 0.002 0.00 1.7
plate_with_hole 0.05 3/3 6/1 0.028 0.006 0.05 1.9
plate_with_hole 0.2 3/3 6/1 0.078 0.023 0.18 1.6
boss 0.0 3/3 7/1 0.027 0.006 0.01 1.8
boss 0.05 3/3 7/1 0.033 0.007 0.03 2.0
boss 0.2 3/3 7/1 0.090 0.017 0.07 3.3
ribbed_plate 0.0 3/3 10/2 0.013 0.002 0.00 2.2
ribbed_plate 0.05 3/3 10/2 0.028 0.005 0.03 2.1
ribbed_plate 0.2 3/3 10/2 0.108 0.020 0.12 2.1
spherical_dome 0.0 3/3 6/0/1 0.065 0.007 0.04 1.6
spherical_dome 0.05 3/3 6/0/1 0.067 0.008 0.06 1.6
spherical_dome 0.2 3/3 6/0/1 0.241 0.028 0.25 1.7
spherical_pocket 0.0 3/3 6/0/1 0.046 0.004 0.02 1.9
spherical_pocket 0.05 3/3 6/0/1 0.057 0.005 0.03 1.9
spherical_pocket 0.2 3/3 6/0/1 0.075 0.015 0.13 1.8
countersunk_plate 0.0 3/3 6/1/0/1 0.039 0.003 0.01 2.0
countersunk_plate 0.05 3/3 6/1/0/1 0.055 0.009 0.07 2.0
countersunk_plate 0.2 1/3 16342/0, 6/1/0/1 0.590 0.049 0.54 21.6
tapered_boss 0.0 3/3 7/0/0/1 0.086 0.011 0.05 1.6
tapered_boss 0.05 3/3 7/0/0/1 0.095 0.012 0.05 1.6
tapered_boss 0.2 3/3 7/0/0/1 0.123 0.025 0.22 1.5
chamfered_boss 0.0 3/3 7/1/0/1 0.053 0.005 0.02 2.4
chamfered_boss 0.05 3/3 7/1/0/1 0.096 0.012 0.08 2.3
chamfered_boss 0.2 3/3 7/1/0/1 0.511 0.059 0.49 2.1

"exact" = valid B-rep with the true face count. All rows are the worst of 3 seeds from python benchmarks/run.py. A row below 3/3 includes the faceted fallback (face count = triangles); that fallback is a valid solid. The 90° countersink (Ø6 hole, Ø12 head, 3 mm deep) at 0.2 mm noise is exact on 1 of 3 seeds. CI checks the cases that are exact, plus one fallback that must stay a valid solid.

Limits (v0.4.2)

Planes, cylinders, spheres, and cones. Cylinders must end on planes perpendicular to their axis (through-holes, bosses, pins). Spheres are exact when each boundary loop is a single plane ∩ sphere circle (domes, spherical bosses, spherical pockets, and zones between two parallel planes). A sphere that runs into an edge or a cylinder falls back to the hybrid solid — vertices are still snapped onto the fitted sphere, but the face stays faceted. Cones are exact when they run between two planes perpendicular to their axis: countersinks, chamfered holes and bosses, drafted/tapered bosses. Cones may also meet a coaxial cylinder (countersunk hole, chamfered pin). A cone that ends in its apex falls back to the hybrid solid. Countersinks and narrow chamfers are exact through about 0.05 mm of noise; a 2 mm chamfer and a wide drafted wall stay exact at 0.2 mm. The countersunk plate's 90° countersink (Ø6 hole, Ø12 head, 3 mm deep) at 0.2 mm noise is exact on one of three seeds. On the other two the conical band and the hole wall meet at a single vertex, so those seeds fall back to a valid faceted solid. No fillets or free-form yet.

Development

pip install -e .[dev]
pytest
python docs/make_demo.py   # regenerate images (needs matplotlib, pillow)

License: MIT

Metadata

Release files for mesh2cad 0.4.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mesh2cad 0.4.2
File Size Uploaded Provenance
mesh2cad-0.4.2.tar.gz 778.8 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for mesh2cad 0.4.2
File Interpreter ABI Platform
mesh2cad-0.4.2-py3-none-any.whl Python 3 none any Details

Total release size: 821.3 kB

Release files / mesh2cad-0.4.2.tar.gz

Download URL mesh2cad-0.4.2.tar.gz
Size 778.8 kB
Tags Source
SHA-256 checksum
How to use checksums
bced12b168df6b36f1eef2ef1ae23601acea86e2c30917af57ebf160cc089ffe
BLAKE2b-256 checksum
How to use checksums
30fbbce1f109c297d1e47b1899e4c8616992a23e416b133bc76039c42fa476b6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 16, 2026.

Transparency log

Release files / mesh2cad-0.4.2-py3-none-any.whl

Download URL mesh2cad-0.4.2-py3-none-any.whl
Size 42.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5ea1785e0540a744cba80476aac94b9e9dedd661d4e58737753b002a9e7d9513
BLAKE2b-256 checksum
How to use checksums
bd409f0065a0b0bbac63f0ba2c47f61f0e26128d22e1a26380c1065019a68fa2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 16, 2026.

Transparency log

Security for mesh2cad 0.4.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for mesh2cad-0.4.2.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 16, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page