Model parametric 3D CAD parts with Claude Code via the SolidCraft MCP server
SolidCraft is an open-source parametric 3D CAD application written in Rust that includes an MCP server, so AI agents can model, measure and screenshot parts. The README highlights SELENE, a scientific rover built entirely through that server.
The problem
Parametric CAD is usually driven by hand through a GUI, which makes it hard for AI agents to build or edit editable models. Scripted automation needs a command interface that mirrors what the UI does and lets the agent check its work.
How they did it
- Install SolidCraft from the desktop installers, a package manager, or use the web version.
- Register the MCP server with Claude Code using the command shown in the README.
- Optionally start the desktop app with a control port and connect the MCP server to it to watch the agent work.
- Let the agent call tools such as execute, batch, measure, screenshot and export to build and check the model.
- Alternatively, write JSON command scripts and run them with the headless CLI.
From the official docs
claude mcp add solidcraft -- solidcraft-cli mcpResults
- SELENE, a scientific rover by @0xlillith, was built entirely through the MCP server and consists of 3,323 editable timeline steps that rebuild with no errors (as stated in the SolidCraft README).
- According to the README, 75 of 76 public reference parts match their analytic or FreeCAD-computed volume, area, centre of mass and bounding box; the README notes this does not prove full equivalence.
As reported by the source (SolidCraft GitHub README); AgentGid did not measure these figures.
This suits solo makers or small hardware teams who already know parametric CAD and are comfortable with terminal tools and MCP setup. Treat the headline numbers with care: both come from the SolidCraft README, and it says 75 of 76 matching parts doesn't prove full equivalence, so keep measuring your own output. Claude Code needs a paid plan ($20/mo); Pi (Free (OSS)) is a cheaper option, with model costs extra.
The agent used here
Similar use cases
Make continuous-take product launch films with the onetake agent skill
The onetake repository is a Claude Agent Skill that lets a coding agent produce product launch films, teasers and feature demos as one continuous camera take. An automated oracle …
The README lists ten example films across concept ads, launch films, app promos and feature demos, each with a finished film and a breakdown document…
Produce AI short dramas from a novel with shuohao-skills in Claude Code
An individual developer published an open-source set of agent skills that take a novel through to shoot-ready AI short-drama material: outline, character bible, art bible, screenp…
As reported by the repository author, each pipeline skill has script-checked quality gates: 14 for the outline, 10 for the art bible, 10 for the scre…
Mod almost any PC game with Claude Code and the universal-modder plugin
An open-source GitHub project packages skills, a command-line tool, a shared knowledge base and the fal MCP server so AI coding agents such as Claude Code can mod PC games the use…
The repository ships three worked examples: a Terraria tModLoader weapon and boss pack with sprites made through fal, an Age of Empires II DE civiliz…
Guides
Claude Code Deploys: 6 Open-Source Repos for a Containment System, Checked
A viral post says GitHub Actions, Argo CD, Argo Rollouts, Prometheus, Sentry and OpenTelemetry turn Claude Code deploys into a containment system. We checked each: role, license, what needs Kubernetes, and what Claude Code's own permissions add.
How to Cut Token Usage in Claude Code and Cursor (2026)
Practical ways to spend fewer tokens with Claude Code and Cursor: measure first, keep context small, match the model to the task, filter what the agent reads, and the open-source tools that help.
Sonnet Builds, Opus Reviews, Haiku Reads: Does the Claude Code Advisor Save Money?
A viral post says running Sonnet, Haiku and Opus together in Claude Code gives better code for fewer tokens. We checked it against Anthropic's docs and prices: when the advisor pays off, when it costs more, and why a ready project kit matters more than the model mix.
JEV for Claude Code: A Second Opinion on Every Command, Checked
A viral post says jev-axi screens every command your Claude Code agent runs for a fraction of a cent. We read the repo, TypeSafe's docs and privacy policy: what runs locally, what is sent, how it fails, and how it compares with auto mode.