OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Solidworks Automation Skill

SolidWorks Automation Skill is a Python-based Skill and MCP toolkit that lets compatible AI agents invoke real desktop CAD software through natural-language tasks. Its execution layer routes work to CAD backends and records traces, artifacts and evidence, with verification intended to check task outcomes rather than treating a successful tool call as proof of completion.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Solidworks Automation Skill — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an agent workflow needs to operate real desktop CAD software and the required task is covered by the project's capability matrix. Review the status of the specific capability and plan for human review where it is marked pilot.

Who it is for

  • Users of compatible agent clients who want to request CAD work in natural language.
  • CAD automation developers integrating agent workflows through MCP.
  • Teams that need execution traces and outcome review in CAD tasks.

Documented uses

  • Invoke documented CAD modeling, assembly, drawing and export workflows from an agent.
  • Track task execution and collect artifacts or evidence for review.
  • Check CAD capability status before selecting a workflow.
  • Use an OCCT/OCP route for certain open-format tasks where SolidWorks is not installed.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. It documents a Windows desktop target and Python 3.10+.

  • The project offers three distinct entry points: Skill, MCP and CAD Studio; select the one that matches the agent client and whether a GUI is needed.
  • Native SLDPRT, SLDASM and SLDDRW outputs require a SolidWorks environment; some open-format outputs are described as available through OCCT/OCP without SolidWorks.
  • Capabilities carry different statuses, including verified, stable, pilot and blocked; consult the capability matrix for the intended operation.
  • The stated deterministic reliability benchmark is not presented as a production SLA or real-user success rate.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the SolidWorks Automation Skill with an agent

Add the repository’s Skill entry point to an agent workflow for natural-language SolidWorks tasks.

Before you start

  • An agent client that supports importing skills; the README names Codex, Claude, and Cursor as agent examples.
  • Use a supported Skill installation option.

Steps

  1. Choose the Skill entry point; the three entry points are alternatives and need not be started together.

  2. Install with the command below or, for Claude, claude skill add https://github.com/wzyn20051216/solidworks-automation-skill.

    Documented command
    npx github:wzyn20051216/solidworks-automation-skill

  3. For environment diagnosis after installation, use the command below.

    Documented command
    python scripts/cad_doctor.py

Expected outcome

The Skill entry point is installed for agent-driven SolidWorks automation; the repository also provides an environment-diagnosis script.

Guide limitations

  • The README identifies native SolidWorks operations as targeting SolidWorks 2026; native SLDPRT, SLDASM, and SLDDRW require a licensed SolidWorks environment.
  • Tool-call success is not treated as task success; tasks requiring review go through result verification before delivery.
Documentation 1 ↗
Source-based practical guide

Set up the MCP entry point with Codex

Add the repository’s MCP toolkit to a Codex workflow.

Before you start

  • PowerShell, as shown for the MCP setup commands.
  • Codex as the MCP client.

Steps

  1. Choose MCP as the entry point; the README says Skill, MCP, and CAD Studio are alternatives.

  2. Install the Smithery CLI with the command below.

    Documented command
    npm install -g @smithery/cli

  3. Add the project with smithery mcp add wzyn20051216/solidworks-automation-skill --client codex --config '{}'.

  4. For environment diagnosis after installation, use the command below.

    Documented command
    python scripts/cad_doctor.py

Expected outcome

The project is added as an MCP entry point for Codex, with environment diagnosis available through the repository’s script.

Guide limitations

  • The README identifies native SolidWorks operations as targeting SolidWorks 2026; native SLDPRT, SLDASM, and SLDDRW require a licensed SolidWorks environment.
  • Tool-call success is not treated as task success; tasks requiring review go through result verification before delivery.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
wzyn20051216/solidworks-automation-skill · Official homepage title · retained in its source language
How we review sourcesSuggest a correction