What is solidworks-mcp CLAUDE.md?

Project instructions for a SolidWorks 2022 MCP server, which lets an AI agent control SolidWorks, a computer-aided design program. They define the required process for turning part requests into verified models.

Use them when creating mechanical parts from descriptions or images, running complete SolidWorks macros, troubleshooting validation failures, capturing result screenshots, and recording reusable fixes.

They give the agent a repeatable modeling process and quality checks, including finding the right SolidWorks session, looking up API details, linting macros, and checking the result.

How ladla90077-web/solidworks-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ladla90077-web/solidworks-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ladla90077-web/solidworks-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ladla90077-web/solidworks-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ladla90077-web/solidworks-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ladla90077-web/solidworks-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ladla90077-web/solidworks-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ladla90077-web/solidworks-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ladla90077-web/solidworks-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ladla90077-web/solidworks-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 552 This file is loaded in full into every session.

When invoked 552 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00552	$0.00552
Opus 5	$0.00276	$0.00276
Sonnet 5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 9d ago against content hash 886ec6fe3b7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

solidworks-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SolidWorks MCP — session rules

This repo is a SolidWorks 2022 MCP server (src/sw_mcp). When the user describes a part, shows a picture, or asks to make anything mechanical, start building immediately — do not ask clarifying questions first.

Automatic workflow (every part request)

prepare_modeling_context(request) — auto-detects/selects the running SolidWorks session. Only stop if it reports start_solidworks (ask the user to open SolidWorks) or select_session (ask which PID).
api_map(...) / docs_lookup_batch(...) — fetch ALL needed signatures, accessor chains and enum tables in one or two calls. Never one lookup per method; never read the CHM cache or big JSON resources directly.
Generate ONE complete macro and run it with run_and_verify. It statically lints first (static_check failures come back in milliseconds — fix those before any rerun). Iterate on the verdict until success: true.
capture_screenshot and show the user the result.
If a fix wasn't already in suggested_fixes, record it with learn_rule.

Pick sensible engineering defaults for unstated dimensions and say what you chose — do not block on questions.

Quality bar (non-negotiable)

Never deliver a bare block or cylinder. Every part gets:

Edge finishing on ALL edges: fillets on external/cosmetic edges, chamfers on hole entries and lead-ins (FeatureFillet3, InsertFeatureChamfer) as a finishing pass before the final rebuild.
Real design intent: Hole Wizard holes (not plain cuts), bolt circles, draft on molded bosses, sane wall thicknesses.
Use get_design_guidance recipes for the archetype (bearing, plate, manifold, bracket) so proportions are engineering-informed.
Verify visually with a screenshot; if any edge is still sharp, add the missing fillet/chamfer and rerun.

Repo notes

Docs are retrieval-based: CHM index + FTS5 (local_docs.py) and keyed Cosmon databases (cosmon_db.py, 0.18s lazy load). Web rendering only on explicit prefer='web'.
Keep tool payloads compact — the latency budget is round trips × context size, not server compute.
Tests: python -m pytest tests -q. COM tests skip without a live SolidWorks; pure tests must never depend on the sw fixture.

Read the full file on GitHub · 47 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 47 lines · 552 tokens per session scan A 886ec6fe3b7f

Subscribe to this mod's changes

solidworks-mcp CLAUDE.md is an instructions file published in the GitHub repository ladla90077-web/solidworks-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 552 tokens to every session, about $0.0028 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

solidworks-mcp: Instructions file for Claude Code