Borrowing it
Nothing to install: this file belongs to HarrierPigeon/Solidworks-MCP-Server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HarrierPigeon/Solidworks-MCP-Server/main/CLAUDE.mdgit clone --depth 1 https://github.com/HarrierPigeon/Solidworks-MCP-ServerWrote 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.
[](https://agentmods.dev/instructions/harrierpigeon/solidworks-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/harrierpigeon/solidworks-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/harrierpigeon/solidworks-mcp-server/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.
<a href="https://agentmods.dev/instructions/harrierpigeon/solidworks-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/harrierpigeon/solidworks-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.06557 | $0.06557 |
| Opus 5 | $0.03279 | $0.03279 |
| Sonnet 5 | $0.01311 | $0.01311 |
| Haiku 4.5 | $0.00656 | $0.00656 |
Grade A, and why
Solidworks-MCP-Server 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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
SolidWorks MCP Server bridges Claude AI with SolidWorks CAD via the Model Context Protocol (MCP), enabling natural language creation and manipulation of 3D CAD models. Requires Windows + SolidWorks installed.
Commands
# Install dependencies
pip install -r requirements.txt
# Or install as an editable package (exposes `solidworks` and `server` for import)
pip install -e .
# Run all tests (closes open docs first, then runs all categories)
python test.py
# Interactive CLI test picker — select tests by number, range, or category
python test.py --gui
# Run a single category
python test.py --category "Sketch Tools"
python test.py --category "Feature Tools"
python test.py --category "Integration"
# Run a single test by name
python test.py --test basic_cube
python test.py --test sketch_line
# List all available tests
python test.py --list
# Run the server directly (normally launched by an MCP client such as Claude Desktop)
python server.py
# Dev server with hot reload (requires watchdog)
python dev_server.py
# Close all open SolidWorks documents (standalone utility)
python clean.py
Claude Desktop Configuration
The server is registered in %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"solidworks": {
"command": "python",
"args": ["C:\\path\\to\\solidworks-mcp\\server.py"]
}
}
}
Architecture
server.py # MCP server: registers tools, routes calls via dispatch map
solidworks/
__init__.py # Package exports for all modules
connection.py # COM connection to SolidWorks, template discovery, part creation
state_tracker.py # Centralized state tracker: stable IDs for features, sketches, entities
state_query.py # MCP tools for querying tracked state (get_state, get_entity, get_sketch_entities)
sketching.py # 2D sketch tools, dimensioning, and constraints with spatial tracking
modeling.py # Core modeling (new_part, extrusion, cut-extrusion, mass_properties, list_features)
selection_helpers.py # Shared selection utilities (edge, face, plane, feature, axis)
features.py # Boss/Base features (revolve, sweep, loft, boundary boss)
cut_features.py # Cut features (cut revolve, cut sweep, cut loft, boundary cut)
applied_features.py # Applied features (fillet, chamfer, shell, draft, rib, wrap, intersect)
patterns.py # Patterns (linear pattern, circular pattern, mirror)
hole_features.py # Hole features (hole wizard, cosmetic thread)
reference_geometry.py # Reference geometry (ref plane, ref axis, ref point, coordinate system)
geometry_query.py # Geometry inspection (body info, faces, edges, face edges, vertices) with feature tagging
document_manager.py # Document lifecycle (save, open, activate, close, list, capture_views)
assembly.py # Assembly tools (new assembly, insert component, mates, interference, assembly queries)
configurations.py # Configurations (variants, per-config dims) and equations
feature_tree.py # Timeline as structured data, renaming, folders
com_utils.py # Shared late-bound COM helpers (com_prop)
test.py # Unified test suite with registry, CLI selector (--gui), category/test filters
clean.py # Close all open SolidWorks documents (standalone utility)
scripts/install.ps1 # End-user installer: installs uv, downloads latest release, sets up venv, patches Claude Desktop config
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 · 253 lines · 6,557 tokens per session scan A fdc227b03996
Solidworks-MCP-Server CLAUDE.md is an instructions file published in the GitHub repository HarrierPigeon/Solidworks-MCP-Server (11 stars, last pushed 26d ago), licensed MIT. It adds 6,557 tokens to every session, about $0.0328 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.
Other instructions, from other repositories
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.