agentmods.dev

mcp AGENTS.md

Repository instructions for developing and running KittyCAD's MCP server, including setup, tests, formatting, linting, type checks, and integration commands.

In plain words
What is it for?
Use them when installing dependencies, starting the server, running local or live tests, checking code quality, or connecting the server to Claude Desktop.
Why use it?
They give contributors the exact commands needed to prepare the environment and check that changes work correctly.

Instructions file for CodexOpenCode

9 3d ago A scan 2,087 tokens original MIT
View the source file KittyCAD/mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/kittycad/mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/KittyCAD/mcp

Made for: Codex, OpenCode.

Per session 2,087 This file is loaded in full into every session.
When invoked 2,087 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.02087 $0.02087
Opus 5 $0.01043 $0.01043
Sonnet 5 $0.00417 $0.00417
Haiku 4.5 $0.00209 $0.00209

Measured 2d ago against content hash d3e1f3bb8b30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp AGENTS.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 2d 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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Commands

Before committing any code, ensure all tests pass, formatting is good, linting is clean, and type checks succeed.

Environment Setup

  • uv venv - Create virtual environment
  • uv pip install -e . - Install package in development mode
  • export ZOO_API_TOKEN="your_api_key_here" - Set required Zoo API token

Running the Server

  • uv run -m zoo_mcp - Start the MCP server locally
  • uv run mcp run src/zoo_mcp/server.py - Alternative method using mcp package
  • uv run mcp dev src/zoo_mcp/server.py - Run server with MCP Inspector for testing

Testing and Quality

  • uv run pytest -n auto - Run all tests (includes live tests that hit zoo.dev)
  • uv run pytest -n auto -m "not live" - Run all tests except those that hit live external services (use this when offline or to avoid network calls)
  • uv run pytest tests/test_server.py - Run specific test file
  • uv run ruff check - Run linter
  • uv run ruff format - Format code
  • uv run ty check - Type check source code

Integration Commands

  • uv run mcp install src/zoo_mcp/server.py - Install server for Claude Desktop integration

Architecture

This is a Model Context Protocol (MCP) server that exposes Zoo CAD and KCL utility tools to AI assistants. The architecture consists of:

Core Components

  • src/zoo_mcp/server.py - FastMCP server that defines the MCP interface and registers all @mcp.tool() entry points (KCL execution, snapshots, physical-property calculations, KCL docs/samples lookup, org datasets, etc.). Owns the lifespan hook that lazily populates the KCL docs/samples indexes.
  • src/zoo_mcp/zoo_tools.py - Implementations of the CAD-oriented tools that talk to Zoo's KittyCAD API (executing/exporting KCL, file conversion, snapshots, physical properties, sketch constraint status, lint-and-fix, org dataset listing/semantic search, etc.).
  • src/zoo_mcp/kcl_docs.py - Fetches and indexes KCL documentation from zoo.dev (via the sitemap, with Accept: text/markdown) and exposes list/search/get helpers backed by a lazily-initialized index.
  • src/zoo_mcp/kcl_samples.py - Fetches and indexes KCL samples from zoo.dev/aquarium and exposes list/search/get helpers; per-sample file contents are parsed from the per-sample markdown pages on demand.
  • src/zoo_mcp/utils/data_retrieval_utils.py - Shared helpers for fetching zoo.dev pages safely (path validation, redirect-blocking fetches, markdown excerpting) used by kcl_docs.py and kcl_samples.py.
  • src/zoo_mcp/utils/image_utils.py - Image utilities used by the snapshot tool (encoding to MCP ImageContent, saving to disk, tiling up to four views into a collage, resizing).
  • src/zoo_mcp/__init__.py - Package initialization: configures logging and the shared TLS context, and defines ZooMCPException and ZooMCPTimeoutError.
  • src/zoo_mcp/__main__.py - python -m zoo_mcp entry point; delegates to server.main.

Read the full file on GitHub · 82 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.

  1. 2d ago First seen · 82 lines · 2,087 tokens per session scan A d3e1f3bb8b30

Subscribe to this mod's changes

mcp AGENTS.md is an instructions file published in the GitHub repository KittyCAD/mcp (9 stars, last pushed 3d ago), licensed MIT. It adds 2,087 tokens to every session, about $0.0104 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js 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