What is mcp-printable AGENTS.md?

Project instructions for Printable, an MCP server for AI-driven 3D modeling designed around FDM printing. They describe its Blender and OpenSCAD tools, required setup, and rules for agents working with the project.

They are for developing or operating Printable with an AI coding agent, including its Blender and OpenSCAD integrations.

They tell coding agents what the project provides, which software it needs, and how to handle image-based checks and modeling operations correctly.

How AaronGoldsmith/mcp-printable configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to AaronGoldsmith/mcp-printable. 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/AaronGoldsmith/mcp-printable/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/AaronGoldsmith/mcp-printable

Made for: Codex, OpenCode.

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/aarongoldsmith/mcp-printable/agents-md/github.svg)](https://agentmods.dev/instructions/aarongoldsmith/mcp-printable/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/aarongoldsmith/mcp-printable/agents-md"><img src="https://agentmods.dev/badge/instructions/aarongoldsmith/mcp-printable/agents-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/aarongoldsmith/mcp-printable/agents-md"><img src="https://agentmods.dev/badge/instructions/aarongoldsmith/mcp-printable/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,420 This file is loaded in full into every session.

When invoked 1,420 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	$0.01420	$0.01420
Opus 5.5	$0.00568	$0.00568
Sonnet 5.5	$0.00284	$0.00284
Haiku 4.5	$0.00142	$0.00142

Measured 2mo ago against content hash db32d62edb58, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-printable 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 2mo 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cross-agent instructions for working with Printable — an MCP server for AI-driven 3D modeling, optimized for FDM-printable geometry.

This file is the entry point for any AI coding agent (Codex, Cursor, Goose, Sourcegraph Amp, JetBrains AI, etc.). Claude Code reads it too, plus the project-specific CLAUDE.md if present.

For human-facing setup and overview, see README.md.

What this project ships

An MCP server (server.py) exposing 30 tools across two backends:
- Blender (blender_*, 25 tools) — TCP to a bundled Blender addon. Requires Blender 3.6+ + addon enabled.
- OpenSCAD (scad_*, 5 tools) — shells out to the openscad CLI. Requires OpenSCAD installed.
Domain-knowledge MCP resources under printable://… URIs (5 of them).
Always-on rules baked into the MCP server's instructions field — every connecting agent sees them automatically on initialize.

Required: image-capable model

Many tools (blender_render_*, blender_cross_section*, blender_get_screenshot, scad_render_views, scad_cross_section) return base64 PNGs that the model is expected to look at — that's how the design loop catches shape-level mistakes the geometry math doesn't. If you're a text-only model, you'll receive the images but be unable to interpret them; treat that as a hard limitation and tell the user up front rather than continuing without visual feedback.

Always-on rules

These are also embedded in the MCP instructions field, but if your agent doesn't surface that, here they are directly:

Blender

Start every modeling task with blender_clear_scene — it auto-sets units to mm. Building at the default 1m scale produces zero-volume meshes that pass watertight checks but are useless.
Use blender_boolean for boolean operations. Never use bpy.ops.object.join() (creates internal faces) or raw bpy boolean modifiers in execute_code (failures are silent).
1–3 operations per blender_execute_code, then blender_validate(checks=['HEALTH']) to verify (watertight? face count sane? connected_components == 1?).
Renders show silhouettes only — use blender_cross_section_gallery to verify internal geometry truth.
For any joint/hinge, you must call blender_check_clearance_sweep before export.
Run blender_validate(checks=['ALL']) on every part before blender_export_stl.

Read the full file on GitHub · 95 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.

2mo ago First seen · 95 lines · 1,420 tokens per session scan A db32d62edb58

Subscribe to this mod's changes

mcp-printable AGENTS.md is an instructions file published in the GitHub repository AaronGoldsmith/mcp-printable (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,420 tokens to every session, about $0.0057 per session on Opus 5.5. 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.

Design and UX

mcp-printable AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-printable AGENTS.mdAaronGoldsmith/mcp-printable	Instructions file	3	4mo ago	MIT	A	1,420	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-printable: Instructions file for Codex