MayaMCP: Instructions file for Claude Code

CLAUDE.md

MayaMCP CLAUDE.md is an instructions file for Claude Code from dcoes/MayaMCP. It costs 911 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that lets an AI client control Autodesk Maya, a 3D modelling and animation program, through Maya's command interface. They describe how the server and its Maya Python tools work.

In plain words
What is it for?
Use them when adding or changing Maya tools, checking the repository's conventions, or deciding where new tool code belongs.
Why use it?
They give coding agents the project's local rules and explain the unusual process for sending Python into Maya and reading results back.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is dcoes/MayaMCP's own configuration. It tells Claude Code how to work on MayaMCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MayaMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dcoes/MayaMCP. 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/dcoes/MayaMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dcoes/MayaMCP

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.

agentmods badge for MayaMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dcoes/mayamcp/claude-md/github.svg)](https://agentmods.dev/instructions/dcoes/mayamcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dcoes/mayamcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dcoes/mayamcp/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.

agentmods 80×15 button for MayaMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dcoes/mayamcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dcoes/mayamcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 911 This file is loaded in full into every session.
When invoked 911 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00911 $0.00911
Opus 5.5 $0.00364 $0.00364
Sonnet 5.5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured yesterday against content hash f609378d0c56, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MayaMCP 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 yesterday.

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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MayaMCP — project instructions

Fork of PatrickPalmer/MayaMCP, pushed to dcoes/MayaMCP (origin), upstream tracked separately (upstream). An MCP server that lets an AI client drive Autodesk Maya through Maya's Command Port.

This project's own working agreements win here, including where they disagree with anything in the workspace root CLAUDE.md or studio/.

What this actually is

Read README.md § Developer Notes before touching src/. The mechanism, briefly: tool code is plain Maya Python, sent over Maya's default Command Port — which only runs MEL — by wrapping the Python in a MEL call to the Python interpreter. Multi-line Python over that port can't return a result directly, so each tool call opens two connections: one to run the code, one to read back _mcp_maya_results. Everything sent is scoped under _mcp_maya_* to avoid colliding with whatever else lives in Maya's global namespace.

Adding a tool means adding a Maya-Python file under src/mayatools/. It does not require touching the MCP server itself or writing any MCP decorators/boilerplate — the server discovers tool signatures at startup. If a task looks like it needs server-side wiring, re-read the Developer Notes; it probably doesn't.

src/mayatools/thirdparty/ is for external scripts the user drops in — treat it as vendored, don't refactor its contents into the project's own style.

MEL — general conventions

MEL surfaces here even though this server's own tools are Python, because Maya's command port speaks MEL, and other Maya work in this workspace (rigging/pipeline scripts) is plain .mel. Keep these in mind whenever MEL is being written or debugged, not just in this repo:

  • Variables are typed and the type is part of the declaration: string $x;, int $i;, float $f[];. There is no implicit conversion between string and numeric the way there is in more forgiving scripting languages — a bare $x = 5 after string $x; is an error, not a coercion.
  • Global variables must be redeclared global in every scope that uses them, including inside procedures, with the exact same type — mismatched types on a redeclare fail silently in ways that are hard to trace.
  • Procedures declared in a .mel file are registered globally in Maya's session once the file is sourced, and persist until Maya restarts or the proc is manually deleted. Re-sourcing a file during iteration redefines the proc but stray old procs from earlier experiments can linger and shadow new work — when debugging "changes aren't taking effect," check for a stale global proc before assuming the file wasn't sourced.
  • Wrap scene-mutating operations in undoInfo -openChunk / -closeChunk. Without it, a multi-step script leaves the user several undos deep with no single "undo my script" action — the kind of thing that's invisible in testing and painful in real use.
  • String quoting inside eval() / command strings is the most common source of MEL bugs. Double-quoted strings inside a string being built for eval need careful escaping; prefer building commands with `...` (backquote/format) substitution or MEL's format command over manual string concatenation where practical.
  • select is stateful and additive by default (-add semantics unless -clear is used) — a proc that queries or operates on "the current selection" without first clearing/restoring it can leak selection state into whatever the user runs next in their own Maya session.

Read the full file on GitHub · 62 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. yesterday First seen · 62 lines · 911 tokens per session scan A f609378d0c56

Subscribe to this mod's changes

MayaMCP CLAUDE.md is an instructions file published in the GitHub repository dcoes/MayaMCP (1 stars, last pushed yesterday), licensed MIT. It adds 911 tokens to every session, about $0.0036 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 2026-11-16.

Related

MayaMCP CLAUDE.md compared with instructions from other repositories

MayaMCP CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
MayaMCP CLAUDE.mddcoes/MayaMCPInstructions file1yesterdayMITA911Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode