What is maya-mcp CLAUDE.md?

A persistent instruction document for working with maya-mcp, an MCP server that connects an AI agent to Autodesk Maya, a 3D modelling and animation program. It explains the server's architecture, tools, configuration, and workflows.

Guiding scene changes, modelling, animation, file import and export, rendering, documentation search, and Vision3D-related actions through maya-mcp.

It gives the agent the project context needed to use Maya controls and Vision3D integration consistently across sessions. It also records how session-only Vision3D URLs are handled.

How abrahamADSK/maya-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to abrahamADSK/maya-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/abrahamADSK/maya-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/abrahamADSK/maya-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/abrahamadsk/maya-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/abrahamadsk/maya-mcp/claude-md)

Your own site

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

Per session 8,269 This file is loaded in full into every session.

When invoked 8,269 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	$0.08269	$0.08269
Opus 5.5	$0.03308	$0.03308
Sonnet 5.5	$0.01654	$0.01654
Haiku 4.5	$0.00827	$0.00827

Measured 1mo ago against content hash 2b77d877c2d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maya-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 1mo 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 · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maya-mcp — Critical Context for Claude

Last updated: 2026-04-12 — per-session Vision3D URL is now fully runtime-only: Claude asks the user for the URL on the first Vision3D call, caches it in memory for the rest of the session, and forgets it on MCP restart. No config file field, no pool, no persisted URLs anywhere. This document persists across Claude Code sessions. Consult here to understand the architecture, configuration, and workflows of maya-mcp.

1. Architecture

maya-mcp is a production-grade MCP (Model Context Protocol) server based on FastMCP with 17 MCP tools organized in three layers (plus the optional WorldLabs environment addon):

Maya Control (10 direct tools + 1 dispatch tool with 13 actions) — Scene manipulation, modeling, animation, I/O, rendering
- Communicates with Maya via TCP Command Port (default port 8100; moved from the historical 7001 because that port is held by Flame's S+W services on hosts with Autodesk Flame installed)
- Uses maya_bridge.py (socket bridge) to execute MEL/Python commands
- All operations use undo chunks for safe rollback
Vision3D Integration (7 actions behind the maya_vision3d dispatch tool) — Optional addon for AI-powered 3D generation via Vision3D
- Communicates via HTTP REST API with Vision3D (port 8000)
- Supports image-to-3D, text-to-3D, and texture painting
- Non-blocking async pattern: submit → poll → download
- Fully per-session URL: the first call that needs a GPU returns vision3d_url_required. The LLM asks the user for the Vision3D URL in the chat, the user types it, the LLM calls select_server with that URL, and it is cached in memory for the rest of the session. Nothing is written to disk — no config field, no pool, no whitelist. Restarting the MCP server clears the selection.
- GPU_API_URL env var is honored as a suggested default the LLM can surface in the prompt, but it is never auto-selected. The user still has to confirm it explicitly via select_server.
- Not required — maya-mcp works fully without Vision3D

Read the full file on GitHub · 488 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.

1mo ago Changed · +16 lines · +354 tokens per session 2b77d877c2d4
2mo ago First seen · 472 lines · 7,915 tokens per session scan A 82bd05b7c45c

Subscribe to this mod's changes

maya-mcp CLAUDE.md is an instructions file published in the GitHub repository abrahamADSK/maya-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 8,269 tokens to every session, about $0.0331 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.

Creative and media Data and AI RAG and vectors

maya-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
maya-mcp CLAUDE.mdabrahamADSK/maya-mcp	Instructions file	3	1mo ago	MIT	A	8,269	Claude Code
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

maya-mcp: Instructions file for Claude Code