maya-mcp-server: Instructions file for Claude Code

CLAUDE.md

maya-mcp-server CLAUDE.md is an instructions file for Claude Code from chadrik/maya-mcp-server. It costs 2,243 tokens per session, scanned A, original, MIT.

Developer instructions for connecting multiple MCP clients to open Autodesk Maya sessions through dedicated network ports.

In plain words
What is it for?
Use them when developing, reconnecting, or testing the Maya MCP server and its command-port session tracking.
Why use it?
They explain how sessions and ports are assigned and include testing rules for avoiding stale or cached Maya modules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is chadrik/maya-mcp-server's own configuration. It tells Claude Code how to work on maya-mcp-server 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 maya-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chadrik/maya-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.

Copy the file
curl -O https://raw.githubusercontent.com/chadrik/maya-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chadrik/maya-mcp-server

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 maya-mcp-server CLAUDE.md

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

agentmods 80×15 button for maya-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chadrik/maya-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/chadrik/maya-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,243 This file is loaded in full into every session.
When invoked 2,243 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 $0.02243 $0.02243
Opus 5.5 $0.00897 $0.00897
Sonnet 5.5 $0.00449 $0.00449
Haiku 4.5 $0.00224 $0.00224

Measured 2mo ago against content hash 010e7606a1da, 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-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 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.

CLAUDE.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maya MCP Server - Developer Guide

⚠️ Critical Testing Rules

  1. Prefer testing with open Maya session - Use manual test scripts in project root
  2. Module updates - Always update maya_mcp module when reconnecting (module may be cached from previous sessions)

🏗️ Architecture Overview

Dedicated CommandPort Design

Two types of ports per Maya session:

  1. Configuration Port (e.g., 7001): One per Maya session (PID)

    • Used only for bootstrap and discovery
    • Clients connect temporarily to create dedicated ports
    • Outside communication port range
  2. Communication Ports (50000-60000): One per MCP client

    • Created during bootstrap via start_command_port()
    • Dedicated to single client for entire session
    • Automatically filtered during port scanning
Maya Session (PID 8453)
├── Configuration Port: 7001 (Python commandPort)
│   └── Used for bootstrap only - clients disconnect after setup
└── Communication Ports: 50000-60000 range
    ├── Port 50625 → MCP Client 1
    ├── Port 51234 → MCP Client 2
    └── Port 52891 → MCP Client 3

SessionManager Port Tracking

self._sessions: dict[str, MayaClient]          # "host:port" -> client (communication port)
self._config_to_session: dict[str, str]        # "host:port" -> session key (config → comm mapping)

Key insight: Don't need _probed_ports set - use _config_to_session to track which configuration ports we've already used to create sessions.

Port Constants

# src/maya_mcp_server/types.py
COMMUNICATION_PORT_MIN = 50000
COMMUNICATION_PORT_MAX = 60000

Filter these out when scanning for configuration ports in _scan_for_sessions().

🔧 Bootstrap Process

Critical Bootstrap Requirements

  1. Function return values: All helper functions in maya_mcp_helper.py MUST return strings (usually JSON)
    • If function returns None, _send_receive() hangs waiting for response
    • Example: start_command_port() returns json.dumps({"success": True, "port": port})

Read the full file on GitHub · 261 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. 2mo ago First seen · 261 lines · 2,243 tokens per session scan A 010e7606a1da

Subscribe to this mod's changes

maya-mcp-server CLAUDE.md is an instructions file published in the GitHub repository chadrik/maya-mcp-server (42 stars, last pushed 3mo ago), licensed MIT. It adds 2,243 tokens to every session, about $0.0090 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 2026-08-30.

Related

maya-mcp-server CLAUDE.md compared with instructions from other repositories

maya-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
maya-mcp-server CLAUDE.mdchadrik/maya-mcp-serverInstructions file423mo agoMITA2,243Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot