3dsmax-mcp

An MCP server that allows AI agents to inspect and manipulate Autodesk 3ds Max scenes via a FastMCP (Python/stdio) server bridged to 3ds Max through a native C++ Global Utility Plugin (named pipes) or, as a fallback, a MAXScript TCP listener on port 8765.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp 3dsmax autodesk automation scene-graph maxscript python named-pipes mcp-server
⚙ Agent Friendliness
55
/ 100
Can an agent use this?
🔒 Security
32
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
85
Documentation
75
Error Messages
0
Auth Simplicity
90
Rate Limits
10

🔒 Security

TLS Enforcement
30
Auth Strength
20
Scope Granularity
30
Dep. Hygiene
45
Secret Handling
40

Primary documented mitigation is MAXScript safe mode ON by default, blocking shell execution, external app launches, file deletion, Python.Execute, and file writing. Authentication/authorization is not documented for the MCP server, so local access control depends on network exposure (named pipe/TCP fallback) and the agent client’s connection context. Running arbitrary agent-driven scene changes and (optionally) disabling safe mode increases risk. No details provided about secrets handling, transport security for the TCP fallback, or dependency vulnerability management.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
25
AF Security Reliability

Best When

You have local access to Autodesk 3ds Max (recommended: 2026), can install the provided bridge, and want an agent to automate repetitive scene/modeling tasks with an MCP-compatible client.

Avoid When

You cannot control agent permissions/actions (safe mode) or you must operate with strict network/security constraints (named pipes/TCP, running scripts inside 3ds Max).

Use Cases

  • Scene graph inspection (objects, materials, modifiers, hierarchies)
  • Programmatic scene edits (transform, clone, parent, hide/freeze in bulk)
  • Automating material/PBR setup from texture folders
  • Generating OSL shaders and writing MAXScript loops driven by an agent
  • Batch inspecting .max assets without opening them (native plugin)
  • Viewport capture automation for visual feedback
  • Agent-driven control of controllers, wire parameters, and data channels

Not For

  • Remote SaaS use where you need internet-accessible APIs
  • Production environments needing audited security guarantees for arbitrary agent-driven actions
  • Cases where you cannot install/maintain the 3ds Max native plugin or run MAXScript inside 3ds Max

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Local MCP (stdio-based) client connection No documented end-user authentication in README; access is gated by local environment and (for MAXScript listener) safe mode restrictions
OAuth: No Scopes: No

No auth mechanism is documented for the MCP server itself. For operations executed inside 3ds Max, the primary safety control described is MAXScript safe mode (blocking certain dangerous capabilities by default).

Pricing

Free tier: No
Requires CC: No

Open-source tooling per MIT license; no service pricing indicated in provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Agent-driven MAXScript/Python execution risks: safe mode is ON by default but disabling it expands capabilities.
  • If the native bridge plugin is not installed, a TCP/MAXScript listener fallback is used; behavior and safety may differ.
  • Agent skill activation may require manual steps depending on the client (Claude requires manual activation via prompt).
  • Paths and environment setup (plugins folder, Max install dir) are Windows/3ds-Max-specific and must be correct for tools to work.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for 3dsmax-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered