Skip to main content

ZBrush adapter for the DCC Model Context Protocol (MCP) ecosystem — embedded Python SDK + optional socket bridge

Project description

dcc-mcp-zbrush

PyPI Python 3.9+ License: MIT Status: Pre-Alpha

ZBrush adapter for the DCC Model Context Protocol ecosystem.

Requires ZBrush 2026.1+ with the official Python SDK (CPython 3.11 embedded in ZBrush).

Quick install

1. Install the Python package

pip install dcc-mcp-zbrush

This installs the dcc-mcp-zbrush Python package — the MCP HTTP server that bridges AI agents to ZBrush. It does not include ZBrush plugin files (see step 2).

2. Install the ZBrush plugin

The plugin files (auto-start script, socket bridge) are distributed separately. Download the plugin ZIP from the latest GitHub Release:

dcc-mcp-zbrush-plugin-<version>.zip

Then run the install script inside the ZIP:

Windows (PowerShell):

.\install\install-windows.ps1

macOS (Terminal):

chmod +x install/install-macos.sh && ./install/install-macos.sh

This copies the plugin into your ZBrush ZStartup/ZPlugs64 directory so it loads automatically on startup.

3. Restart ZBrush

Launch or restart ZBrush. The plugin auto-starts the MCP server in embedded mode.

4. Health check

Verify the server is running:

curl http://127.0.0.1:8765/mcp

5. Configure your AI client

Add the MCP server to your AI client config (Cursor, Claude Desktop, etc.):

{
  "mcpServers": {
    "zbrush": {
      "url": "http://127.0.0.1:8765/mcp"
    }
  }
}

How it works

ZBrush does not ship a built-in HTTP REST server. The pre-alpha scaffold that assumed Preferences > Network > Enable HTTP Server was incorrect.

The supported integration paths are:

Mode When to use Stack
Embedded (recommended) ZBrush 2026.1+ with Python SDK Python plugin inside ZBrush → dcc-mcp-core MCP HTTP server → zbrush.commands
Sidecar + socket plugin External MCP process / restricted installs External Python → TCP :9876 → bridge/plugin/mcp_socket_bridge.py inside ZBrush

Rust is not used inside ZBrush. Like Maya/Houdini, Rust lives in the dcc-mcp-core wheel (PyO3) that powers the MCP HTTP server. The ZBrush-facing code is Python only.

GoZ C++ SDK is for mesh exchange between DCC apps, not general MCP automation — we do not build the primary adapter on GoZ.

Embedded mode (default inside ZBrush):

AI Agent → MCP HTTP :8765 → ZBrushMcpServer (inside ZBrush) → zbrush.commands

Sidecar mode:

AI Agent → MCP HTTP :8765 → ZBrushMcpServer (external Python)
         → TCP :9876 → mcp_socket_bridge.py (inside ZBrush) → zbrush.commands

Features (v0.2.0)

  • DccServerBase adapter with progressive skill loading
  • Bundled skills: zbrush-scripting, zbrush-scene, zbrush-subtool, zbrush-interchange
  • In-process executor for ZBrush's embedded Python VM
  • Optional socket bridge plugin for sidecar deployments
  • Gateway election compatible with dcc-mcp-core

Requirements

  • ZBrush 2026.1+
  • Python 3.9+ on the sidecar host (ZBrush itself ships 3.11)
  • dcc-mcp-core >= 0.18.2

Environment variables

Variable Default Purpose
DCC_MCP_ZBRUSH_PORT 8765 MCP HTTP port
DCC_MCP_ZBRUSH_MODE auto embedded or sidecar
DCC_MCP_ZBRUSH_AUTOSTART 1 Auto-start embedded server from plugin
DCC_MCP_ZBRUSH_SOCKET_PORT 9876 Socket bridge port (sidecar)
DCC_MCP_GATEWAY_PORT 9765 Gateway election port
DCC_MCP_MINIMAL 1 Progressive skill loading

Bundled skills

Skill Tools
zbrush-scripting execute_python, get_session_info
zbrush-scene get_scene_info, list_subtools
zbrush-subtool select_subtool, get_subtool_status
zbrush-interchange export_active_subtool_obj

Path concepts

  • PYTHONPATH — where Python looks for packages (pip install handles this)
  • ZBRUSH_PLUGIN_PATH / ZStartup/ZPlugs64 — where ZBrush loads auto-start plugins

pip install dcc-mcp-zbrush puts the Python package on PYTHONPATH.
The plugin ZIP goes into ZBRUSH_PLUGIN_PATH (handled by the install scripts above).

Skill authoring

Skills lazy-import zbrush.commands and run on the main thread (affinity: main).

from dcc_mcp_core.skill import skill_entry
from dcc_mcp_zbrush.api import import_zbc, with_zbrush, zb_success

@skill_entry
@with_zbrush
def my_tool(**kwargs) -> dict:
    zbc = import_zbc()
    count = zbc.get_subtool_count()
    return zb_success(f"{count} subtool(s)", count=count)

Sidecar mode (optional)

If you cannot install the embedded plugin or need the MCP server to run outside ZBrush:

  1. The plugin ZIP already includes sidecar/mcp_socket_bridge.py — copy it to ZPlugs64 (the install scripts handle this).
  2. Start ZBrush.
  3. Run the MCP server outside ZBrush:
dcc-mcp-zbrush --mode sidecar --port 8765 --socket-port 9876

Development

See docs/development.md for source-based setup, testing, and contribution workflow.

References

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dcc_mcp_zbrush-0.2.4.tar.gz (34.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dcc_mcp_zbrush-0.2.4-py3-none-any.whl (28.4 kB view details)

Uploaded Python 3

File details

Details for the file dcc_mcp_zbrush-0.2.4.tar.gz.

File metadata

  • Download URL: dcc_mcp_zbrush-0.2.4.tar.gz
  • Upload date:
  • Size: 34.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for dcc_mcp_zbrush-0.2.4.tar.gz
Algorithm Hash digest
SHA256 53cce413c3785c1c22303ef0d3d6bf60d6ed9c8d83d0cac7dddb7d3792785982
MD5 af6a9debc913a4c1f4e6b6bf7cc3567c
BLAKE2b-256 c11fcb605911a406a7ab2889f7e09650b9d5f742bc66b8f90481e5010b5f7b46

See more details on using hashes here.

Provenance

The following attestation bundles were made for dcc_mcp_zbrush-0.2.4.tar.gz:

Publisher: release.yml on dcc-mcp/dcc-mcp-zbrush

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file dcc_mcp_zbrush-0.2.4-py3-none-any.whl.

File metadata

  • Download URL: dcc_mcp_zbrush-0.2.4-py3-none-any.whl
  • Upload date:
  • Size: 28.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for dcc_mcp_zbrush-0.2.4-py3-none-any.whl
Algorithm Hash digest
SHA256 52f97b6b70788f0d88528a6a14ee24438b2283fc74c3e3cb0ce7a8f9248dde1a
MD5 84ce1601d8e1e7830c13feb1efc0556a
BLAKE2b-256 e249747eb2aadf427d0719ced85a80f18aa9fa73898ca7acc30d5a6ae1c202d4

See more details on using hashes here.

Provenance

The following attestation bundles were made for dcc_mcp_zbrush-0.2.4-py3-none-any.whl:

Publisher: release.yml on dcc-mcp/dcc-mcp-zbrush

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page