dcc-mcp-mari

Production-oriented DCC-MCP adapter for Foundry Mari. It exposes project, geometry, channel, node graph, layer, shader, image, and texture-export workflows as typed tools without arbitrary Python execution. The host plugin supports Mari 5.0 and newer while keeping the DCC-MCP runtime in a separately installed Python 3.9+ sidecar.

Architecture

Mari loads a small standard-library plugin on its GUI thread. The plugin owns an authenticated loopback socket and starts the separately installed DCC-MCP sidecar. A Qt timer executes bounded Mari API commands on the host thread, while networking, discovery, jobs, and Gateway integration stay outside Mari's bundled Python environment.

Install

The authoritative agent-first lifecycle, platform paths, stable JSON schema, exit codes, recovery behavior, and troubleshooting are in install.md.

python -m pip install dcc-mcp-mari
dcc-mcp-mari install --dcc-path <mari-executable> --python <python> --dry-run --json
dcc-mcp-mari install --dcc-path <mari-executable> --python <python> --yes --json

Restart Mari after installation. The default Windows target is Documents/Mari/Scripts. Override it for a custom MARI_SCRIPT_PATH:

dcc-mcp-mari install --dcc-path <mari-executable> --python <python> --script-dir "D:/Mari/Scripts" --yes --json

Uninstall only this adapter's startup files:

dcc-mcp-mari uninstall --dcc-path <mari-executable> --python <python> --yes --json

Capability groups

  • mari-session: connection and full project lifecycle, including archive, rename, duplicate, and removal.
  • mari-geometry: geometry and channel lifecycle.
  • mari-nodegraph: nodes, connections, and layer stacks.
  • mari-lookdev: shaders, images, export items, and texture export.

All host mutations require a live Mari process. File inputs must be existing absolute paths, output parents must already exist, and destructive operations are explicitly annotated for DCC-MCP clients.

Development

python -m pip install -e ".[dev]"
python -m ruff check src tests
python -m ruff format --check src tests
python -m pytest
python -m build
python -m twine check dist/*

Mari Python API reference: Using Python in Mari.

Project links

Data verified by PyPI on Aug 25, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for hao.long from gravatar.com hao.long

Credits

Author: loonghao

GitHub Statistics

Data verified by PyPI on Aug 25, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT License (MIT)

Requires

Python >=3.9

Provides Extra

dev test

Tags

automation dcc mari mcp texture-painting

Classifiers

Report project as malware

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_mari-0.3.0.tar.gz (44.1 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_mari-0.3.0-py3-none-any.whl (54.8 kB view details)

Uploaded Python 3

File details

Details for the file dcc_mcp_mari-0.3.0.tar.gz.

File metadata

  • Download URL: dcc_mcp_mari-0.3.0.tar.gz
  • Upload date:
  • Size: 44.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for dcc_mcp_mari-0.3.0.tar.gz
Algorithm Hash digest
SHA256 5f0daf2af28dcb85964fcca59bf5c59b74413b96b87c93783d634ffb32c3e66c
MD5 65f1e5db65f50d6842c5a913163311b7
BLAKE2b-256 855ca5d25d820db2df0f46e72108e96748b7daf9a4fdfe9f6b2b9d4a1aed3178

See more details on using hashes here.

Provenance

The following attestation bundles were made for dcc_mcp_mari-0.3.0.tar.gz:

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

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_mari-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: dcc_mcp_mari-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 54.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for dcc_mcp_mari-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e38dc9b396134ca23b5e386e5527493f8f86ec2b7b2ded5894ffa652c07b0a7d
MD5 d86e34497fdc20f42a32584091ce6fa5
BLAKE2b-256 1370f4f59d0f29ddd64d4202e3b50c5de9426329cd542f97c53999ef70b73f11

See more details on using hashes here.

Provenance

The following attestation bundles were made for dcc_mcp_mari-0.3.0-py3-none-any.whl:

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

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

Release history Release notifications | RSS feed

This release

0.3.0 This release

2 files

0.2.1

2 files

0.2.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page