About
Krita adapter for the DCC Model Context Protocol
README
Krita adapter for the DCC Model Context Protocol ecosystem.

The adapter uses a small Krita Python plug-in and a loopback JSON-lines bridge. The MCP server runs in the normal Python environment; KRITA API calls stay inside the plug-in process. It does not expose arbitrary Python or Script-Fu execution.
Install
pip install dcc-mcp-krita
dcc-mcp-krita-install
Restart Krita, enable the bundled Python plug-in, then start:
dcc-mcp-krita
The MCP endpoint defaults to http://127.0.0.1:8767/mcp; the plug-in bridge uses
127.0.0.1:3848. Override the latter with DCC_MCP_KRITA_BRIDGE_PORT before
starting both processes.
Current tools
- Check KRITA bridge status and version.
- List open images with dimensions.
- Inspect the active image.
The first release targets safe session discovery. Image mutation and export will be added only through typed KRITA procedures, not arbitrary source evaluation.
Development
python -m pip install -e ".[dev]"
python -m pytest
python -m ruff check src tests tools
python tools/lint_skills.py
python -m build
python -m twine check dist/*
Krita plug-in API reference: https://developer.krita.org/api/3.0/
Installing Dcc Mcp Krita
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/dcc-mcp/dcc-mcp-kritaFAQ
Is Dcc Mcp Krita MCP free?
Yes, Dcc Mcp Krita MCP is free — one-click install via Unyly at no cost.
Does Dcc Mcp Krita need an API key?
No, Dcc Mcp Krita runs without API keys or environment variables.
Is Dcc Mcp Krita hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Dcc Mcp Krita in Claude Desktop, Claude Code or Cursor?
Open Dcc Mcp Krita on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
ARA
Generate images, video and audio from any AI agent — one connector.
by ARAOmni Video
An MCP server that transforms LLM-enabled IDEs into professional video editors by pre-processing footage into text proxies, generating motion graphics via HTML/
by buildwithtazaYouTube
Transcripts, channel stats, search
by YouTubeEverArt
AI image generation using various models.
by modelcontextprotocolCompare Dcc Mcp Krita with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All media MCPs
