Kitsu MCP Server

An MCP (Model Context Protocol) server that connects AI assistants like Claude to Kitsu — the open-source production management tool for animation, VFX, and game studios.

Built with FastMCP and the Gazu Python client.

Features

98 tools covering the full Kitsu production pipeline:

Category	Tools
Projects	List, overview, stats, create, close, add/remove task types
Assets	List, details, create, update, delete, update custom data, asset types, CSV import/export
Shots & Sequences	List, details, create, update, delete, update custom data, batch create, CSV import/export, OTIO import
Tasks	List, details, create, batch create, assign, unassign, start task, submit for review, update custom data, update status, set estimates, delete
Time Tracking	Add, set, get time spent, get time spent range
Comments	Add comments, reply to comment, acknowledge comment, list comment history
Previews	Upload, publish, set main, list per task, get URLs, download, update annotations
Attachments	List attachment files per task
Casting	Get/set shot casting, get asset casting
Team & People	List team, update roles, add/remove members, person tasks, create person, invite, departments
Playlists	List, create, add entities, remove entities, build movie
Budgets	List, create budgets and budget entries
Concepts	List, create concepts
Edits	List, create, details, update, delete, list previews
Scenes	List, create scenes
Metadata	List and add custom metadata descriptors
Notifications	List, mark all as read, subscribe/unsubscribe from tasks
Pipeline Config	List/create task types, list/create task statuses
Other	Search, daily progress report

Edit / Montage Review Workflow

Edits are full-length montages or sequences (like animatics, trailers, or final cuts) — the Kitsu equivalent of Frame.io's file-based review. Upload a complete video with audio and review it with annotations, comments, and version tracking.

1. create_edit("My Project", "Trailer_v03")
2. create_task("My Project", "Trailer_v03", "Edit", entity_type="edit")
3. upload_preview(task_id, "/path/to/trailer_v03.mp4", comment="v3 with music")

The team can then review the full montage in Kitsu's player with drawing/annotation tools and timecoded comments.

Requirements

• Python 3.10+
• A running Kitsu instance (self-hosted or cloud)
• A Kitsu user account with appropriate permissions

Installation

git clone https://github.com/INGIPSA/kitsu-mcp-server.git
cd kitsu-mcp-server
pip install -r requirements.txt

Configuration

The server requires three environment variables:

Variable	Description	Example
KITSU_HOST	Your Kitsu API URL	https://kitsu.yourstudio.com/api
KITSU_USER	Login email	artist@yourstudio.com
KITSU_PASSWORD	Login password	your-password

Usage

With Claude Code

Add to your Claude Code MCP config (~/.claude/mcp.json or project-level .mcp.json):

{
  "mcpServers": {
    "kitsu": {
      "command": "python",
      "args": ["path/to/kitsu-mcp-server/server.py"],
      "env": {
        "KITSU_HOST": "https://kitsu.yourstudio.com/api",
        "KITSU_USER": "your-email@example.com",
        "KITSU_PASSWORD": "your-password"
      }
    }
  }
}

With Claude Desktop

Add the same config block to Claude Desktop's settings under MCP servers.

Standalone

export KITSU_HOST="https://kitsu.yourstudio.com/api"
export KITSU_USER="your-email@example.com"
export KITSU_PASSWORD="your-passw

... [View full README on GitHub](https://github.com/INGIPSA/kitsu-mcp-server#readme)