Kitsu MCP Server
Connects AI assistants to the Kitsu open-source production management platform for animation, VFX, and game studios. It provides over 70 tools to manage projects, assets, shots, tasks, and production pipelines through natural language.
README
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
71 tools covering the full Kitsu production pipeline:
| Category | Tools |
|---|---|
| Projects | List, overview, stats, create, close |
| Assets | List, details, create, update, delete, asset types, CSV import/export |
| Shots & Sequences | List, details, create, update, delete, batch create, CSV import/export, OTIO import |
| Tasks | List, details, create, batch create, assign, update status, set estimates, delete |
| Time Tracking | Add, set, get time spent |
| Comments | Add comments, list comment history |
| Previews | Upload preview, publish preview (status + comment + file in one) |
| Casting | Get/set shot casting, get asset casting |
| Team & People | List team, person tasks, create person, departments |
| Playlists | List, create, add entities, build movie |
| Budgets | List, create budgets and budget entries |
| Concepts | List, create concepts |
| Edits | List, create edits |
| Scenes | List, create scenes |
| Metadata | List and add custom metadata descriptors |
| Other | Search, notifications, task statuses, daily progress report |
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/claude_desktop_config.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-password"
python server.py
Example prompts
Once connected, you can ask your AI assistant things like:
- "List all open projects in Kitsu"
- "Create shots SH010 through SH200 in sequence SQ01"
- "Upload this render as a preview for the lighting task on SH020"
- "What happened in the project in the last 24 hours?"
- "Assign the animation task on SH030 to anna@studio.com"
- "Add 4 hours of work on this task for today"
- "Export all shots to CSV"
- "Create a new playlist and add all shots from SQ01"
- "What are the budget entries for this project?"
Available tools
Read
list_projects— List all open projectsget_project_overview— Project overview with team, task types, asset typesget_project_stats— Task statistics grouped by statuslist_assets— List assets (optionally filtered by type)get_asset_details— Asset details with taskslist_sequences— List sequenceslist_shots— List shots (optionally filtered by sequence)get_shot_details— Shot details with tasks and castinglist_my_tasks— Tasks assigned to logged-in userlist_tasks_for_entity— Tasks for a specific asset or shotget_task_details— Task details with comment historyget_time_spent— Time entries for a tasklist_comments— Comments on a taskget_shot_casting— Asset breakdown for a shotget_asset_casting— Shots an asset appears inlist_team_members— Team members in a projectget_person_tasks— Tasks for a specific personlist_departments— All departmentslist_playlists— Playlists in a projectlist_task_statuses— Available task statuseslist_notifications— Recent notificationssearch— Search entities by namedaily_progress_report— Activity summary for last N hourslist_concepts— Concepts in a projectlist_edits— Edits in a projectlist_scenes— Scenes in a projectlist_metadata_descriptors— Custom metadata fieldsget_budgets— Budgets for a projectget_budget_entries— Entries in a budgetexport_assets_csv— Export assets to CSVexport_shots_csv— Export shots to CSV
Create
create_project— Create a new projectcreate_asset_type— Create an asset typecreate_asset— Create an assetcreate_episode— Create an episodecreate_sequence— Create a sequencecreate_shot— Create a shotcreate_task— Create a task with optional assigneescreate_person— Create a new usercreate_department— Create a departmentcreate_playlist— Create a playlistcreate_budget— Create a budgetcreate_budget_entry— Create a budget entrycreate_concept— Create a conceptcreate_edit— Create an editcreate_scene— Create a sceneadd_metadata_descriptor— Add a custom metadata field
Update
update_task_status— Change task status with optional commentassign_task— Assign a person to a taskset_task_estimate— Set time estimate for a taskadd_comment— Add a comment to a taskset_shot_casting— Set which assets appear in a shotupdate_asset— Update asset description/metadataupdate_shot— Update shot description/frames/metadataadd_time_spent— Add time spent on a taskset_time_spent— Set time spent on a taskadd_person_to_department— Add person to departmentremove_person_from_department— Remove person from departmentadd_entity_to_playlist— Add shot/asset to playlist
Batch
batch_create_shots— Create multiple shots at once (e.g. SH010-SH200)batch_create_tasks— Add a task type to all shots/assets in a group
Preview
upload_preview— Upload a preview file to a taskpublish_preview— Status + comment + preview in one step
Import/Export
import_assets_csv— Import assets from CSVimport_shots_csv— Import shots from CSVimport_otio— Import timeline from OpenTimelineIO
Dangerous (require confirm=True)
delete_shot— Delete a shotdelete_asset— Delete an assetdelete_task— Delete a taskclose_project— Close/archive a projectbuild_playlist_movie— Build a movie from playlist
License
MIT License — see LICENSE.
Credits
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。