ani-mcp
A smart AniList integration for the Model Context Protocol that provides AI assistants with tools for searching media, managing watchlists, and analyzing user anime or manga tastes. It goes beyond basic API calls by offering personalized recommendations, taste comparisons, and natural language profile summaries.
README
ani-mcp
A smart MCP server for AniList that understands your anime and manga taste - not just raw API calls.
What makes this different
Most AniList integrations mirror the API 1:1. ani-mcp adds an intelligence layer on top:
- Taste profiling - builds a model of your preferences from your completed list
- Personalized picks - "what should I watch next?" based on your taste and mood
- Compatibility - compare taste between two users
- Year in review - your watching/reading stats wrapped up
Plus the essentials: search, details, trending, seasonal browsing, list management, and community recommendations.
Install
Add to your MCP client config (e.g. mcp.json, claude_desktop_config.json, Cursor settings, etc.):
{
"mcpServers": {
"anilist": {
"command": "npx",
"args": ["-y", "ani-mcp"],
"env": {
"ANILIST_USERNAME": "your_username"
}
}
}
}
Works with any MCP-compatible client.
Environment Variables
| Variable | Required | Description |
|---|---|---|
ANILIST_USERNAME |
No | Default username for list and stats tools. Can also pass per-call. |
ANILIST_TOKEN |
No | AniList OAuth token. Required for write operations and private lists. |
DEBUG |
No | Set to true for debug logging to stderr. |
MCP_TRANSPORT |
No | Set to http for HTTP Stream transport. Default: stdio. |
MCP_PORT |
No | Port for HTTP transport. Default: 3000. |
MCP_HOST |
No | Host for HTTP transport. Default: localhost. |
Tools
Search & Discovery
| Tool | Description |
|---|---|
anilist_search |
Search anime/manga by title with genre, year, and format filters |
anilist_details |
Full details, relations, and recommendations for a title |
anilist_seasonal |
Browse a season's anime lineup |
anilist_trending |
What's trending on AniList right now |
anilist_genres |
Browse top titles in a genre with optional filters |
anilist_recommendations |
Community recommendations for a specific title |
Lists & Stats
| Tool | Description |
|---|---|
anilist_list |
A user's anime/manga list, filtered by status |
anilist_stats |
Watching/reading statistics, top genres, score distribution |
Intelligence
| Tool | Description |
|---|---|
anilist_taste |
Generate a taste profile from your completed list |
anilist_pick |
Personalized "what to watch next" based on taste and mood |
anilist_compare |
Compare taste compatibility between two users |
anilist_wrapped |
Year-in-review summary |
Info
| Tool | Description |
|---|---|
anilist_staff |
Staff credits and voice actors for a title |
anilist_schedule |
Airing schedule and next episode countdown |
anilist_characters |
Search characters by name with appearances and VAs |
Write (requires ANILIST_TOKEN)
| Tool | Description |
|---|---|
anilist_update_progress |
Update episode or chapter progress |
anilist_add_to_list |
Add a title to your list with a status |
anilist_rate |
Score a title (0-10) |
anilist_delete_from_list |
Remove an entry from your list |
Docker
docker build -t ani-mcp .
docker run -e ANILIST_USERNAME=your_username ani-mcp
Runs on port 3000 with HTTP Stream transport by default.
Build from Source
git clone https://github.com/gavxm/ani-mcp.git
cd ani-mcp
npm install
npm run build
npm test
License
MIT
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。