AniList MCP

為什麼要用

核心特性

Search anime, manga, characters, staff, and studios
Read user watchlist/readlist (with optional auth token)
Genre and tag-based discovery
Cross-reference with MAL IDs
Trend and top-rated lists

即時演示

實際使用效果

anilist-mcp.replay ▶ 就緒

0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "anilist-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "anilist-mcp"
      ]
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "anilist-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "anilist-mcp"
      ]
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "anilist-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "anilist-mcp"
      ]
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "anilist-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "anilist-mcp"
      ]
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "anilist-mcp",
      "command": "npx",
      "args": [
        "-y",
        "anilist-mcp"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "anilist-mcp": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "anilist-mcp"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add anilist-mcp -- npx -y anilist-mcp

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： AniList MCP

Get genre-aware anime recommendations from your AniList history

👤 Anime fans ⏱ ~15 min intermediate

何時使用： You want recs that actually respect what you've already finished.

前置條件

Server/skill installed and authenticated — See repo README

步驟

Pull watch history

Read my AniList user list (username: foobar). Group by genre and score.✓ 已複製

→ Distribution by genre + average score per genre
Recommend

Recommend 5 highly-rated anime in my top two genres that I haven't watched yet.✓ 已複製

→ List of 5 with titles, year, score, why-you'd-like-it

結果： Personalized recs grounded in your actual taste.

注意事項

Recommendations are LLM-generated — Recommendations are LLM-generated — verify with AniList scores; don't trust title hallucinations.

搭配使用： fetch

組合

與其他 MCP 搭配，撬動十倍槓桿

anilist-mcp + fetch

Pair with fetch for complementary capabilities

Use this server together with fetch to complete a multi-step task.✓ 已複製

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫	成本
search_anime	query, year, season	Find anime by title or season	1 GraphQL call
search_character	name	Look up a character across series	1 GraphQL call
user_list	username, type	Read a user's public watchlist	1 GraphQL call

成本與限制

運行它的成本

API 配額: See provider docs for rate limits
每次呼叫 Token 數: Varies by tool
費用: See repo README for pricing details
提示: Cache tool results and avoid repeated identical calls.

安全

權限、密鑰、影響範圍

憑證儲存： Use environment variables; never commit secrets

資料出站： Tool calls go to the provider's API as documented

故障排查

常見錯誤與修復

rate limited

AniList caps unauthenticated requests at 30/min. Set ANILIST_TOKEN to raise the limit.

驗證： Wait 60s and retry

user not found

AniList usernames are case-sensitive. Use the exact handle from the user's profile URL.

驗證： Open https://anilist.co/user/<name> in a browser

替代方案

AniList MCP 對比其他方案

替代方案	何時用它替代	權衡
MyAnimeList unofficial MCPs	You're already syncing to MAL	API is less stable than AniList's GraphQL