anime-mcp-server
An MCP server for anime and manga discovery, enabling search, detail retrieval, franchise watch order, seasonal schedule, character lookups, rankings, and studio filmography via natural language.
README
<div align="center"> <h1>@cyanheads/anime-mcp-server</h1> <p><b>Search anime/manga, get full detail, franchise watch order, seasonal schedule, characters, rankings, and studio filmography via MCP. STDIO or Streamable HTTP.</b> <div>8 Tools • 1 Resource</div> </p> </div>
<div align="center">
</div>
<div align="center">
</div>
Tools
Eight tools covering anime and manga discovery, detail, and navigation:
| Tool | Description |
|---|---|
anime_search_media |
Search anime or manga by title, genre, tag, season, year, format, or status. Returns ranked results with IDs, titles, scores, format, and episode/chapter counts. AniList primary; Jikan fallback on empty results. |
anime_get_media |
Full detail for one anime or manga by AniList ID — synopsis, format, episode/chapter count, status, season, studios, source material, genres and tags (spoiler-flagged), AniList and MAL scores side by side, streaming links, cover/banner, and direct relations. |
anime_get_relations |
Franchise untangler. Walks the related-works graph from a media ID beyond one hop — sequels, prequels, side stories, movies, OVAs, source and adaptation — and returns them in suggested watch/read order. |
anime_get_schedule |
Airing schedule for a season or upcoming episode window. Season mode lists all anime airing in a given season/year. Upcoming mode returns the next episode for each airing title within a date window, with UTC timestamp and countdown. |
anime_find_characters |
Characters and voice actors for a title, or look up a character/VA by name. Returns characters with role (main/supporting/background), voice actors by language, and cross-links to other media. |
anime_get_recommendations |
Recommendations for a title, merged from AniList and Jikan (MAL), with scores and vote counts. Optionally accepts what the user liked about the source title to contextualize picks. |
anime_get_rankings |
Top, trending, or seasonal rankings. Filterable by genre, tag, and format. Top returns all-time by score; trending returns current week; seasonal returns the current or specified season sorted by popularity. |
anime_get_studio |
A studio's full filmography by name or AniList studio ID — all titles the studio produced, sortable by year or score, with format, status, and episode count. |
anime_search_media
Search for anime or manga across multiple dimensions.
- Free-text title search with AniList primary; falls back to Jikan when AniList returns empty
- Filter by genre, tag, season, year, format (
TV,MOVIE,OVA,MANGA,NOVEL, etc.), and status (RELEASING,FINISHED, etc.) - Adult content gated behind explicit
include_adult: true(default off) - Pagination via
pageandper_page
anime_get_media
Full detail for a single anime or manga — the flagship tool for a title's complete profile.
- AniList full-detail query supplemented in parallel by Jikan (MAL score) and Kitsu (streaming links with sub/dub language flags)
- AniList and MAL scores surfaced side by side — never blended
- Spoiler-safe by default: tags carry a
spoilerflag; relation descriptions omitted unlessreveal_spoilers: true - All timestamps UTC; season labels included to avoid boundary ambiguity
anime_get_relations
Build the watch/read order for an entire franchise.
- Multi-hop BFS over AniList's relation graph, up to
max_depthhops (default 2, max 4) - Relation types: SOURCE, PREQUEL, SEQUEL, SIDE_STORY, SPIN_OFF, ADAPTATION, OVA, SPECIAL, MOVIE
- Topological sort: SOURCE → PREQUEL → main story chain → SEQUEL → SIDE_STORY → SPIN_OFF → supplementary entries
- Each entry includes
seasonYearand episode/chapter count for context
anime_find_characters
Bidirectional character and voice actor lookup.
- By media ID: characters for a title with voice actors by language
- By character name: find the character and all media they appear in
- By voice actor name: find the VA and all roles across media
- Language filter via AniList
StaffLanguageenum (JAPANESE, ENGLISH, KOREAN, etc.)
Resources and prompts
| Type | Name | Description |
|---|---|---|
| Resource | anime://media/{id} |
Full media record for an anime or manga by AniList ID — same data as anime_get_media. Stable URI for injectable context. |
All resource data is also reachable via tools. Use anime_search_media to discover AniList IDs before fetching the resource URI.
Features
Built on @cyanheads/mcp-ts-core:
- Declarative tool and resource definitions — single file per primitive, framework handles registration and validation
- Unified error handling — handlers throw, framework catches, classifies, and formats
- Pluggable auth:
none,jwt,oauth - Swappable storage backends:
in-memory,filesystem,Supabase,Cloudflare KV/R2/D1 - Structured logging with optional OpenTelemetry tracing
- STDIO and Streamable HTTP transports
Anime/manga-specific:
- Three-source architecture: AniList GraphQL (primary), Jikan v4 REST (MAL scores + recommendations), Kitsu JSON:API (streaming links with sub/dub language detail)
- ID reconciliation via AniList's
idMalbridge — no cross-source ID guessing - Franchise relation graph traversal with topological watch-order sort
- Rate-limit-aware service layer: AniList 30 req/30s with automatic backoff; Jikan 350ms floor between calls
- Keyless by design — all three sources are public and require no API credentials
- Local-only by design: free APIs are tightly rate-limited per IP; hosting would pool users onto one IP and risk throttling or bans. Each local user brings their own IP and modest usage.
Agent-friendly output:
- Dual scores surfaced separately — AniList
meanScore(0–100) and MALscore(0–10) with population size (scored_by) so agents can reason about weight; never blended into a composite - Spoiler safety by default — AniList tags carry
isGeneralSpoiler; relation descriptions omitted unless opted in - Supplement provenance — each response indicates which sources contributed (AniList, Jikan, Kitsu) and which failed gracefully, so agents know what data is present
- UTC timestamps throughout; season labels echoed (
WINTER 2024) to avoid the winter/spring/summer/fall boundary footgun
Getting started
No API keys required — all three upstream sources (AniList, Jikan, Kitsu) are keyless public APIs.
Add the following to your MCP client configuration file:
{
"mcpServers": {
"anime-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/anime-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
Or with npx (no Bun required):
{
"mcpServers": {
"anime-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/anime-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
Or with Docker:
{
"mcpServers": {
"anime-mcp-server": {
"type": "stdio",
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "MCP_TRANSPORT_TYPE=stdio",
"ghcr.io/cyanheads/anime-mcp-server:latest"
]
}
}
}
For Streamable HTTP, set the transport and start the server:
MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp
Prerequisites
- Bun v1.3.0 or higher (or Node.js v24+). No API keys needed.
Installation
- Clone the repository:
git clone https://github.com/cyanheads/anime-mcp-server.git
- Navigate into the directory:
cd anime-mcp-server
- Install dependencies:
bun install
- Configure environment (optional):
cp .env.example .env
# edit .env if you want to change transport or log level
Configuration
No server-specific env vars are required. All framework variables are optional with sensible defaults.
| Variable | Description | Default |
|---|---|---|
MCP_TRANSPORT_TYPE |
Transport: stdio or http. |
stdio |
MCP_HTTP_PORT |
Port for HTTP server. | 3010 |
MCP_HTTP_HOST |
Hostname for HTTP server. | 127.0.0.1 |
MCP_HTTP_ENDPOINT_PATH |
Endpoint path for the MCP server. | /mcp |
MCP_AUTH_MODE |
Auth mode: none, jwt, or oauth. |
none |
MCP_LOG_LEVEL |
Log level (RFC 5424): debug, info, notice, warning, error. |
info |
OTEL_ENABLED |
Enable OpenTelemetry instrumentation. | false |
See .env.example for the full list of optional overrides.
Running the server
Local development
-
Build and run:
# One-time build bun run rebuild # Run the built server bun run start:stdio # or bun run start:http -
Run checks and tests:
bun run devcheck # Lint, format, typecheck, security bun run test # Vitest test suite bun run lint:mcp # Validate MCP definitions against spec
Docker
docker build -t anime-mcp-server .
docker run --rm -p 3010:3010 anime-mcp-server
The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/anime-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.
Project structure
| Directory | Purpose |
|---|---|
src/index.ts |
createApp() entry point — registers tools, resources, and inits services. |
src/mcp-server/tools |
Tool definitions (*.tool.ts). |
src/mcp-server/resources |
Resource definitions (*.resource.ts). |
src/services/anilist |
AniList GraphQL client — primary source for all queries. |
src/services/jikan |
Jikan v4 REST client — MAL scores and recommendations. |
src/services/kitsu |
Kitsu JSON:API client — streaming links with sub/dub language detail. |
tests/ |
Unit and integration tests mirroring src/. |
changelog/ |
Per-version changelog files (changelog/<minor>.x/<version>.md). |
Development guide
See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:
- Handlers throw, framework catches — no
try/catchin tool logic - Use
ctx.logfor request-scoped logging,ctx.statefor tenant-scoped storage - Register new tools and resources via the barrels in
src/mcp-server/*/definitions/index.ts - Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields
- AniList is primary — supplement failures (Jikan, Kitsu) degrade gracefully via
Promise.allSettled
Contributing
Issues and pull requests are welcome. Run checks and tests before submitting:
bun run devcheck
bun run test
License
Apache-2.0 — see LICENSE for details.
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。