Eight tools covering anime and manga discovery, detail, and navigation:

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 page and per_page

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 spoiler flag; relation descriptions omitted unless reveal_spoilers: true
• All timestamps UTC; season labels included to avoid boundary ambiguity

Build the watch/read order for an entire franchise.

• Multi-hop BFS over AniList's relation graph, up to max_depth hops (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 seasonYear and episode/chapter count for context

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 StaffLanguage enum (JAPANESE, ENGLISH, KOREAN, etc.)

All resource data is also reachable via tools. Use anime_search_media to discover AniList IDs before fetching the resource URI.

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 idMal bridge — 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 MAL score (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

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

• Bun v1.3.0 or higher (or Node.js v24+). No API keys needed.

1. Clone the repository:

git clone https://github.com/cyanheads/anime-mcp-server.git

2. Navigate into the directory:

cd anime-mcp-server

3. Install dependencies:

bun install

4. Configure environment (optional):

cp .env.example .env
# edit .env if you want to change transport or log level

No server-specific env vars are required. All framework variables are optional with sensible defaults.

See .env.example for the full list of optional overrides.

• 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 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.

See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for 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

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

Apache-2.0 — see LICENSE for details.