Ani MCP

io.github.gavxmPublished by GitHub account gavxmv0.15.7Updated Oct 24, 2026

A smart MCP server for AniList that gets your anime/manga taste - not just API calls.

VerifiedSTDIODesktop onlyProductivity & WorkflowData & AnalyticsMedia & Design

Overview

AI-generated overview

A local MCP server for AniList that lets an assistant search anime and manga, read your lists and stats, and build taste-based recommendations.

What you can do
Search and browse titles, seasons, trending lists, genres and community recommendations, with pagination and full details or relations for a title. Read a user's anime or manga list, check whether a title is on it, and view watching and reading statistics. Build a taste profile and get personalized picks, compatibility comparisons, sequel alerts, franchise watch orders, session plans and year-in-review summaries. Look up staff, studios, characters, airing schedules and upcoming episodes. View profiles, feeds, reviews and activity, and post, react or favourite on AniList. Analyze scoring bias, drop patterns, taste evolution, franchise completion and viewing pace. Write to your list: update or
When to use it
Useful when you want an assistant to help decide what to watch or read next, plan a viewing session, compare taste with friends, or manage and analyze an AniList library rather than just query the raw API.
Requirements
Runs locally via npx (Node.js) or Docker, or as an .mcpb extension in Claude Desktop. No account is needed for browsing. Set ANILIST_USERNAME for list, stats and recommendation tools, and ANILIST_TOKEN (AniList OAuth token) for write operations and private lists. Optional variables control title language, score format, adult content, mood keywords, debug logging and HTTP transport.
Before you install
ANILIST_TOKEN is a secret granting access to your AniList account; write tools can update progress, add, rate or delete list entries, post activities and react, so review actions before confirming. Adult content is excluded by default and only included when ANILIST_NSFW is set to true. Requests go only to the AniList API, and the server stores nothing locally.

Installation

In SourceWeft

  1. Open Ani MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[ani-mcp]

ani-mcp

[npm version] [npm downloads] [CI] [License: MIT] [MCP Bundle]

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, mood, and seasonal lineup
  • Compatibility - compare taste between two users
  • Sequel alerts - find sequels airing this season for shows you've finished
  • Watch order - franchise chain traversal for long-running series
  • Session planning - "I have 90 minutes, what should I watch?" from your current list
  • Year in review - your watching/reading stats wrapped up

Plus the essentials: search, details, trending, seasonal browsing, list management, social features, and community recommendations. All search and browse tools support pagination for browsing beyond the first page of results.

Try it in 30 seconds

No account needed. Works with any MCP-compatible client.

Claude Desktop

Add to your config file (Settings > Developer > Edit Config or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

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

Restart Claude Desktop after saving.

Alternatively, download ani-mcp.mcpb from the latest release and install via Settings > Extensions.

Claude Code

sh
claude mcp add ani-mcp -- npx -y ani-mcp

Personalized features

Add your username for recommendations, taste profiling, and list management:

json
{  "mcpServers": {    "anilist": {      "command": "npx",      "args": ["-y", "ani-mcp"],      "env": {        "ANILIST_USERNAME": "your_username"      }    }  }}

For write operations (updating progress, scoring, list edits), also add ANILIST_TOKEN. See Environment Variables for details.

Environment Variables

VariableRequiredDescription
ANILIST_USERNAMENoDefault username for list and stats tools. Can also pass per-call.
ANILIST_TOKENNoAniList OAuth token. Required for write operations and private lists.
ANILIST_TITLE_LANGUAGENoTitle preference: english (default), romaji, or native.
ANILIST_SCORE_FORMATNoOverride score display: POINT_100, POINT_10_DECIMAL, POINT_10, POINT_5, POINT_3.
ANILIST_NSFWNoSet to true to include adult content in results. Default: false.
ANILIST_MOOD_CONFIGNoJSON object to add or override mood keywords. See Mood config.
DEBUGNoSet to true for debug logging to stderr.
MCP_TRANSPORTNoSet to http for HTTP Stream transport. Default: stdio.
MCP_PORTNoPort for HTTP transport. Default: 3000.
MCP_HOSTNoHost for HTTP transport. Default: localhost.

Tools

Search & Discovery

ToolDescription
anilist_searchSearch anime/manga by title with genre, year, and format filters
anilist_detailsFull details, relations, and recommendations for a title
anilist_seasonalBrowse a season's anime lineup
anilist_trendingWhat's trending on AniList right now
anilist_genresBrowse top titles in a genre with optional filters
anilist_genre_listList all valid genres and content tags
anilist_recommendationsCommunity recommendations for a specific title

Lists & Stats

ToolDescription
anilist_listA user's anime/manga list, filtered by status
anilist_lookupCheck if a specific title is on a user's list
anilist_statsWatching/reading statistics, top genres, score distribution

Intelligence

ToolDescription
anilist_tasteGenerate a taste profile from your completed list
anilist_pickPersonalized "what to watch next" from your backlog, seasonal lineup, or discovery pool
anilist_compareCompare taste compatibility between two users
anilist_wrappedYear-in-review summary
anilist_explain"Why would I like this?" - score a title against your taste profile
anilist_similarFind titles similar to a given anime or manga
anilist_sequelsSequels airing this season for titles you've completed
anilist_watch_orderViewing order for a franchise
anilist_sessionPlan a viewing session within a time budget
anilist_mal_importImport a MyAnimeList user's list and generate recommendations
anilist_kitsu_importImport a Kitsu user's list and generate recommendations

Cards

ToolDescription
anilist_taste_cardGenerate a shareable taste profile card as a PNG image
anilist_compat_cardGenerate a compatibility card comparing two users as a PNG image

[Taste Profile Card] [Compatibility Card]

Info

ToolDescription
anilist_staffStaff credits and voice actors for a title
anilist_staff_searchSearch for a person by name and see all their works
anilist_studio_searchSearch for a studio and see their productions
anilist_scheduleAiring schedule and next episode countdown
anilist_airingUpcoming episodes for titles you're currently watching
anilist_charactersSearch characters by name with appearances and VAs
anilist_whoamiCheck authentication status and score format

Social

ToolDescription
anilist_profileView a user's profile, bio, favourites, and stats
anilist_feedRecent activity from a user's feed
anilist_reviewsCommunity reviews for a title
anilist_favouriteToggle favourite on anime, manga, character, staff, or studio
anilist_activityPost a text activity to your feed
anilist_group_pickFind anime/manga for a group to watch together
anilist_shared_planningFind overlap between two users' planning lists
anilist_follow_suggestionsRank followed users by taste compatibility
anilist_reactLike or reply to an activity

Analytics

ToolDescription
anilist_calibrationPer-genre scoring bias vs community consensus
anilist_dropsDrop pattern analysis - genre/tag clusters and median drop point
anilist_evolutionHow your taste shifted across 2-year time windows
anilist_completionistFranchise completion tracking via relation graph
anilist_seasonal_statsPer-season pick/finish/drop rates
anilist_paceEstimated completion date for currently watching titles

Write (requires ANILIST_TOKEN)

ToolDescription
anilist_update_progressUpdate episode or chapter progress
anilist_add_to_listAdd a title to your list with a status
anilist_rateScore a title (0-10)
anilist_delete_from_listRemove an entry from your list
anilist_undoUndo the last write operation
anilist_unscoredList completed but unscored titles for batch scoring
anilist_batch_updateBulk filter + action on list entries (dry-run default)

Resources

MCP resources provide context to your AI assistant without needing a tool call. Clients that support resources can automatically include this information in conversations.

ResourceDescription
anilist://profileYour AniList profile with bio, stats, and favourites
anilist://taste/{type}Taste profile (genre weights, themes, scoring patterns) for ANIME or MANGA
anilist://list/{type}Currently watching/reading entries with progress and scores

Prompts

Pre-built conversation starters that clients can offer as quick actions.

PromptDescription
setupWalk through connecting your AniList account step by step
seasonal_reviewReview this season's anime against your taste profile
what_to_watchPlan what to watch now with optional mood and time budget
roast_my_tasteGet a humorous roast of your anime taste
compare_usCompare your taste with another user
year_in_reviewYour anime/manga year in review
explain_titleWhy would you like (or dislike) a specific title?
find_similarFind titles similar to one you enjoyed

Examples

Here are some things you can ask your AI assistant once ani-mcp is connected:

"What should I watch next?" Uses anilist_pick to analyze your completed list, build a taste profile, and recommend titles from your Planning list ranked by how well they match your preferences.

"I want something dark and psychological" Uses anilist_pick with mood filtering to boost titles matching that vibe and penalize mismatches.

"What's good this season?" Uses anilist_pick with source: SEASONAL to rank currently airing anime against your taste profile.

"I have 90 minutes, what should I watch tonight?" Uses anilist_session to pick from your currently watching list and fill a time budget with the best-matching episodes.

"Any sequels airing for stuff I've finished?" Uses anilist_sequels to cross-reference your completed list with this season's lineup.

"What order do I watch Fate in?" Uses anilist_watch_order to traverse the franchise relation graph and produce a numbered viewing order.

"Compare my taste with username123" Uses anilist_compare to find shared titles, compute a compatibility score, and highlight biggest disagreements.

"Why would I like Vinland Saga?" Uses anilist_explain to score a title against your taste profile, breaking down genre affinity and theme alignment.

"Show me my anime year in review" Uses anilist_wrapped to summarize everything you watched in a given year.

Mood config

anilist_pick and anilist_session accept a freeform mood string. Built-in keywords include: dark, chill, hype, action, romantic, funny, brainy, sad, scary, epic, wholesome, intense, mystery, fantasy, scifi, trippy, nostalgic, artistic, competitive, cozy.

To add or override keywords, set ANILIST_MOOD_CONFIG as a JSON object:

json
{  "ANILIST_MOOD_CONFIG": "{\"cozy\":{\"boost\":[\"Slice of Life\",\"Iyashikei\"],\"penalize\":[\"Horror\"]},\"mykeyword\":{\"boost\":[\"Romance\"],\"penalize\":[]}}"}

Each key is a mood keyword mapping to { boost: string[], penalize: string[] } arrays of AniList genres and tags.

Privacy

See PRIVACY.md for details. In short: ani-mcp runs locally, sends requests only to the AniList API, stores nothing, and collects no analytics.

Docker

sh
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

sh
git clone https://github.com/gavxm/ani-mcp.gitcd ani-mcpnpm installnpm run buildnpm test

Support

Bug reports and feature requests: GitHub Issues

License

MIT

Source: README.md at commit af4e721

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.15.7LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts