[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup) # Triage AniList notifications and reply to activity > Sort AniList notifications into likes, follows, replies and mentions, then reply to the ones that need you. Runs daily, nothing to host. Source: https://cotlet.dev/integrations/anilist-api-mcp-server/triage-anilist-notifications Your AniList notification count keeps growing: likes on a list update, a new follower, two replies under a post and a mention in a forum thread, all in one stream. Cotlet does it in your own AniList account with list\_notifications, list\_activity and reply\_to\_activity, called by your AI agent, an n8n workflow or a script. [Sign up free](https://cotlet.dev/app/signup?app=anilist) [All AniList tools](https://cotlet.dev/integrations/anilist-api-mcp-server.md) Hosted · nothing to install or maintain ## Can AniList do this on its own? AniList's GraphQL API can do this (checked 17 Oct 2026). The Notification query returns notifications of a chosen type, and the SaveActivityReply mutation posts a reply. Both need an OAuth token and your own code. There is no official MCP server, so nothing lets an agent triage the feed without a custom integration. ## How you do it in AniList today 1. Open your notifications on anilist.co and scroll through every type in one list. 2. Open each reply or mention to read it with the activity it belongs to. 3. Write a reply under the activity by hand, one at a time. 4. Open the forum thread for mentions in thread comments, which are separate from activity replies. 5. Repeat daily, because likes and follows bury the few notifications that need an answer. ## How to triage AniList notifications and reply to activity Prompt ``` Read my unread AniList notifications. Summarize likes and follows in one line, and for replies and mentions in my activity draft a short answer. Post the replies I approve. ``` 1. 01 ### Pull unread notifications by type list\_notifications fetches the stream and groups it by type. Likes and follows are counted and summarized in one line, because they need no answer. 2. 02 ### Open what needs a reply For each activity reply or mention, list\_activity loads the activity it points to, so the agent reads your original post and the reply together instead of a bare notification line. 3. 03 ### Draft, do not post The agent writes a short answer in your tone and shows it under the reply it answers. A mention from someone you do not know is flagged, not answered. 4. 04 ### Post the approved replies reply\_to\_activity posts only the drafts you approved. Each call asks for your OK by default, because a reply is public to anyone who can see the activity. 5. 05 ### Clear the count The notification query can reset the unread count when it is read. The agent resets it only after the summary is delivered, so nothing disappears unread. ### What you get back Example data ``` AniList notifications for yourname: 14 unread 9 likes on 3 activities, 2 new followers 2 replies to your activity: both answered, posted after your OK 1 mention in a forum thread: left for you Skipped: 0 ``` ### Other ways to ask - Only tell me about replies and mentions, skip likes and follows entirely. - Every evening, list new followers and show me their top-rated anime so I can decide whom to follow back. - Draft replies to everything under my last text activity, but post nothing. - Tell me when a show I am watching has aired a new episode. ## What AniList allows, and what to know first - NotificationType includes ACTIVITY\_REPLY, ACTIVITY\_MENTION, ACTIVITY\_MESSAGE, FOLLOWING, AIRING and the like types for activities, replies, threads and thread comments. - An AIRING notification means an anime you are currently watching has aired. - An activity reply takes between 2 and 8000 characters. - The notification query has an option to reset the unread notification count to 0 on load. - A mention in a forum comment is its own type, THREAD\_COMMENT\_MENTION, separate from activity mentions. reply\_to\_activity asks for your OK by default. To run it daily without you, switch confirmation off for that tool in your dashboard. Sources: [AniList API Docs: NotificationType](https://docs.anilist.co/reference/enum/notificationtype) · [AniList API Docs: Query reference (Notification, Activity)](https://docs.anilist.co/reference/query) · [AniList API Docs: Mutations reference (SaveActivityReply)](https://docs.anilist.co/reference/mutation) ## Call reply\_to\_activity from a script curl ``` curl -X POST https://cotlet.dev/api/v1/anilist/activities/912345678/replies \ -H "Authorization: Bearer $COTLET_API_KEY" \ -H "Content-Type: application/json" \ -d '{"text":"Thanks! Episode 9 was my favourite too."}' ``` Example response ``` { "reply_id": 77120045, "activity_id": 912345678, "posted": true } ``` MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is anilist\_write → reply\_to\_activity. Example data. [Schedule it in n8n, Make, Zapier or cron](https://cotlet.dev/integrations/anilist-api-mcp-server.md#automations) ## AniList tools this automation uses __Cotlet AniList tools used to triage AniList notifications and reply to activity__ | Tool | Parameters | | ------------------- | ------------------------ | | list\_notifications | type, mark\_read, cursor | | list\_activity | username, type, cursor | | reply\_to\_activity | activity\_id, text | [All 14 AniList tools with descriptions](https://cotlet.dev/integrations/anilist-api-mcp-server.md#tools) ## Frequently asked questions ### Is it safe to connect AniList to Cotlet? Yes. You sign in to AniList yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get AniList once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security. ## More AniList automations - [Update AniList anime list progress and scores](https://cotlet.dev/integrations/anilist-api-mcp-server/update-anime-list-progress.md) - [AniList API and MCP server: every tool](https://cotlet.dev/integrations/anilist-api-mcp-server.md) - [All use cases](https://cotlet.dev/use-cases.md) ## Give your agent access to AniList. Free 7-day trial with 2,000 credits, no card needed. Cotlet is independent and not affiliated with AniList. [Sign up free](https://cotlet.dev/app/signup?app=anilist) --- Give your AI agents your signed-in browser. **Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md) **Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet) **Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) **Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md) **Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors) **Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet) Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners. ## For AI agents: sign your user up Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed. 1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests 2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them. 3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests. One call creates the account and sends the access request; we email the user when access is granted.