[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)

# Trakt API and MCP server

> Trakt has a full REST API for history, ratings, watchlist, lists and calendars, but no official MCP server (checked 17 Oct 2026). Anyone can register an API app for free, with a verified GitHub account, and sign users in with OAuth 2.0 and PKCE. Trakt tells developers not to scrape its website.

Tracker for movies and TV: your watch history, ratings, watchlist, custom lists and an episode calendar in one account, synced from media centers and apps.

## What is the Trakt API?

Cotlet's Trakt API exposes 15 endpoints for your own Trakt account: search titles, get watchlist, get watch history, get ratings, list your lists, get list items, get calendar, get account limits, add to watchlist, remove from watchlist, mark as watched, remove from history, rate titles, create list and add to list. The search_titles endpoint returns find movies and shows by title and year, with Trakt IDs. Each endpoint takes simple JSON inputs like items, type or page and works both as an operation of the trakt_read or trakt_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Creators & communities](https://cotlet.dev/integrations/category/creators-communities.md)
- **Endpoints:** 15 (8 read, 7 write)
- **Updated:** 2026-10-21

Trakt has a full REST API for history, ratings, watchlist, lists and calendars, but no official MCP server (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for Trakt with 15 endpoints (8 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Trakt have an official API?

Trakt has a full REST API for history, ratings, watchlist, lists and calendars, but no official MCP server (checked 17 Oct 2026). Anyone can register an API app for free, with a verified GitHub account, and sign users in with OAuth 2.0 and PKCE. Trakt tells developers not to scrape its website.

| Task | Trakt official | Cotlet |
|---|---|---|
| Search movies and shows | Yes: REST API search; you wire the app key and headers yourself | Yes |
| Read watchlist, history and ratings | Yes: REST API with OAuth and paging | Yes |
| Add and remove watchlist items | Yes: REST API; the watchlist item limit depends on the account, VIP raises it | Yes |
| Mark movies and episodes as watched | Yes: REST API; it does not check for duplicate plays, your client has to | Yes |
| Rate movies, shows and episodes | Yes: REST API, ratings 1 to 10 | Yes |
| Create and fill custom lists | Yes: REST API; the number of lists and items per list depends on the account | Yes |
| Read your calendar of upcoming episodes | Yes: REST API, up to 33 days per call | Yes |
| Read your account limits | Yes: REST API settings call | Yes |

Sources: [Trakt API: Introduction](https://docs.trakt.tv/docs/getting-started), [Trakt API: Create an App](https://docs.trakt.tv/docs/create-an-app), [Trakt API: API Use Policy](https://docs.trakt.tv/docs/api-use-policy), [Trakt API: User Account Limits](https://docs.trakt.tv/docs/user-account-limits)

## For AI agents

```text
Trakt has a full REST API for history, ratings, watchlist, lists and calendars, but no official MCP server (checked 17 Oct 2026). Anyone can register an API app for free, with a verified GitHub account, and sign users in with OAuth 2.0 and PKCE. Trakt tells developers not to scrape its website.
Cotlet provides a hosted MCP server and REST API for Trakt: 15 tools (8 read, 7 write).
Access       Sign up at https://cotlet.dev/app/signup?app=trakt, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    trakt_read, trakt_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/trakt, each operation at its own route, e.g. POST /api/v1/trakt/watchlists
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   search_titles, get_watchlist, get_history, get_ratings, list_lists, get_list_items, get_calendar, get_account_limits, add_to_watchlist, remove_from_watchlist, add_to_history, remove_from_history, rate_titles, create_list, add_to_list
Confirm      create_list, add_to_list (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/trakt-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=trakt, requests Trakt in the Cotlet console and creates an API key there.
2. The user signs in to Trakt once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Trakt for agents. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Trakt server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Trakt MCP server instead.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Trakt in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Trakt only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Trakt login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Trakt's terms; Cotlet is not affiliated with Trakt.
```

## What can an AI agent do in Trakt?

Cotlet is best for Trakt users who want their AI agent to manage watchlists, history, ratings and lists without running or fixing a server.

- **[Add a list of titles to your watchlist](https://cotlet.dev/integrations/trakt-api-mcp-server/bulk-add-to-watchlist.md)**: "Add these to my Trakt watchlist: Past Lives (2023), Slow Horses (2022) and Perfect Days (2023). Skip anything already on it and tell me which titles you could not match." → `search_titles`, `get_watchlist`, `add_to_watchlist`
- **[Log watched episodes in bulk](https://cotlet.dev/integrations/trakt-api-mcp-server/log-watched-episodes.md)**: "Mark Slow Horses season 4, episodes 1 to 3 as watched on 2026-10-10. Check my history first so nothing is logged twice." → `search_titles`, `get_history`, `add_to_history`
- **Rate everything you watched this month** (runs: weekly): "List what I watched in the last 30 days that I have not rated, and propose ratings from 1 to 10 from my past ratings. Rate only what I approve." → `get_history`, `get_ratings`, `rate_titles`
- **Build a themed list from your watchlist**: "Create a private list called "Cozy autumn" and add the five shortest shows from my watchlist to it." → `get_watchlist`, `create_list`, `add_to_list`
- **Send a weekly calendar digest** (runs: weekly): "Every Sunday, list the episodes of my shows airing in the next 7 days, grouped by day." → `get_calendar`

## Can Trakt automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Trakt connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to rate everything you watched this month, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/trakt/history. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/trakt/history with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 15 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Trakt.

### search_titles

Find movies and shows by title and year, with Trakt IDs. Access: read. REST: `GET /api/v1/trakt/titles/search`. MCP: `trakt_read → search_titles`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `query` | string | yes | Title to look for. |
| `type` | string | no | 'movie' or 'show'. Default: both. |
| `year` | integer | no | Release year, to separate titles with the same name. |

Returns matches for a text query, best match first, each with its Trakt ID, title, year and type. Use the ID in the write tools when a title has several matches. Returns at most one page of results per call.

Example response:

```json
{
  "results": [
    {
      "type": "movie",
      "trakt_id": 548210,
      "title": "Past Lives",
      "year": 2023
    },
    {
      "type": "show",
      "trakt_id": 401992,
      "title": "Slow Horses",
      "year": 2022
    }
  ]
}
```

### get_watchlist

Titles on your watchlist with the date each was added. Access: read. REST: `GET /api/v1/trakt/watchlist`. MCP: `trakt_read → get_watchlist`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `type` | string | no | Only this kind of title: 'movies', 'shows', 'seasons' or 'episodes'. Default: all. |
| `page` | integer | no | Page number, starting at 1. Default: 1. |
| `limit` | integer | no | Items per page. Default: 20. |

Returns your watchlist in pages, with the type, title, year and the date each item was added. Filter by type to see only movies or only shows. Use it before adding, so you do not add a title twice.

Example response:

```json
{
  "items": [
    {
      "type": "show",
      "trakt_id": 401992,
      "title": "Slow Horses",
      "year": 2022,
      "added_at": "2026-10-02T18:20:00Z"
    },
    {
      "type": "movie",
      "trakt_id": 548210,
      "title": "Past Lives",
      "year": 2023,
      "added_at": "2026-09-28T09:05:00Z"
    }
  ],
  "page": 1,
  "total_pages": 1
}
```

### get_history

What you watched and when, newest first. Access: read. REST: `GET /api/v1/trakt/history`. MCP: `trakt_read → get_history`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `type` | string | no | Only this kind of title: 'movies', 'shows', 'seasons' or 'episodes'. Default: all. |
| `start_at` | datetime | no | Only plays after this time. |
| `end_at` | datetime | no | Only plays before this time. |
| `page` | integer | no | Page number, starting at 1. Default: 1. |
| `limit` | integer | no | Items per page. Default: 20. |

Returns your watch history in pages, newest first, with the date of each play. A title watched twice appears twice. Filter by type or by a start and end date to check a batch you logged.

Example response:

```json
{
  "items": [
    {
      "type": "episode",
      "show": "Slow Horses",
      "season": 4,
      "episode": 3,
      "title": "Hello Goodbye",
      "watched_at": "2026-10-10T21:40:00Z"
    },
    {
      "type": "movie",
      "title": "Perfect Days",
      "year": 2023,
      "watched_at": "2026-10-06T19:30:00Z"
    }
  ],
  "page": 1,
  "total_pages": 4
}
```

### get_ratings

Your ratings from 1 to 10 for movies, shows, seasons and episodes. Access: read. REST: `GET /api/v1/trakt/ratings`. MCP: `trakt_read → get_ratings`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `type` | string | no | Only this kind of title: 'movies', 'shows', 'seasons' or 'episodes'. Default: all. |
| `rating` | integer | no | Only titles with this score, 1 to 10. |
| `page` | integer | no | Page number, starting at 1. Default: 1. |
| `limit` | integer | no | Items per page. Default: 20. |

Returns the titles you rated with your score and the date you rated them. Filter by type or by a score to find, for example, everything you gave a 10. Use it to match the tone of earlier scores before proposing new ones.

Example response:

```json
{
  "items": [
    {
      "type": "movie",
      "title": "Past Lives",
      "year": 2023,
      "rating": 9,
      "rated_at": "2026-09-30T22:10:00Z"
    },
    {
      "type": "show",
      "title": "Slow Horses",
      "year": 2022,
      "rating": 8,
      "rated_at": "2026-08-14T20:00:00Z"
    }
  ],
  "page": 1,
  "total_pages": 6
}
```

### list_lists

Your custom lists with name, privacy and item count. Access: read. REST: `GET /api/v1/trakt/lists`. MCP: `trakt_read → list_lists`.

No parameters.

Returns your personal lists with their ID, name, privacy setting ('private', 'link', 'friends' or 'public') and number of items. Use the ID in get_list_items and add_to_list.

Example response:

```json
{
  "lists": [
    {
      "list_id": "cozy-autumn",
      "name": "Cozy autumn",
      "privacy": "private",
      "item_count": 5
    },
    {
      "list_id": "movie-night",
      "name": "Movie night",
      "privacy": "friends",
      "item_count": 12
    }
  ]
}
```

### get_list_items

The titles on one of your lists, in list order. Access: read. REST: `GET /api/v1/trakt/lists/{list_id}/items`. MCP: `trakt_read → get_list_items`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `list_id` | string | yes | List ID or slug from list_lists. |
| `page` | integer | no | Page number, starting at 1. Default: 1. |
| `limit` | integer | no | Items per page. Default: 20. |

Returns the items of one list in the order of the list, in pages. Each item has its type, title, year and Trakt ID.

Example response:

```json
{
  "items": [
    {
      "type": "show",
      "trakt_id": 401992,
      "title": "Slow Horses",
      "year": 2022
    },
    {
      "type": "movie",
      "trakt_id": 548210,
      "title": "Past Lives",
      "year": 2023
    }
  ],
  "page": 1,
  "total_pages": 1
}
```

### get_calendar

Episodes of your shows airing in the coming days. Access: read. REST: `GET /api/v1/trakt/calendar`. MCP: `trakt_read → get_calendar`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `start_date` | date | no | First day, YYYY-MM-DD. Default: today. |
| `days` | integer | no | 1 to 33. Default: 7. |

Returns the episodes airing from a start date for a number of days, in air order, with show, season, episode and air time in UTC. Your calendar covers shows you watched or watchlisted, minus hidden shows. A call covers at most 33 days.

Example response:

```json
{
  "days": [
    {
      "date": "2026-10-19",
      "episodes": [
        {
          "show": "Slow Horses",
          "season": 5,
          "episode": 1,
          "title": "Cold Open",
          "first_aired": "2026-10-19T01:00:00Z"
        }
      ]
    },
    {
      "date": "2026-10-21",
      "episodes": [
        {
          "show": "Severance",
          "season": 3,
          "episode": 4,
          "title": "The Long Floor",
          "first_aired": "2026-10-21T01:00:00Z"
        }
      ]
    }
  ]
}
```

### get_account_limits

Your VIP status and limits for lists and the watchlist. Access: read. REST: `GET /api/v1/trakt/account-limits`. MCP: `trakt_read → get_account_limits`.

No parameters.

Returns whether the account is Trakt VIP and the limits Trakt sets for it: personal lists, items per list and watchlist items. Limits differ by account and change over time, so call it before a large add.

Example response:

```json
{
  "vip": false,
  "limits": {
    "lists": 2,
    "items_per_list": 100,
    "watchlist_items": 100
  }
}
```

### add_to_watchlist

Add movies and shows to your watchlist in one call. Access: write. REST: `POST /api/v1/trakt/watchlists`. MCP: `trakt_write → add_to_watchlist`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `items` | array | yes | Titles to change. Each item is an object: type ('movie', 'show', 'season' or 'episode'), title and year, or trakt_id from search_titles. Seasons and episodes also take season and episode numbers. add_to_history also takes watched_at, rate_titles takes rating. |

Adds the given titles to your watchlist. A show on its own adds just the show. Titles already on the watchlist are counted, not added twice, and titles Trakt cannot match come back in not_found. The call fails with an account-limit error if the watchlist is full. It reaches no one and remove_from_watchlist undoes it, so it needs no confirmation.

Example response:

```json
{
  "added": {
    "movies": 2,
    "shows": 1
  },
  "already_on_watchlist": 0,
  "not_found": []
}
```

### remove_from_watchlist

Take titles off your watchlist. Access: write. REST: `DELETE /api/v1/trakt/watchlists`. MCP: `trakt_write → remove_from_watchlist`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `items` | array | yes | Titles to change. Each item is an object: type ('movie', 'show', 'season' or 'episode'), title and year, or trakt_id from search_titles. Seasons and episodes also take season and episode numbers. add_to_history also takes watched_at, rate_titles takes rating. |

Removes the given titles from your watchlist. Titles that are not on it come back in not_found. It reaches no one, and add_to_watchlist puts a title back, so it needs no confirmation.

Example response:

```json
{
  "removed": {
    "movies": 1,
    "shows": 0
  },
  "not_found": []
}
```

### add_to_history

Log movies and episodes as watched, with the date of the watch. Access: write. REST: `POST /api/v1/trakt/histories`. MCP: `trakt_write → add_to_history`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `items` | array | yes | Titles to change. Each item is an object: type ('movie', 'show', 'season' or 'episode'), title and year, or trakt_id from search_titles. Seasons and episodes also take season and episode numbers. add_to_history also takes watched_at, rate_titles takes rating. |

Adds plays to your history. A show with no seasons logs every episode, so name seasons and episodes when you mean a few. A watched_at in the past is accepted. Trakt does not check for duplicate plays, so use get_history first. It reaches no one and remove_from_history undoes it, so it needs no confirmation.

Example response:

```json
{
  "added": {
    "movies": 0,
    "episodes": 3
  },
  "skipped_duplicates": 0,
  "not_found": []
}
```

### remove_from_history

Delete plays from your watch history. Access: write. REST: `DELETE /api/v1/trakt/histories`. MCP: `trakt_write → remove_from_history`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `items` | array | yes | Titles to change. Each item is an object: type ('movie', 'show', 'season' or 'episode'), title and year, or trakt_id from search_titles. Seasons and episodes also take season and episode numbers. add_to_history also takes watched_at, rate_titles takes rating. |

Removes the given titles from your history, all plays of each one. Use get_history first to see which plays you are deleting. add_to_history logs a play again with a date. It reaches no one, so it needs no confirmation.

Example response:

```json
{
  "removed": {
    "movies": 0,
    "episodes": 1
  },
  "not_found": []
}
```

### rate_titles

Rate movies, shows, seasons or episodes from 1 to 10. Access: write. REST: `POST /api/v1/trakt/titles/rate`. MCP: `trakt_write → rate_titles`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `items` | array | yes | Titles to rate. Each item is an object like the items of add_to_watchlist plus rating (integer, 1 to 10). |

Sets your rating on each title. A new score replaces the old one. Each item takes a rating field next to the title. It reaches no one and sending another rating changes it, so it needs no confirmation.

Example response:

```json
{
  "rated": {
    "movies": 1,
    "shows": 1
  },
  "not_found": []
}
```

### create_list

Create a custom list with a name, a description and a privacy setting. Access: write, asks the user first. REST: `POST /api/v1/trakt/lists`. MCP: `trakt_write → create_list`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `name` | string | yes | Name of the list. |
| `description` | string | no | Short description. |
| `privacy` | string | no | 'private', 'link', 'friends' or 'public'. Default: 'private'. |

Creates an empty personal list. Privacy is 'private' unless you set it, and 'friends', 'link' or 'public' make the list visible to other people. The call fails with an account-limit error when you are at your list limit. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "list_id": "cozy-autumn",
  "name": "Cozy autumn",
  "privacy": "private",
  "item_count": 0
}
```

### add_to_list

Add titles to one of your custom lists. Access: write, asks the user first. REST: `POST /api/v1/trakt/lists/{list_id}`. MCP: `trakt_write → add_to_list`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `list_id` | string | yes | List ID or slug from list_lists. |
| `items` | array | yes | Titles to change. Each item is an object: type ('movie', 'show', 'season' or 'episode'), title and year, or trakt_id from search_titles. Seasons and episodes also take season and episode numbers. add_to_history also takes watched_at, rate_titles takes rating. |

Adds the given titles to a list. Titles already on it come back as already_on_list and the call fails with an account-limit error when the list is full. If the list is public, other people see the change. Use list_lists to check the privacy first. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "added": {
    "movies": 0,
    "shows": 5
  },
  "already_on_list": 0,
  "not_found": []
}
```

## How do I connect Trakt to Claude Code, Codex or Cursor?

Connecting Trakt takes three steps: sign up, sign in to Trakt once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key.

### Connect Trakt to your agent.

1. **Create an account** Sign up and add Trakt in the console. Your API key is there too.

2. **Sign in to Trakt in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Trakt there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

   Claude Code:

```
claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"
```

   Cursor:

```
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}
```

   Codex:

```
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
```

4. **Ask your agent** Ask in plain words. Your agent finds the Trakt tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.

```
Add these to my Trakt watchlist: Past Lives (2023), Slow Horses (2022) and Perfect Days (2023). Skip anything already on it and tell me which titles you could not match.
```

### Call Trakt from your scripts.

1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.

```
export COTLET_API_KEY="cotlet_..."
```

2. **Call a tool** Every tool is an endpoint under /api/v1/trakt with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.

```
curl -X POST https://cotlet.dev/api/v1/trakt/watchlists \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"items":[{"type":"movie","title":"Past Lives","year":2023},{"type":"show","title":"Slow Horses","year":2022},{"type":"movie","title":"Perfect Days","year":2023}]}'
```

3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing.

```
{
  "added": {
    "movies": 2,
    "shows": 1
  },
  "already_on_watchlist": 0,
  "not_found": []
}
```

## Why use Cotlet for Trakt?

**Built for agents**

- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with Claude Code, Codex and Cursor.

**Your login stays yours**

- You sign in to Trakt yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no CAPTCHA solving, no MFA bypass.

**You stay in control**

- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.

**Kept working for you**

- We test every integration every 6 hours.
- When Trakt changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Trakt to Cotlet?

Yes. You sign in to Trakt yourself, in your own Cloud Browser, and we never save your password. Your agents only get Trakt once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

- **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev)
- **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on)
- **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev)
- **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev)

[How Cotlet protects your access](https://cotlet.dev/security.md)

### Common concerns

**Who runs Cotlet?**

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

**Is this an official Trakt integration?**

No, Cotlet is independent of Trakt. Trakt's own API is too limited for this work. Cotlet works through your own Trakt account, the way you use Trakt in the browser, so you need no partner approval and no developer setup.

**What about client data and GDPR?**

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

**Can I start with read only?**

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

**Is it reliable?**

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

**How do I stop?**

Press Disable for agents next to Trakt in your console: your agents lose access at once and you stay signed in. Signing out of Trakt in the browser works too, and Reset browser deletes the whole profile.

## Is there a Trakt MCP server on GitHub?

Yes. Community Trakt MCP servers exist on GitHub, usually maintained by one person. You install one yourself, register your own Trakt API app, handle the OAuth sign-in and fix the server when something changes. Cotlet hosts the same kind of server for you, with no API app and no token to run, and our team keeps it working.

|  | GitHub MCP server | Cotlet |
|---|---|---|
| Setup | Clone the repo, register a Trakt API app with a verified GitHub account, store the client ID and tokens, add the server to each MCP client | Sign up, sign in to Trakt once, add one MCP server or API key |
| When Trakt changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your Trakt session | OAuth tokens in a file on your computer, readable by any program you run | In your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When the session expires | Tools fail until you refresh the token or sign in again by hand | Your Cloud Browser keeps you signed in; if Trakt logs you out, your agent gets a link to sign in again |
| Upkeep | You update, monitor and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |

### Which one fits you

**Pick Cotlet if**

- you are not a developer, or you do not want to maintain a server
- you need it to keep working when Trakt changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off

**Pick an open-source server if**

- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client

## How much does the Trakt API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Trakt API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 20 to 30 credits (25 for most tools, about $0.10 to $0.15), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

| Credits | Price, one time | Calls at 25 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 200 | $5.80 |
| 15,000 | $79 | 600 | $5.27 |
| 32,000 | $149 | 1,280 | $4.66 |
| 60,000 | $249 | 2,400 | $4.15 |

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md)

## How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Trakt account.

- **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms)
- **Your sign-in:** You sign in to Trakt yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Trakt only after you enable it. When Trakt signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md)
- **Revoking access:** Press Disable for agents next to Trakt, sign out of Trakt in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA.
- **Trakt's terms:** You use your own Trakt account and stay responsible for following Trakt's terms. Cotlet is independent and not affiliated with Trakt. [Terms](https://cotlet.dev/terms)
- **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev)

## Frequently asked questions

**How do I get access?**

Sign up free, open Trakt in the console and press Request access. Then you create your API key and connect Trakt there.

**Do I need to be technical?**

No. You sign in to Trakt once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

**Is it safe to connect Trakt to Cotlet?**

Yes. You sign in to Trakt yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Trakt 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.

**Is a hosted server safer than a local one? My Trakt sign-in would leave my computer.**

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Trakt cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

**Why does Cotlet send requests instead of clicking in my browser?**

To be fast, Cotlet doesn't click through Trakt's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Trakt sees the same browser and IP you signed in with, and every request is listed in your Background activity.

**What if someone gets my Cotlet API key?**

The key holds no Trakt login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

**Why a signed-in browser and not OAuth, like other integration platforms?**

Trakt offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

**Do I need Trakt VIP?**

No. Cotlet works in your own Trakt account, free or VIP. Trakt sets limits on lists and watchlist items by account, and VIP raises some of them, so get_account_limits shows what your account allows (Trakt API: User Account Limits, checked 17 Oct 2026).

**Does Trakt allow automation of my account?**

Trakt's API use policy permits tools that help a person manage their own watch history, ratings and lists, and forbids bulk harvesting of its data and posting spam (checked 17 Oct 2026). Cotlet acts only inside your own account, one call at a time, and does not collect Trakt data for anyone else.

**Can my agent post or send messages in Trakt without asking me?**

No. Every call to create_list or add_to_list waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. add_to_watchlist, remove_from_watchlist, add_to_history, remove_from_history, rate_titles runs without asking, because it sends nothing to anyone and one call undoes it.

**Can I use the Trakt API in n8n?**

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/trakt from the HTTP Request node.

---

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.