Get Collection Contents
get_collection_contentsFetch one page of the items saved in a collection, or in everything the user saved: iOS screens, iOS flows, web screens, web flows or website sections, one kind per call. id is a collection id from list_collections, the UUID after /collections/ in a Mobbin collection URL (https://mobbin.com/collections//...), or all-saved for everything saved for the user's Mobbin MCP connection. To find one specific item the user saved, read all-saved without asking which collection; it holds every save. Items come newest save first. collection.counts says how many items of each kind the target holds, so you know the number of pages before reading. Read a target in full when it holds 100 screens or sections, or 30 flows, of the kind or fewer. When it holds more, tell the user how many there are, read the first 3 pages, and ask what to look for (an app, a pattern) before reading further, unless they asked for everything. A page can hold fewer than limit items and still have a next page. You can read at most 20 pages of a kind. Older saves past that cannot be fetched here. When has_next_page is false on page 20 and the counts say more remain, tell the user and suggest they gather what they need into a collection. Each item carries the user's team's comments on it, oldest first. Read them: they hold the team's notes on the item, such as why it was saved or what they discussed. Screens list screen_patterns and ui_elements, sections list section_patterns, flows list actions. Use them with app_name or site_name to pick the items that match the request, e.g. the saved login screens or everything saved from Airbnb, instead of using every item. Every preview image follows a text label with the item id (Screen <id>, Section <id>, Flow <id>: screen <n>/<total>; 3 previews per flow). Examine the previews to understand each item's actual content; do not describe items from metadata alone. Inline images are low-res previews for you to read, not for the user. Each result's image_url is the high-resolution image. Whenever the user wants to save, export, embed, or paste a result (files, Figma, Notion, docs, slides), download it from image_url instead of reusing the inline preview. Image URLs expire after 30 days, so download the file rather than linking to it; link to mobbin_url when citing. When you present items, cite each one as a markdown link to its mobbin_url.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>",
"content_type": "<content_type>"
},
"name": "get_collection_contents"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | A collection id from list_collections, or "all-saved" for everything saved for the user's Mobbin MCP connection. | |
| page | No | 1-based page. `has_next_page` says whether another follows. | |
| limit | No | Items per page. Default 20 for screens and sections, 5 for flows. Flows allow at most 10, as each flow inlines 3 previews. Use the same value on every page when paging through a target. Pages are counted in units of `limit`, so changing it skips or repeats items. | |
| platform | No | Required for screens and flows. Ignored for sections. | |
| output_tool | No | The product the results go into next, not a later step, if known, e.g. Figma, Paper, Notion. Product name only. When the results go into more than one product, name the one the user asked for first. Not the search source: Mobbin only when the results go back to Mobbin. Omit when unknown. MUST be the same across all calls for the same task. | |
| task_intent | No | One short sentence summarizing the user's overall task. Helps return more relevant results. Write it in English even when the conversation is in another language. MUST be the same across all calls for the same task. Do NOT include verbatim user messages, conversation history, file contents, or personal data. | |
| content_type | Yes | Which kind of saved item to fetch. | |
| image_format | No | Image format. Use jpg if your client does not support webp. | webp |
| output_destination | No | What you will do with the results after this call. Choose by what gets made with the results, not by the search itself. When the request does not say, go by where you are running: a coding agent in a repository means `code`, a design tool means `design_tool`, a plain chat host means `chat`. Helps return results in the form the workflow needs. `code`: implement or change UI in a codebase or coded prototype, also when looking up examples to base it on first, e.g. React, Swift, HTML/CSS, v0, Lovable. `design_tool`: recreate or put results on a design canvas, e.g. Figma, Paper, Pen.dev, MagicPath. `doc`: write a report, PRD, spec, audit or slides, e.g. in Notion, Google Docs or Slides. `reference_library`: only when saving is the ask: the user wants the results kept for later in a folder, notes or a Mobbin collection. Looking things up to build, design or write from is NOT this. `chat`: only answer in the conversation; the user has not asked you to build, design, write or save anything. `other`: an unlisted destination, none of the above, e.g. posting the results to Slack or email. MUST be the same across all calls for the same task. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| page | Yes | 1-based page number of this batch. | |
| items | Yes | Newest save first. Can hold fewer than `limit` items while `has_next_page` is still true. | |
| collection | Yes | ||
| has_next_page | Yes | Whether another page follows. |