Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to Raindrop

Scalekit connector
Open markdown

The Raindrop connector lets your AI agent act in each user's Raindrop account. Each user signs in to Raindrop once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 37 tools.

Tools
37
What they doRead · write · destructive
17 · 11 · 917 read11 write9 destructive
Users sign in with
OAuth app
Your own Raindrop app

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv
  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>
  3. Create the Raindrop connection

    In AgentKit > Connections, create a Raindrop connection and copy its redirect URI. The name you give it is the connection_name your code passes. See Configure connections.

  4. Register an OAuth app

    Raindrop connections use your own OAuth app. Register one with Raindrop and add the redirect URI you copied.

    Then enter the app's Client ID and Client Secret on the Raindrop connection.

  5. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    const scalekit = new ScalekitClient(
    process.env.SCALEKIT_ENVIRONMENT_URL,
    process.env.SCALEKIT_CLIENT_ID,
    process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    const connector = 'raindrop'
    const identifier = 'user_123'
    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize Raindrop:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    // Make your first call
    const result = await actions.executeTool({
    connector,
    identifier,
    toolName: 'raindrop_get_collection_counts',
    toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • raindrop_check_urls_existCheck whether URLs are already saved as bookmarks.Read-only

    Check URLs Exist

    Check whether URLs are already saved as bookmarks. Returns result true and an ids array holding the IDs of the matching existing bookmarks; the array is empty or the result is false when none match. Use before raindrop_create_bookmark or raindrop_create_bookmarks to avoid duplicates. Does not change anything.

    Inputs

    urlsarrayrequired
    URLs to look up, as an array of strings including scheme.
  • raindrop_get_bookmarkRetrieve one bookmark (raindrop) by ID.Read-only

    Get Bookmark

    Retrieve one bookmark (raindrop) by ID. Returns the bookmark's _id, title, link, excerpt, note, tags, type, cover, collection, highlights, important flag and timestamps. Use raindrop_list_bookmarks to find bookmark IDs or to search.

    Inputs

    bookmark_idintegerrequired
    Numeric ID of the bookmark (raindrop). Use the _id returned by raindrop_list_bookmarks or raindrop_create_bookmark.
  • raindrop_get_collectionRetrieve one collection by ID.Read-only

    Get Collection

    Retrieve one collection by ID. Returns the collection's _id, title, count, color, cover, view, public flag, access level, sharing info, parent and timestamps. Use raindrop_list_collections to discover collection IDs first.

    Inputs

    collection_idintegerrequired
    Numeric ID of the collection. Use the ID returned by raindrop_list_collections.
  • raindrop_get_collection_countsRetrieve bookmark counts for the system collections (All, Unsorted, Trash) plus account-level broken-link and duplicate counts.Read-only

    Get Collection Counts

    Retrieve bookmark counts for the system collections (All, Unsorted, Trash) plus account-level broken-link and duplicate counts. Returns an items array of {_id, count} for collection IDs 0 (all), -1 (Unsorted) and -99 (Trash), and a meta object with PRO status and the broken and duplicate counts. Use raindrop_list_collections for user-created collections. Use raindrop_get_filters for counts inside one collection.

    Inputs

    This tool takes no inputs.

  • raindrop_get_filtersGet filter counts for a collection: bookmarks by type, tags, favorites, untagged, broken and duplicates.Read-only

    Get Filters

    Get filter counts for a collection: bookmarks by type, tags, favorites, untagged, broken and duplicates. Returns broken, duplicates, important and notag counts plus tags and types arrays of {_id, count}. Use raindrop_list_bookmarks with a search query to fetch the matching bookmarks.

    Inputs

    collection_idintegerrequired
    Collection to compute filters for. Use 0 for all collections.
    searchstring
    Search query to restrict the counted bookmarks, same syntax as raindrop_list_bookmarks.
    tags_sortstring
    Sort of the tags list: -count (by usage, default) or _id (by name).one of -count_id
  • raindrop_get_userRetrieve the profile of the Raindrop user who authorized the connection.Read-only

    Get Authenticated User

    Retrieve the profile of the Raindrop user who authorized the connection. Returns the user ID, full name, email, PRO status and expiry, file storage usage, collection groups and preferences. Use this to confirm which account is connected. Use raindrop_get_collection_counts for bookmark totals.

    Inputs

    This tool takes no inputs.

  • raindrop_list_bookmarksList bookmarks (raindrops) in a collection, with optional search, sorting and paging.Read-only

    List Bookmarks

    List bookmarks (raindrops) in a collection, with optional search, sorting and paging. Returns an items array of bookmarks (_id, title, link, excerpt, note, tags, type, collection, created) and the total count. Use raindrop_get_bookmark for one bookmark by ID. Pass collection_id 0 for all bookmarks, -1 for Unsorted or -99 for Trash.

    Inputs

    collection_idintegerrequired
    Collection to read from. Use 0 for all bookmarks except Trash, -1 for Unsorted, -99 for Trash, or a collection ID from raindrop_list_collections.
    nestedboolean
    Set true to also include bookmarks from nested sub-collections.
    pageinteger
    Zero-based page number. Combine with perpage to page through results.
    perpageinteger
    Bookmarks per page, maximum 50.
    searchstring
    Search query using Raindrop search syntax, for example 'javascript #dev' or 'domain:github.com'. Omit to list everything.
    sortstring
    Sort order: -created (newest first, default), created, score (relevance, only with search), -sort (manual order), title, -title, domain or -domain.one of -createdcreatedscore-sorttitle-titledomain-domain
  • raindrop_list_child_collectionsList all nested (child) collections of the authenticated user.Read-only

    List Child Collections

    List all nested (child) collections of the authenticated user. Returns the same fields as raindrop_list_collections plus parent.$id for each collection, which links it to its parent. Use raindrop_list_collections for root collections. Combine both lists to rebuild the full collection tree.

    Inputs

    This tool takes no inputs.