Raindrop.io for AI agents
Raindrop.io is a bookmark manager for organizing, tagging, and sharing saved web content. Individuals and teams use it to keep research and reference links organized in collections. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Raindrop.io.
Save a new bookmark
Add a link to a collection with tags so it is easy to find again later.
Search bookmarks read-only
Search saved bookmarks for a topic before starting new research on it.
Delete an empty collection with approval
Remove an unused collection only after confirming it has no bookmarks left.
11 Raindrop.io actions, graded by risk.
Every Raindrop.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- raindrop_io.list_tagsList Tags
- raindrop_io.get_bookmarkGet Bookmark
- raindrop_io.list_bookmarksList Bookmarks
- raindrop_io.list_collectionsList Collections
write
5Create and change things. Allow, or ask the user first.
- raindrop_io.create_bookmarkCreate Bookmark
- raindrop_io.update_bookmarkUpdate Bookmark
- raindrop_io.create_bookmarksCreate Bookmarks
- raindrop_io.create_collectionCreate Collection
- raindrop_io.update_collectionUpdate Collection
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- raindrop_io.delete_bookmarkDelete Bookmark
- raindrop_io.delete_empty_collectionDelete Empty Collection
Raindrop.io in three steps.
- 01Your users connect Raindrop.ioThey add their Raindrop.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Bookmark” can wait for the user, and “delete Bookmark” can be denied outright.
- 03Any agent can actYour agent calls Raindrop.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('raindrop_io', { read: 'allow', write: 'ask', // create_bookmark destructive: 'deny', // delete_bookmark }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Raindrop.io connects.
Users add their Raindrop.io api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Raindrop.io connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Raindrop.io from any agent.
Raindrop.io and Arc0, answered.
Can I use Raindrop.io with Claude, ChatGPT or Cursor?
Yes. Connect Raindrop.io to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Raindrop.io actions you allow.
How do users connect Raindrop.io?
Users add their Raindrop.io api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Raindrop.io actions can my agent take?
11 in total: 4 read, 5 write and 2 destructive, such as “create Bookmark”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Raindrop.io?
Yes. Actions like “delete Bookmark” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Raindrop.io too?
Yes. The same Raindrop.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Raindrop.io into your agent.
Your users connect Raindrop.io once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan