Files and knowledge
Raindrop.io for AI agents.
Make saved research easy to use.
Find collections and bookmarks in a user’s Raindrop.io library. Prepare research briefs grounded in saved links and their returned metadata.
About Raindrop.io
With the Raindrop.io connector, your agent reads bookmarks in each user’s own Raindrop.io library. It can list collections, search bookmarks, and read the details of a saved link, using only the tools your project allows.
Raindrop.io is a bookmark manager for saving and organizing links.
Tools
What your agent can do in Raindrop.io.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Raindrop.io connection.
-
List root collections
Readraindrop_io_list_collectionsFind the connected user’s top-level collections.
-
List child collections
Readraindrop_io_list_child_collectionsFind child collections under accessible collection folders.
-
Read a collection
Readraindrop_io_get_collectionRetrieve one identified collection and its returned metadata.
-
List bookmarks
Readraindrop_io_list_bookmarksRead saved links in one collection with the requested result scope.
-
Search bookmarks
Readraindrop_io_search_bookmarksSearch saved links in the connected user’s library.
-
Read a bookmark
Readraindrop_io_get_bookmarkRetrieve one identified saved link and its returned metadata.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Raindrop.io, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent browse collections and bookmarks, and switch off
raindrop_io_search_bookmarksif it should only list them. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example collections but not individual bookmarks. A call outside them is refused.
Get started
Connect Raindrop.io
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Raindrop.io
Each end user authorizes their own Raindrop.io account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Raindrop.io account, once. const connection = await agent200 .user("user_123") .connect("raindrop_io"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Raindrop.io tools
Name the user, the model and the tools. The model decides which Raindrop.io tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Find my saved links about vector databases", tools: ["raindrop_io"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Connect the intended Raindrop.io account
Have the end user authorize the registered Agent200 application through Raindrop.io OAuth. Select the user’s intended library and collection before reading saved links.
-
Respect the connected user’s library
Collection and bookmark results come from the authorized account. Resolve a collection ID when names are similar and follow pagination for larger reading lists.
-
Keep the application user stable
Use the same authenticated application user for authorization and later requests. Keep the Agent200 key in secure server configuration.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Raindrop.io connector and how to use it.
Connector: Raindrop.io, through Agent200. In code: "raindrop_io". What it does: Find collections and bookmarks in a user’s Raindrop.io library. Prepare research briefs grounded in saved links and their returned metadata. Page: https://www.agent200.com/connectors/raindrop-io/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Raindrop.io's own page, through the authorization link Agent200 returns. Never ask a user for a Raindrop.io password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: raindrop_io_list_collections, raindrop_io_list_child_collections, raindrop_io_get_collection, raindrop_io_list_bookmarks, raindrop_io_search_bookmarks, raindrop_io_get_bookmark. Name "raindrop_io" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/raindrop-io/framework/claude/ https://www.agent200.com/connectors/raindrop-io/framework/chatgpt/ https://www.agent200.com/connectors/raindrop-io/framework/claude-code/ https://www.agent200.com/connectors/raindrop-io/framework/muse/ https://www.agent200.com/connectors/raindrop-io/framework/grok-bot/ https://www.agent200.com/connectors/raindrop-io/framework/openai-dots/ https://www.agent200.com/connectors/raindrop-io/framework/claude-duet/ https://www.agent200.com/connectors/raindrop-io/framework/hermes-agent/ https://www.agent200.com/connectors/raindrop-io/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/raindrop-io.md
Guides
Use Raindrop.io with the AI you build on.
Step-by-step setup for Raindrop.io with a specific model, assistant or agent framework.
-
Raindrop.io + Claude
How to connect Raindrop.io to Claude
-
Raindrop.io + ChatGPT
How to connect Raindrop.io to ChatGPT
-
Raindrop.io + Claude Code
How to connect Raindrop.io to Claude Code
-
Raindrop.io + Muse
How to connect Raindrop.io to Muse
-
Raindrop.io + Grok Bot
How to connect Raindrop.io to Grok Bot
-
Raindrop.io + OpenAI Dots
How to connect Raindrop.io to OpenAI Dots
-
Raindrop.io + Claude Duet
How to connect Raindrop.io to Claude Duet
-
Raindrop.io + Hermes Agent
How to connect Raindrop.io to Hermes Agent
-
Raindrop.io + OpenClaw
How to connect Raindrop.io to OpenClaw
FAQ
Raindrop.io and Agent200, answered.
What does a bookmark result contain?
The API returns saved-link fields such as title, link, description, tags and collection identifiers when available. A bookmark record is not proof that the linked article’s full text was read. Raindrop.io bookmark reference.
How do I find bookmarks in nested collections?
Raindrop.io separates top-level and child collection endpoints. Fetch both when the requested folder may be nested, then use the returned collection ID. Nested collections reference.
Does a search return the whole library?
No. Search and list responses can be paginated. State the query, collection and result scope used; do not infer that absent results mean no saved bookmark exists.
Can the agent save or edit bookmarks?
The listed tools are read operations. A suggested reading list in an answer does not add, edit or delete saved links.
How is access granted?
Raindrop.io documents OAuth authorization for registered applications. The end user authorizes the account used for the read; inspect the runtime’s advertised schemas before calling any tool. OAuth reference.