Raindrop.io + Claude Duet
Connect Raindrop.io to Claude Duet
Prepare a grounded research brief
Read bookmarks with Claude Duet and Agent200. Prepare a research brief using the connected user’s own Raindrop.io account.
On this page
Overview
Request an on-demand research brief in Claude Duet. Ask it to name retrieved sources and missing information. This request does not establish continuous monitoring.
Start with one identified bookmark. Preserve returned collection identity, bookmark title, URL, description, tags and other fields actually returned; report missing data and keep the workflow read-only.
Provider reference: Raindrop.io API.
- Connector
- Raindrop.io
- Works with
- Claude Duet · Agent app, through MCP
- Authentication
- Managed OAuth, per end user
- You need
- An Agent200 API key
- Tools
- 6 tools
- MCP server
https://api.agent200.com/mcp/
Before you start
- An Agent200 API key. Create one on the API keys page of the dashboard.
- Raindrop.io enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- An end user with a Raindrop.io account. They approve access once, on Raindrop.io's own page.
- Claude Duet, with custom MCP servers allowed. Claude Duet is a research preview for Pro, Max and Ultra users in the US, by invitation. It uses the connectors of your Claude account, and sending an API key needs Claude's Request headers option.
Connect Raindrop.io to Claude Duet
-
1
Step 1: Create your Agent200 API key
Open the API keys page in the Agent200 dashboard and choose Create an API key. You add it to Claude Duet in the next step, as "Authorization: Bearer <your key>". One key covers Raindrop.io and every other connector enabled for your project. Keep it out of chats and source control.
-
2
Step 2: Add Agent200 as a custom connector in Claude
Duet has no connector settings of its own: it uses those of your Claude account. In Claude, go to Customize > Connectors, choose Add > Add custom connector, enter the server URL, choose No sign-in and add the
authorizationrequest header withBearerand your key.Add custom connectorMCP: Claude custom connector (URL and request header) Remote MCP server URL: https://api.agent200.com/mcp/ Authentication: No sign-in Request header name: authorization Value: Bearer YOUR_AGENT200_API_KEY -
3
Step 3: Use it from Duet
Open Claude Duet with the same Claude account. The connectors set up in Claude are there from your first message; manage them in your Claude settings.
-
4
Step 4: Approve actions when Duet asks
Duet asks before it sends a message, pays, signs or deletes anything. If you cannot approve right away, it finishes the rest and brings the approval back later.
-
5
Step 5: Connect your Raindrop.io account
The first time you ask Claude Duet for something in Raindrop.io, Agent200 returns an authorization link. Open it and approve access on Raindrop.io's own page. Agent200 stores the connection and keeps it working; your password never reaches Claude Duet or Agent200.
Test your connection
Run one request to check everything is wired up.
Ask
Find the Raindrop.io collection I name and list relevant saved links. Prepare a concise research brief from returned bookmark titles, URLs, descriptions and tags. Identify the collection and disclose when the linked pages themselves were not read. Do not change bookmarks.
What should come back
- The selected bookmark is identified.
- Only returned collection identity, bookmark title, URL, description, tags and other fields actually returned are reported.
- Access gaps and missing context are explicit; no source data is changed.
Check the connected account, collection ID, search query and pagination. A bookmark record may lack a description or tag; report the gap without inventing page content.
Get your API key
Create a key in the Agent200 dashboard. It reaches Raindrop.io and every other connector enabled for your project.
Instructions for AI agents
Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Raindrop.io to Claude Duet.
Goal: connect Raindrop.io to Claude Duet with Agent200, through its MCP server. Guide: https://www.agent200.com/connectors/raindrop-io/framework/claude-duet/ 1. The user needs an Agent200 API key. If they have none, send them to https://agent200.com/platform/apikeys/ to choose "Create an API key". They paste it into Claude Duet's settings themselves: never ask for it in chat and never write it into files you share. 2. Make sure Raindrop.io is enabled for their project in the Agent200 dashboard (Connectors), with the tools the task needs. 3. Add Agent200's MCP server to Claude Duet: URL https://api.agent200.com/mcp/, transport streamable HTTP, header "Authorization: Bearer <the user's Agent200 API key>". Follow the setup steps on the guide page for Claude Duet's exact menus or commands. 4. The first Raindrop.io request returns an authorization link if the user has not connected Raindrop.io yet: show it to them and continue once they have approved access on Raindrop.io's own page. 5. Check it works with this request: "Find the Raindrop.io collection I name and list relevant saved links. Prepare a concise research brief from returned bookmark titles, URLs, descriptions and tags. Identify the collection and disclose when the linked pages themselves were not read. Do not change bookmarks." What should come back: - The selected bookmark is identified. - Only returned collection identity, bookmark title, URL, description, tags and other fields actually returned are reported. - Access gaps and missing context are explicit; no source data is changed. 6. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Raindrop.io, then retry.
The whole guide is also available as Markdown, for agents and LLMs: /connectors/raindrop-io/framework/claude-duet.md
Raindrop.io tools Claude Duet can call
-
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.
How it works
-
01
You ask Claude Duet
In your own words, for something in Raindrop.io.
-
02
Claude Duet picks a tool
It sees the Raindrop.io tools on the Agent200 MCP server and calls the one the request needs.
-
03
Agent200 runs the call
With your own Raindrop.io connection, within the tools and scopes your project allows.
-
04
Claude Duet answers
It gets the result back from the MCP server and uses it in its reply or its next step.
Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's Raindrop.io account.
Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and Raindrop.io enforces what its API grants.
Troubleshooting
The source cannot be read
Check the connected account, collection ID, search query and pagination. A bookmark record may lack a description or tag; report the gap without inventing page content.
FAQ
How do I verify this result?
Compare the named bookmark and returned collection identity, bookmark title, URL, description, tags and other fields actually returned with the source. Treat missing information as missing, not as a fact.
