Raindrop.io + Claude Code

Build a Raindrop.io reader with Claude Code Prepare a grounded research brief

Use Claude Code to build a separate read-only Raindrop.io assistant with Agent200. Ground the research brief in returned source data.

On this page
  1. Overview
  2. Before you start
  3. Setup steps
  4. Test your connection
  5. Instructions for AI agents
  6. Raindrop.io tools
  7. How it works
  8. Troubleshooting
  9. FAQ

Overview

Use Claude Code to implement a read-only Raindrop.io reader in your application. Validate identifiers, schemas and access failures before presenting a research brief.

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 Code · Coding agent, with the SDK
Authentication
Managed OAuth, per end user
Tools
6 tools
Model in examples
openai/gpt-5.6-sol

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 Code in your project. It writes the code with the Agent200 SDK; you review it.

Connect Raindrop.io to Claude Code

  1. 1

    Step 1: Create your Agent200 API key

    Create a key on the API keys page and store it securely.

    .env
    Conceptual example
    Store the Agent200 API key as an environment variable
    # Keep the key out of your code, prompts and chats.
    export AGENT200_API_KEY="paste-your-key-here"
  2. 2

    Step 2: Inspect the real tool definitions

    Confirm the actual Raindrop.io read operations and input schemas in your runtime.

  3. 3

    Step 3: Connect the user’s Raindrop.io account

    Preserve the same stable user identity during authorization and later requests.

    connect.js
    Conceptual example
    Let 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);
    }
  4. 4

    Step 4: Build and test the read-only answer

    Prepare the research brief only from returned source data. The code example illustrates a sequence, not an SDK installation contract.

    run.js
    Conceptual example
    Run 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);

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.

Read the SDK docs

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 Code.

Agent brief
Goal: connect Raindrop.io to Claude Code with Agent200.
Guide: https://www.agent200.com/connectors/raindrop-io/framework/claude-code/

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. Make sure Raindrop.io is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's Raindrop.io account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Raindrop.io.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "raindrop_io" in the tools. The model decides when a Raindrop.io tool is needed; Agent200 executes the call.
7. 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.
8. 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 code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

The whole guide is also available as Markdown, for agents and LLMs: /connectors/raindrop-io/framework/claude-code.md

Raindrop.io tools Claude Code can call

  • List root collections

    Read
    raindrop_io_list_collections

    Find the connected user’s top-level collections.

  • List child collections

    Read
    raindrop_io_list_child_collections

    Find child collections under accessible collection folders.

  • Read a collection

    Read
    raindrop_io_get_collection

    Retrieve one identified collection and its returned metadata.

  • List bookmarks

    Read
    raindrop_io_list_bookmarks

    Read saved links in one collection with the requested result scope.

  • Search bookmarks

    Read
    raindrop_io_search_bookmarks

    Search saved links in the connected user’s library.

  • Read a bookmark

    Read
    raindrop_io_get_bookmark

    Retrieve one identified saved link and its returned metadata.

How it works

  1. 01

    Your app sends the request

    It calls Agent200 with the model, instructions, the input, the end user's id and the Raindrop.io tools.

  2. 02

    The model picks a tool

    The model decides whether a Raindrop.io tool is needed, and with which arguments.

  3. 03

    Agent200 runs the call

    It uses that user's own Raindrop.io connection, within the endpoints and scopes your project allows, and returns the result to the model.

  4. 04

    Your app gets the result

    Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

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.

Is this a native product integration?

This describes a separate application built with Agent200 and Claude Code; it does not install a connector into the Claude Code app.

Use Raindrop.io with another framework

200 OK

Raindrop.io, connected to Claude Code.
One SDK. One API key.

Agent200 handles the OAuth, the tokens and every tool call. You keep your agent, your model and your code.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)