# Connect Raindrop.io to Claude Prepare a grounded research brief

> Read bookmarks with Claude and Agent200. Prepare a research brief using the connected user’s own Raindrop.io account.

- Page: https://www.agent200.com/connectors/raindrop-io/framework/claude/
- Connector: [Raindrop.io](https://www.agent200.com/connectors/raindrop-io.md)
- Framework: Claude
- Updated: 2026-11-17

## Instructions for AI agents

Goal: connect Raindrop.io to Claude with Agent200, through its MCP server.
Guide: https://www.agent200.com/connectors/raindrop-io/framework/claude/

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'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: 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'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.

## Overview

Ask Claude for a focused research brief from one selected bookmark. Compare its answer with the retrieved source and separate suggestions from recorded facts.

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](https://developer.raindrop.io/v1/raindrops/multiple).

- **Connector:** [Raindrop.io](https://www.agent200.com/connectors/raindrop-io/)
- **Works with:** Claude · Agent app, through MCP
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [6 tools](https://www.agent200.com/connectors/raindrop-io/framework/claude/#tools)
- **MCP server:** `https://api.agent200.com/mcp/`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) 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, with custom MCP servers allowed.** Custom connectors are on every Claude plan (Free: one). Sending an API key uses the Request headers option, a beta that only some accounts have; on Team and Enterprise an Owner adds the connector for everyone.

## Connect Raindrop.io to Claude

### 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 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.

Create an API key: https://agent200.com/platform/apikeys/

### Step 2: Open Connectors in Claude

On a Free, Pro, Max or Ultra plan, go to **Customize > Connectors**. On Team or Enterprise, an Owner goes to **Organization settings > Connectors**; members then find the connector under Customize > Connectors.

### Step 3: Add a custom connector

Select **Add**, then **Add custom connector**. Enter a name, Agent200, and the remote MCP server URL, then choose **Continue**.

### Step 4: Send your key as a request header

Under Authentication choose **No sign-in**. Open **Request headers**, pick `authorization`, enter `Bearer` followed by a space and your key, mark it Required and choose **Add**. Claude sends the value exactly as typed.

File `Add custom connector`:

```text
Remote MCP server URL:  https://api.agent200.com/mcp/
Authentication:         No sign-in
Request header name:    authorization
Value:                  Bearer YOUR_AGENT200_API_KEY
```

### Step 5: Turn it on in a chat

In a chat, select **+ > Connectors** and turn Agent200 on. Ask Claude to list the Agent200 tools to check the connection; Claude asks before a tool runs the first time.

### Step 6: Connect your Raindrop.io account

The first time you ask Claude 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 or Agent200.

## Test your connection

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.

## Raindrop.io tools Claude can call

- **List root collections** (`raindrop_io_list_collections`, read): Find the connected user’s top-level collections.
- **List child collections** (`raindrop_io_list_child_collections`, read): Find child collections under accessible collection folders.
- **Read a collection** (`raindrop_io_get_collection`, read): Retrieve one identified collection and its returned metadata.
- **List bookmarks** (`raindrop_io_list_bookmarks`, read): Read saved links in one collection with the requested result scope.
- **Search bookmarks** (`raindrop_io_search_bookmarks`, read): Search saved links in the connected user’s library.
- **Read a bookmark** (`raindrop_io_get_bookmark`, read): Retrieve one identified saved link and its returned metadata.

## How it works

1. **You ask Claude.** In your own words, for something in Raindrop.io.
2. **Claude picks a tool.** It sees the Raindrop.io tools on the Agent200 MCP server and calls the one the request needs.
3. **Agent200 runs the call.** With your own Raindrop.io connection, within the tools and scopes your project allows.
4. **Claude 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.

## Use Raindrop.io with another framework

- [Raindrop.io + ChatGPT](https://www.agent200.com/connectors/raindrop-io/framework/chatgpt.md)
- [Raindrop.io + Claude Code](https://www.agent200.com/connectors/raindrop-io/framework/claude-code.md)
- [Raindrop.io + Muse](https://www.agent200.com/connectors/raindrop-io/framework/muse.md)
- [Raindrop.io + Grok Bot](https://www.agent200.com/connectors/raindrop-io/framework/grok-bot.md)
- [Raindrop.io + OpenAI Dots](https://www.agent200.com/connectors/raindrop-io/framework/openai-dots.md)
- [Raindrop.io + Claude Duet](https://www.agent200.com/connectors/raindrop-io/framework/claude-duet.md)
- [Raindrop.io + Hermes Agent](https://www.agent200.com/connectors/raindrop-io/framework/hermes-agent.md)
- [Raindrop.io + OpenClaw](https://www.agent200.com/connectors/raindrop-io/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
