Raindrop.io MCP for AI. Manage every saved link and collection via chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Raindrop.io (Bookmarks) connects your saved web links, collections, and tags to any AI client. You use this server to manage your entire digital reading list through natural conversation—no more clicking through tabs or fighting with folder structures.
Create new bookmarks, merge tag groups, delete old collections, or empty trash, all by simply telling your agent what you need done.
What your AI can do
Create collection
Creates a single new folder (collection) for your bookmarks.
Create many raindrops
Adds multiple specified links to your bookmark library at once.
Create raindrop
Saves a single web link as a new bookmark (raindrop).
Create, update, and delete individual bookmarks, handling single or bulk link operations.
List root collections, create subfolders, merge existing folders, or delete them entirely.
Manage content classification by listing tags, renaming groups of tags, merging redundant tags, or deleting unused ones.
Retrieve all saved highlights, list backups, and permanently empty the trash collection when you're done with old links.
Ask an AI about this
Waiting for input…
Raindrop.io (Bookmarks) MCP Server: 26 Tools for Knowledge Management
Manage your entire digital library—from creating single bookmarks to merging complex tag structures—all through conversational commands.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Raindrop.io (Bookmarks) on VinkiusCreate Collection
Creates a single new folder (collection) for your bookmarks.
Create Many Raindrops
Adds multiple specified links to your bookmark library at once.
Create Raindrop
Saves a single web link as a new bookmark (raindrop).
Delete Collection
Deletes an entire collection of bookmarks.
Delete Many Raindrops
Removes multiple specified bookmarks from your library in a single action.
Delete Raindrop
Deletes a specific bookmark (raindrop).
Delete Tags
Removes tags that are no longer needed for organization.
Empty Trash
Permanently deletes all items currently sitting in your trash folder.
Get Collection
Retrieves the details and contents of a single specified collection.
Get Public User
Gets publicly available information about your Raindrop.io account.
Get Raindrop
Retrieves the content and metadata for a single bookmark.
Get User
Gets authenticated details about your connected Raindrop.io user account.
List All Highlights
Lists every highlight you have saved across all collections and tags.
List Backups
Shows a list of your available data backups.
List Child Collections
Retrieves a list of subfolders within a parent collection.
List Collection Highlights
Lists all highlights saved specifically inside one specified collection.
List Filters
Shows which filtering options are available for a given collection.
List Raindrops
Lists all bookmarks found within a specific collection, handling sorting and trash views.
List Root Collections
Retrieves the names and IDs of all top-level folders in your library.
List Tags
Shows you all the tags currently applied across your entire bookmark system.
Merge Collections
Combines two or more specified collections into a single new folder.
Rename Merge Tags
Renames an existing tag, or merges it with another tag to keep your taxonomy clean.
Update Collection
Modifies the name or structure of an existing collection folder.
Update Many Raindrops
Applies a bulk update (like changing tags) to multiple selected bookmarks at once.
Update Raindrop
Modifies the metadata or content of a single existing bookmark.
Update User
Changes details about your connected Raindrop.io account.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Raindrop.io integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Raindrop.io (Bookmarks), then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Raindrop.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 26 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Saving links today feels like managing a poorly indexed filing cabinet.
Right now, when you save an interesting article, you click 'Save' and that link goes into some folder. If you save 50 articles over a month, those folders get messy. You end up with links scattered across dozens of collections—some for work, some for personal reading, some just labeled 'To Read.' Finding one specific source means clicking through six different nested folders.
With this MCP server, your agent handles the structure. Instead of navigating 10 tabs and manually dragging files, you simply tell it: 'Put all my articles about quantum computing into a new folder called Quantum Reads' (running `create_collection`). Your saved knowledge is organized by conversation.
Raindrop.io MCP Server: Organize links using conversational commands.
Manual cleanup involves logging into the web clipper, clicking through collections to find old tags, and then manually deleting or merging them in the UI. It's tedious, error-prone work that stops you from actually doing your research.
Now, tell your agent: 'Merge all my 'Tutorial' and 'Guide' tags into one called Best Practices.' The server runs `rename_merge_tags` instantly, updating every single bookmark across your entire library. It’s a structural fix in seconds.
What your AI can actually do with this
You connect your Raindrop.io account to any AI client, and you'll manage every link you save straight from a chat window. You don't gotta click through tabs or fight with folder structures anymore; just tell your agent what you need done.
Managing Your Links (Bookmarks)
You can treat your bookmark library like a database. Need to save one thing? Use create_raindrop to drop a single link into your collection. Got twenty links from an article and wanna dump 'em all at once? You run create_many_raindrops. If a link is stale or you just don't need it, running delete_raindrop handles that specific bookmark, or if you gotta clear out a bunch of junk fast, delete_many_raindrops gets the job done.
When something changes—like an article updates its meta data—you can call update_raindrop to fix it, and you'll use update_many_raindrops if you gotta change tags or metadata for a whole bunch of links at once.
Structuring Your Folders (Collections)
The server lets you build out your digital filing cabinet. You start by pulling a list of all top-level folders using list_root_collections. Then, if you need a new topic area, you run create_collection to make that single folder. If you're building out deep research material, you can check the subfolders inside any parent with list_child_collections, and then create those nested sections too.
You can modify an existing folder's name or structure using update_collection. Wanna group two separate topics into one big umbrella? Just run merge_collections to combine them. If a whole collection is dead weight, you delete it with delete_collection. And when you mess up, don't sweat it; you can check the contents and metadata of any folder using get_collection.
Controlling Tags (Taxonomy)
Tags keep everything clean. You pull a list of every tag applied to your entire library using list_tags. If two tags mean the same thing—like 'AI' and 'Artificial Intelligence'—you can run rename_merge_tags to combine them into one neat category. Wanna dump useless labels? Use delete_tags to remove tags that nobody uses anymore.
You also use tags for filtering, so you get a list of available options for any collection using list_filters, and the system keeps track of all tags applied across your entire set of links.
Retrieval and Viewing History
You can check what's in any specific folder by running list_raindrops on it, which handles sorting and trash views. If you just want to see everything saved—every single highlight you've bookmarked across every collection and tag—you call list_all_highlights. For a deep dive into one area, you can list all highlights specific to one folder using list_collection_highlights.
You can pull the full details of any individual link with get_raindrop, or get info on what's sitting in your trash by checking list_raindrops while viewing the trash.
System Cleanup and Account Info
Need to keep things tidy? When you’re done experimenting, you can use empty_trash to permanently wipe out every item currently marked for deletion. You can see how much of your data is protected by checking list_backups, or if you need to adjust the credentials connected to your agent, you run update_user.
The server also lets you pull basic public info about your account via get_public_user and gives you authenticated details through get_user. Finally, you can update those user details using update_user.
019e38e0-3b44-73de-912d-14456d7355ec 
Here's how it actually works
The bottom line is that it turns your private link library into a conversational resource for your agent.
Subscribe to this server on Vinkius Marketplace.
Input your Raindrop.io Personal Access Token into the connection settings.
Your AI client now treats your entire bookmark library as an accessible tool, allowing you to issue commands like 'Create a collection called Project Alpha' or 'Delete all tags related to finance.'
Who is this actually for?
Anyone who saves links but struggles to find them later. This is for the researcher drowning in PDFs, the developer hoarding technical documentation, or the writer with thousands of reference articles scattered across dozens of folders. If you save links frequently, this server gives you structure.
Needs to categorize hundreds of sources instantly—using natural language commands to create collections and apply tags like 'Primary Source' or 'Theory'.
Manages deep research lists, needing the ability to merge tags (e.g., merging 'Travel' and 'Italy') and keep track of different project resources.
Uses it to organize technical bookmarks—keeping documentation links in specific collections and running cleanup jobs like emptying the trash regularly.
What Changes When You Connect
Stop losing links in deep folder structures. Use the list_root_collections tool to instantly see your top-level organization, making navigation immediate.
Clean up messy taxonomies fast. The rename_merge_tags tool lets you merge two tags—say, 'AI' and 'Machine Learning'—into one clean tag without losing any content.
Process research data in batches. Instead of adding links one by one, use create_many_raindrops to dump a list of 50 articles into a new project folder instantly.
Keep your system tidy and secure. Use the empty_trash tool when you're done with old references, permanently removing items without manual file deletion.
Maintain structural integrity with bulk edits. The update_many_raindrops tool lets you change a tag or add notes to dozens of bookmarks at once.
See it in action
The Overwhelmed Researcher
A researcher just saved 50 links on climate science. Instead of manually creating 10 folders, they ask the agent: 'Create a root collection called Climate Research and move all related bookmarks into it.' The agent runs create_collection followed by multiple update tools, organizing the data in seconds.
The Project Manager
A PM needs to group resources from two separate meetings. They ask: 'Merge my 'Meeting A' collection and my 'Ideas' collection into a new folder called 'Q3 Planning'. The agent uses merge_collections.' This saves hours of manual file reorganization.
The Technical Writer
A writer has saved articles tagged 'UX Design' and 'Wireframing.' They realize they should be one category. They tell the agent: 'Merge tags 'UX Design' and 'Wireframing' into 'Product UI'. The agent runs rename_merge_tags, cleaning up their system taxonomy.
The Developer Doing Cleanup
A developer finished a project and has 30 old links in the trash. They simply type: 'Empty my trash collection.' The agent executes empty_trash, guaranteeing no forgotten or unnecessary data remains.
The honest tradeoffs
Treating bookmarks like files
Trying to manually copy and paste links into a spreadsheet, then using that sheet to remember which folder they belong in.
Use the agent. Tell it: 'Create a collection called Project Gamma' (using create_collection), then give it the list of links for immediate saving across multiple raindrops (create_many_raindrops).
Ignoring tag redundancy
Having five different tags like 'Tech,' 'Technology,' and 'AI stuff' that all mean the same thing, leading to confusion.
Use rename_merge_tags to combine similar labels. Say: 'Merge these three tech-related tags into one called Core Technology.' This keeps your system clean.
Manually tracking updates
Finding a link saved under the wrong collection or needing to change its description after saving it.
Don't worry about manual edits. Use update_raindrop and specify which bookmark needs changing, so you can fix metadata directly through chat.
When It Fits, When It Doesn't
Use this server if your core pain point is organizing a large volume of saved links (web bookmarks) that need classification by folders and tags. This tool excels at content management—structuring the knowledge base itself.
Don't use it if you are trying to process transactional data, like managing user accounts or sending messages; for those, look into messaging servers or CRM tools. If you only want to view a list of links without making changes, list_raindrops is enough. But if you need structure—creating new folders, merging tags, updating bulk items—this is the right tool.
Questions you might have
How do I create new collections using the Raindrop.io (Bookmarks) MCP Server? +
You use the create_collection tool. Just ask your agent to 'Create a new collection named Project Nova.' It runs the command and makes the folder available immediately.
Can I bulk update links using the Raindrop.io (Bookmarks) MCP Server? +
Yes, you can run update_many_raindrops. This lets you apply a single change—like adding a new tag or changing the description—to dozens of bookmarks without touching them one by one.
What does list_root_collections do? +
It shows all your top-level folders. If you want to see what major categories you have, just ask it to list_root_collections. It gives you the starting point for any search.
If I delete a tag, is the bookmark still usable? +
Yes. Deleting a tag with delete_tags only removes the classification label. The actual link and its content remain safe in the bookmark's collection.
How do I use `list_all_highlights` to see every annotation I've saved? +
The list_all_highlights function gathers all your saved highlights across every collection. This is the quickest way to get a global view of your annotations without having to filter by location.
What does running the `empty_trash` tool actually do? +
The empty_trash function permanently deletes all items in your Trash collection. Use this when you are certain that none of the removed links or bookmarks need to be recovered, as there is no undo.
How can I fix overlapping tags using `rename_merge_tags`? +
rename_merge_tags lets you combine duplicate tags across your entire library. This keeps your content taxonomy clean and prevents links from being managed under inconsistent or redundant labels.
What information does the `get_user` tool provide about my account? +
The get_user function returns your authenticated Raindrop.io user profile details. You can use this to confirm which specific account you're managing or retrieve associated metadata.
Can I organize my bookmarks into nested folders using this integration? +
Yes. You can use list_root_collections to see top-level folders and list_child_collections to see nested ones. You can also create new collections with create_collection.
Is it possible to delete multiple bookmarks at once? +
Absolutely. The delete_many_raindrops tool allows your agent to remove a list of bookmark IDs in a single operation.
How can I see the highlights I've made on my saved pages? +
You can use the list_all_highlights tool to retrieve all highlights across your entire account, or list_collection_highlights for a specific collection.
We've already built the connector for Raindrop.io. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 26 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.