Compatible with every major AI agent and IDE
What is the Raindrop.io (Bookmarks) MCP Server?
Connect your Raindrop.io account to any AI agent and take full control of your digital library through natural conversation.
What you can do
- Collection Management — List root and child collections, create new folders, or merge existing ones to keep your library organized.
- Bookmark Operations — Create, update, or delete individual raindrops (bookmarks). Support for bulk operations allows you to manage multiple links at once.
- Tagging & Filtering — Organize your content with tags. List, rename, merge, or delete tags to maintain a clean taxonomy.
- Highlights & Backups — Access all your saved highlights across collections and view your available backups.
- Trash Maintenance — Quickly empty your trash to permanently remove unwanted items.
How it works
- Subscribe to this server
- Enter your Raindrop.io Personal Access Token
- Start managing your knowledge base from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Researchers — instantly save and categorize sources without leaving your research chat.
- Developers — manage technical bookmarks and documentation links directly from your IDE.
- Knowledge Workers — organize deep-dive reading lists and project resources using natural language.
Built-in capabilities (26)
Create a new collection
Create multiple raindrops
Create a new raindrop (bookmark)
Delete a collection
Delete multiple raindrops
Delete a raindrop (bookmark)
Delete tags
Empty the trash collection
Get a single collection
Get public user details
Get a single raindrop (bookmark)
io user. Get authenticated user details
List all highlights
List all backups
List child collections
List highlights in a collection
) for a collection. List filters
Use 0 for all, -1 for unsorted, -99 for trash. List raindrops in a collection
List root collections
List tags
Merge multiple collections
Rename or merge tags
Update a collection
Update multiple raindrops
Update a raindrop (bookmark)
Update authenticated user details
Why Vercel AI SDK?
The Vercel AI SDK gives every Raindrop.io (Bookmarks) tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 26 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Raindrop.io (Bookmarks) integration everywhere
- —
Built-in streaming UI primitives let you display Raindrop.io (Bookmarks) tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Raindrop.io (Bookmarks) in Vercel AI SDK
Raindrop.io (Bookmarks) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Raindrop.io (Bookmarks) to Vercel AI SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Raindrop.io (Bookmarks) in Vercel AI SDK
The Raindrop.io (Bookmarks) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 26 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Vercel AI SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Raindrop.io (Bookmarks) for Vercel AI SDK
Every tool call from Vercel AI SDK to the Raindrop.io (Bookmarks) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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.
How does the Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp
Explore More MCP Servers
View all →
Mailgun (Transactional Email & Domains)
10 toolsManage email infrastructure via Mailgun — send transactional emails, monitor domain health, and audit delivery logs.

Infinity
12 toolsOrganize any kind of work with flexible boards, lists, and tables that adapt to how your team thinks and operates.

ChargeOver
7 toolsBill your customers with flexible recurring invoicing, automated dunning, and payment collection that keeps revenue flowing.

Dixa
10 toolsEquip your AI agent to manage customer conversations, track agents, and monitor support queues via the Dixa API.
