Raindrop.io
Connect Raindrop.io to an AI assistant to organize, search, and manage bookmarks, collections, tags, highlights, reminders, and user data via MCP.
Create, read, update, delete, share, merge, and clean up collections; empty trash.
Create, read, update, delete, search, and bulk-edit bookmarks; batch move, tag, and delete.
Manage tags: list, rename, merge, delete globally or per collection.
Manage highlights: list all or by bookmark/collection, create, update, delete.
Set and delete bookmark reminders.
Get user info and stats; check import/export status; export bookmarks as CSV, HTML, or PDF.
Audit broken links, duplicates, and untagged items; remove duplicates and empty collections (with confirmation).
Get AI-powered organization and tag suggestions.
Used for making HTTP requests to the Raindrop.io API
Can be used for installing dependencies and running the Raindrop.io MCP server
Used for environment variable configuration in the Raindrop.io MCP server
Required to run the Raindrop.io MCP server (v18 or later recommended)
Allows installing and running the Raindrop.io MCP server via npx command
Used for implementing the Raindrop.io MCP server with strong typing for better maintainability
Used for schema validation of API parameters and responses in the Raindrop.io MCP server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Raindrop.io find my bookmarks about machine learning from last week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Raindrop.io MCP Server
Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
Raindrop.io now also offers a hosted Streamable HTTP MCP endpoint (
https://api.raindrop.io/rest/v2/ai/mcp) in beta for Pro users. Use that when its hosted toolset is sufficient; use this package for local stdio, self-hosted HTTP, and its additional library-management tools.
What it can do
Create, update, and delete collections and bookmarks
Search bookmarks by tags, domain, type, date, and more
Manage tags (list, rename, merge, delete)
Read highlights from bookmarks
Bulk edit bookmarks in a collection
Audit broken links and duplicates, and manage trash
Related MCP server: raindrop-mcp
Tools
diagnostics - Server diagnostic information and library health metrics
collection_list - List all collections as a flat list
get_collection_tree - Hierarchical view of collections with full breadcrumb paths
collection_manage - Create, update, or delete collections
bookmark_search - Advanced search with filters, tags, and pagination
bookmark_manage - Create, update, or delete bookmarks
get_raindrop - Fetch a single bookmark by ID
list_raindrops - List bookmarks for a collection with pagination
get_suggestions - AI-powered organization advice (tags/collections) for a URL or bookmark
suggest_tags - Suggest relevant tags from bookmark metadata using AI-assisted analysis
bulk_edit_raindrops - Bulk update, move, or remove bookmarks in a specific collection
tag_manage - Rename, merge, or delete tags
highlight_manage - Create, update, or delete highlights
library_audit - Scan library for broken links, duplicates, and untagged items
empty_trash - Permanently empty the trash (requires confirmation)
cleanup_collections - Remove empty collections (requires confirmation)
remove_duplicates - Find and remove duplicate bookmarks with safe confirmation flow
Install
Quick Start (One-Liners)
Tool | One-Liner Command |
Gemini CLI |
|
Codex CLI |
|
Claude Code |
|
GitHub Copilot |
|
Vercel Skills |
|
Note: For tools adding an MCP server via
npx, you must have theRAINDROP_ACCESS_TOKENenvironment variable set in your shell or the tool's environment config.
Vercel Skills (npx skills)
This project is compatible with the Vercel Skills system. All necessary manifests are present:
manifest.json: Standard MCP manifest for server definition.SKILL.md: Standardized skill description for agent discovery.mcp.json: Root configuration for MCP clients and registries.
To add this server to your local skill directory:
npx skills add adeze/raindrop-mcp --globalTo contribute this to the Vercel Skills Registry, submit a Pull Request adding this repository URL to the registry.
Claude Desktop (MCPB)
Download the latest raindrop-mcp.mcpb from the GitHub Release and add it to Claude Desktop:
In Claude Desktop, add the bundle and set this environment variable:
RAINDROP_ACCESS_TOKEN (from your Raindrop.io integrations settings)
NPX (CLI)
Set your API token as an environment variable and run:
export RAINDROP_ACCESS_TOKEN=YOUR_RAINDROP_ACCESS_TOKEN
npx @adeze/raindrop-mcpManual MCP config (mcp.json)
Add this to your MCP client configuration:
{
"servers": {
"raindrop": {
"type": "stdio",
"command": "npx",
"args": ["@adeze/raindrop-mcp@latest"],
"env": {
"RAINDROP_ACCESS_TOKEN": "YOUR_RAINDROP_ACCESS_TOKEN"
}
}
}
}HTTP
bun run start:http serves /mcp on 127.0.0.1:3002; set HTTP_PORT to
change the port. HTTP tools use the server's RAINDROP_ACCESS_TOKEN. Host and
Origin checks prevent DNS rebinding but do not authenticate callers. For remote
access, place an authenticated reverse proxy in front of the loopback endpoint.
Requirements
A Raindrop.io account
A Raindrop.io API Access Token: https://app.raindrop.io/settings/integrations
Support
Release
This repository uses semantic-release as the only supported release flow.
How publishing works
Releases run from pushes to
mastervia.github/workflows/publish.ymlafter validation passes.Release runs are serialized; only the release job receives repository write and OIDC permissions.
semantic-releaseanalyzes Conventional Commit messages, computes the next version, updatesCHANGELOG.md, tags/releases on GitHub, and publishes npm.During release preparation,
.releaserc.jsonsyncsmanifest.json,mcp.json, andgemini-extension.json, then buildsraindrop-mcp.mcpbso the GitHub Release includes the bundle.
Pre-release dry-run
In GitHub Actions, select Validate and Publish → Run workflow on
master. Leavedry_runenabled to preview a release; disable it to run semantic-release publishing.This validates semantic version calculation, registry auth, and release pipeline behavior without publishing.
Required secrets
GITHUB_TOKENis provided by GitHub Actions for release automation.
npm trusted publishing
npm publishing is configured via GitHub Actions OIDC trusted publishing.
Keep the trusted publisher workflow filename set to
publish.yml, including manual dry runs.NPM_TOKENis not required for the standard CI release path.
Local validation before merge
Use Node 24.15+ and Bun 1.4.3+. The published server requires Node 22.19+.
Vite+ 1.1 manages lint, formatting, type checks, tests, and packaging through
vite.config.ts; Bun remains the package manager.
bun install --frozen-lockfile
bun run check
bun run test
bun run test:coverage
bun run docsbun run build runs vp pack, preserving build/index.js, build/server.js,
source maps, and bundled dependencies. Tests build first so package checks work
from a clean checkout. bun run dev and bun run dev:http retain Bun's server
watch mode; bunx vp run dev runs the same script. vp dev starts a Vite web
server and is not this MCP server's development command.
The server uses TypeScript 7.0.2. TypeDoc and OpenAPI type generation currently need the TypeScript 6 compiler
API, so tooling/compiler-api keeps its own TypeScript 6.0.3 dependency. Install from the
root; bun run docs still generates the existing documentation.
bun run update:deps refreshes dependencies while keeping coverage aligned with
Vite+'s bundled Vitest 5.0.3. Update those pins together when upgrading Vite+.
The migration removed the generated clearMocks: false setting after the same
61 tests passed with Vitest 5 defaults. Coverage resolves the same 16 files as
Vitest 4; no thresholds or exclusions were relaxed. No tsdown compatibility
settings were needed because the original build used Bun.
The unused Java/Axios generator stack was removed; typed openapi-fetch remains
the shared client. Both current OpenAPI generators tested require the older
TypeScript compiler API: Hey API 0.99.0 fails under TypeScript 7 before CLI help.
The isolated, tested generator avoids changes to authentication, rate limiting
and cache behavior.
Release tooling still pulls braces 3.0.3, affected by
GHSA-vfj7-8cjw-p6xm;
no patched version is published. This dependency is not included in the server
bundle. Do not feed untrusted glob patterns to release tooling.
Breaking changes and reviewed fixes
Deleting bookmarks, collections, tags or highlights, and bulk removal now requires
confirm: true. Cleanup tools keep their existing preview flow.HTTP binds to
127.0.0.1; OAuth callbacks require matching, unexpired, single-use browser state. Remote access requires an authenticated proxy.Bulk moves/updates/removals use the source collection's API endpoint. Bookmark updates preserve
collectionId; omit URL/title when changing only other fields. Collection0means All and cannot be used for bulk mutations;-1means Unsorted.Tags use upstream search operators, preserving pagination and total counts. Collection paths no longer depend on API ordering; mutations invalidate affected bookmark, search and collection-count caches.
Permanent upstream errors are not retried. Resource templates use the MCP SDK; unsupported resource subscriptions are no longer advertised.
MCPB packages contain bundled runtime code rather than development dependencies. Environment files, logs and local Codex state are excluded.
These fixes address the substance of PR #52 and issues #54/#55. Older SDK v1/Zod 3 migrations are superseded by this SDK v2 setup. Framework replacement was unnecessary: existing SDK APIs and shared service helpers eliminated redundant code. Live Raindrop mutations and OAuth provider login remain manual validation steps.
Commit message examples
fix: handle empty tag merge payloadfeat: add collection path filterfeat!: remove deprecated search parameter
Do not manually bump versions, push release tags, or run manual npm publish commands for normal releases.
📋 Recent Enhancements (v2.4.x)
Smart Organization & Hierarchy
AI Suggestions: New
get_suggestionstool provides organizational advice using Raindrop's API and MCP Sampling.Collection Tree:
get_collection_treetool provides a hierarchical view with full breadcrumb paths.Bulk Move: Added
moveoperation tobulk_edit_raindropsfor efficient library organization.Pagination Support: Standardized
list_raindropsandbookmark_searchwith pagination for large libraries.
Safety & Quality
Confirmation Logic: Destructive tools (
empty_trash,cleanup_collections) now require explicit confirmation.Standardized Naming: All tools now use consistent snake_case naming conventions.
CI/CD Pipeline: Enhanced GitHub Actions with automated linting, type-checking, and cross-transport tests.
Code Quality: Established ESLint and Prettier configurations for maintainable development.
📋 Previous Enhancements (v2.3.3)
Advanced Cleanup & Library Audit
📋 Previous Enhancements (v2.3.2)
MCP Resource Links Implementation
Modern
resourcecontent following current MCP SDK best practicesEfficient data access: tools return lightweight links instead of full payloads
Better performance: clients fetch full bookmark/collection data only when needed
Seamless integration with dynamic resource system (
mcp://raindrop/{id})
SDK & API Updates
Updated to the latest supported MCP SDK in this repository
Modern tool registration with improved descriptions
Fixed API endpoints and path parameters
All core tools fully functional
Tool Optimization
Resource-efficient responses for bookmark/collection lists
Dynamic resource access via
mcp://collection/{id}andmcp://raindrop/{id}Better client UX with lighter list payloads
Full MCP compliance with official SDK patterns
Service Layer Improvements
Reduced code through extracted common helpers
Consistent error handling and response processing
Enhanced type safety with generic handlers
Centralized endpoint building
Testing Improvements
Stronger end-to-end coverage for MCP tool execution
Expanded integration tests for real-world client flows
MCP 2.0 Preparation (Bulk Ops)
Laying groundwork for MCP 2.0 bulk-operation workflows and tooling
OAuth (Coming Soon)
OAuth-based auth flow to simplify setup without manual tokens
Note
Apologies to anyone affected by the last couple of builds. Thank you for the patience and reports.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Available Tools
37 toolsbatchDeleteBookmarksC
Delete multiple bookmarks at once
Inputs: ids (required), permanent.
batchUpdateBookmarksC
Update multiple bookmarks at once
Inputs: ids (required), collectionId, important, tags.
bulkMoveBookmarksC
Move multiple bookmarks to another collection
Inputs: collectionId (required), ids (required).
bulkTagBookmarksC
Add or remove tags from multiple bookmarks
Inputs: ids (required), operation (required), tags (required).
createBookmarkC
Create a new bookmark
Inputs: collectionId (required), link (required), excerpt, important, +2 more.
createCollectionC
Create a new collection
Inputs: title (required), isPublic.
createHighlightC
Create a new highlight for a bookmark
Inputs: raindropId (required), text (required), color, note.
deleteBookmarkC
Delete a bookmark
Inputs: id (required), permanent.
deleteCollectionC
Delete a collection
Inputs: id (required).
deleteHighlightC
Delete a highlight
Inputs: id (required).
deleteReminderC
Delete a reminder from a bookmark
Inputs: raindropId (required).
deleteTagC
Remove a tag from all bookmarks or in a specific collection
Inputs: tag (required), collectionId.
deleteTagsC
Delete tags from all bookmarks
Inputs: tags (required), collectionId.
emptyTrashB
Empty the trash by permanently deleting all raindrops in it
Inputs: no named parameters.
exportBookmarksC
Export bookmarks in various formats
Inputs: format (required), broken, collectionId, duplicates.
getAllHighlightsC
Get all highlights across all bookmarks
Inputs: page, perPage.
getBookmarkC
Get a specific bookmark by ID
Inputs: id (required).
getBookmarksC
Get bookmarks with optional filtering
Inputs: collection, page, perPage, search, +2 more.
getCollectionC
Get a specific collection by ID
Inputs: id (required).
getCollectionsB
Get all collections
Inputs: no named parameters.
getExportStatusB
Check the status of an ongoing export
Inputs: no named parameters.
getHighlightsC
Get highlights for a specific bookmark
Inputs: raindropId (required).
getHighlightsByCollectionC
Get highlights for bookmarks in a specific collection
Inputs: collectionId (required).
getImportStatusB
Check the status of an ongoing import
Inputs: no named parameters.
getTagsC
Get all tags
Inputs: collectionId.
getUserInfoC
Get user information
Inputs: no named parameters.
getUserStatsC
Get user statistics
Inputs: collectionId.
mergeCollectionsC
Merge multiple collections into one target collection
Inputs: sourceIds (required), targetId (required).
mergeTagsC
Merge multiple tags into one destination tag
Inputs: destinationTag (required), sourceTags (required), collectionId.
removeEmptyCollectionsB
Remove all empty collections
Inputs: no named parameters.
renameTagB
Rename a tag across all bookmarks or in a specific collection
Inputs: newName (required), oldName (required), collectionId.
searchBookmarksC
Search bookmarks with advanced filters
Inputs: collection, createdEnd, createdStart, important, +6 more.
setReminderC
Set a reminder for a bookmark
Inputs: date (required), raindropId (required), note.
updateBookmarkC
Update an existing bookmark
Inputs: id (required), collectionId, excerpt, important, +2 more.
updateCollectionC
Update an existing collection
Inputs: id (required), isPublic, sort, title, +1 more.
updateHighlightC
Update an existing highlight
Inputs: id (required), color, note, text.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 37 tools
Most tools have distinct purposes targeting specific resources (bookmarks, collections, highlights, tags) and actions, with clear boundaries. However, some overlap exists between deleteTag and deleteTags, and between getHighlights and getHighlightsByCollection, which could cause minor confusion.
Tool names follow a highly consistent verb_noun pattern throughout, with clear and predictable naming (e.g., createBookmark, getBookmarks, updateCollection). All names use camelCase uniformly, making them easy to parse and understand.
With 37 tools, the count is high and feels heavy for a bookmark management domain. While many tools cover specific operations, the number may overwhelm agents and could likely be consolidated or streamlined without losing functionality.
The tool set provides comprehensive CRUD and lifecycle coverage for bookmarks, collections, highlights, tags, and user operations. It includes advanced features like bulk operations, reminders, sharing, and import/export, leaving no obvious gaps for the domain.
Maintenance
Related MCP Connectors
Official Bookmax MCP server: search and save bookmarks, read notes and docs from AI assistants.
Remote MCP server for full read/write access to a Zotero library
Remote MCP server for saving, searching, syncing, and managing Teak cards.
MCP server wrapping the Tesla Fleet API and TeslaMate API
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that allows Claude Desktop to access and manage Raindrop.io bookmarks through natural language commands, supporting operations for collections, raindrops, and tags.128MIT
- AlicenseBqualityDmaintenanceEnables management of Raindrop.io bookmarks, collections, tags, and highlights via MCP tools, with support for search, bulk editing, and library auditing.17MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that exposes Raindrop.io's bookmark management API as tools for AI assistants, enabling collection, bookmark, and tag operations.1MIT
- AlicenseNot gradedqualityBmaintenanceMCP server to manage your GitHub starred repositories and lists19MIT