raindrop-mcp
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-mcp search my bookmarks for machine learning"
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-mcp
A Raindrop.io MCP server in Python (FastMCP), serving streamable HTTP natively — no stdio↔HTTP bridge needed. Also runs as a plain stdio server for clients that spawn a local process.
Built as a drop-in replacement for
@adeze/raindrop-mcp: the 17 tools keep
the same names, parameters, and required fields, so existing prompts and client
configs keep working. (Two tools differ internally: get_suggestions /
suggest_tags use Raindrop's native suggest endpoint rather than
MCP-sampling-based AI refinement.)
Tools
Tool | What it does |
| All collections, flat |
| Collections as a hierarchy with breadcrumb paths |
| Create / update / delete a collection |
| Remove empty collections (dry-run unless |
| Full-text search with tag / domain / type / date / flag filters |
| Create / update / delete a bookmark |
| One bookmark by ID (with highlights) |
| Bookmarks in a collection, paginated |
| Bulk update / move / remove |
| Count (and list) broken links and duplicates |
| Permanently empty Trash (dry-run unless |
| Delete same-URL duplicates, keeping the oldest (dry-run by default) |
| Rename / merge / delete tags |
| Create / update / delete highlights |
| Suggested tags + collections for a URL or bookmark |
| Suggested tags for a URL |
| Server/runtime metadata |
Collection IDs: 0 = all, -1 = Unsorted, -99 = Trash. Destructive sweeps
default to a dry run.
Related MCP server: Raindrop.io MCP Server
Setup
Requires Python ≥ 3.10 and uv.
uv sync
cp config/.env.example config/.env # then paste your tokenGet a token at raindrop.io → Settings → Integrations → For Developers →
create an app → Test token. Set it as RAINDROP_ACCESS_TOKEN in
config/.env (or in the process environment, which takes precedence).
Running
Streamable HTTP (network clients — Claude Desktop remote MCP, gateways):
MCP_TRANSPORT=http MCP_PORT=8591 uv run start
# serves http://0.0.0.0:8591/mcpstdio (clients that spawn the server locally):
uv run startsystemd user unit (example)
[Unit]
Description=Raindrop.io MCP (native FastMCP HTTP)
After=network.target
[Service]
Type=simple
WorkingDirectory=%h/raindrop-mcp
Environment=MCP_TRANSPORT=http
Environment=MCP_HOST=0.0.0.0
Environment=MCP_PORT=8591
ExecStart=%h/raindrop-mcp/.venv/bin/start
MemoryMax=512M
MemorySwapMax=0
Restart=always
RestartSec=5
[Install]
WantedBy=default.targetThe server binds 0.0.0.0 in the example — front it with your LAN/VPN
(Tailscale works well); the Raindrop token authorizes every request it serves.
Notes
Scaffolded with mcp-template.
Rate limiting: honours
Retry-Afteronce on HTTP 429 (Raindrop allows 120 req/min).skipCacheparameters are accepted for compatibility but are no-ops — this server doesn't cache.
License
MIT
Available Tools
17 toolsbookmark_manageB
Creates, updates, or deletes bookmarks. Use the operation parameter to specify the action.
Inputs: url (required), title (required), operation (required), id, +4 more. Returns: object
bookmark_searchB
Searches bookmarks with advanced filters, tags, and full-text search.
Inputs: tag, page, sort, tags, +13 more. Returns: object
bulk_edit_raindropsB
Bulk update, move, or remove bookmarks in a specific collection.
Inputs: collectionId (required), ids, tags, important, +2 more. Returns: object
cleanup_collectionsA
Remove all collections that do not contain any bookmarks. Requires 'confirm: true' to execute.
Inputs: confirm. Returns: object
collection_listA
Lists all Raindrop.io collections as a flat list.
Inputs: skipCache. Returns: object
collection_manageC
Creates, updates, or deletes a collection. Use the operation parameter to specify the action.
Inputs: operation (required), id, title, parentId. Returns: object
diagnosticsD
Diagnostics resource and runtime metadata.
Inputs: includeEnvironment. Returns: object
empty_trashA
Permanently delete all bookmarks currently in the trash collection. Requires 'confirm: true' to execute.
Inputs: confirm. Returns: object
get_collection_treeB
Returns a hierarchical view of all collections with full breadcrumb paths.
Inputs: skipCache. Returns: object
get_raindropA
Fetch a single Raindrop.io bookmark by ID.
Inputs: id (required), skipCache. Returns: object
get_suggestionsB
Get suggestions for tags and collections for a specific URL or existing bookmark.
Inputs: url, useAi, raindropId. Returns: object
highlight_manageA
Creates, updates, or deletes highlights. Use the operation parameter to specify the action.
Highlights live on the bookmark: mutations are a PUT of the bookmark's
highlights array (an entry with an _id edits it; empty text removes it).
Inputs: text (required), operation (required), bookmarkId (required), id, +2 more. Returns: object
library_auditA
Scans the entire library for broken links and duplicate bookmarks.
Inputs: details. Returns: object
list_raindropsB
List Raindrop.io bookmarks for a collection with pagination.
Inputs: collectionId (required), page, sort, perPage, +1 more. Returns: object
remove_duplicatesA
Scans all collections and removes duplicate bookmarks (same URL, keeping the oldest) in batches of 50. Supports dry run to report counts without deleting.
Inputs: dryRun, skipCache. Returns: object
suggest_tagsA
Suggests relevant tags for a bookmark based on its URL (via Raindrop's suggest endpoint).
Inputs: url (required), title (required), description. Returns: object
tag_manageB
Renames, merges, or deletes tags. Use the operation parameter to specify the action.
Inputs: tagNames (required), operation (required), newName, collectionId. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Each tool targets a distinct aspect of Raindrop.io management (bookmarks, collections, tags, highlights, diagnostics) with clear descriptions. The only potential overlap is between bookmark_manage (single) and bulk_edit_raindrops (bulk), but the descriptions clearly differentiate them.
Naming patterns are mixed: some use noun_verb (bookmark_manage, collection_list) and others use verb_noun (get_raindrop, list_raindrops). Additionally, diagnostics is just a noun. While readable, the inconsistency reduces predictability.
17 tools is well-scoped for a bookmark management server. It covers all necessary CRUD operations and utilities without unnecessary clutter, earning its place.
The tool surface is comprehensive, covering CRUD for bookmarks, collections, tags, and highlights, plus search, suggestions, bulk editing, duplicate removal, and trash management. No obvious gaps for the domain.
Related MCP Connectors
Search, label, and manage your X (Twitter) bookmarks from any MCP client via Tweetsmash
Team-shared memory MCP: 15 tools, search, links, collections, bulk ops, Teams workspaces.
Search your Glasp web and Kindle highlights, notes, and AI memories from any MCP client. Read-only.
Personal knowledge MCP: capture bookmarks, notes & todos by chat; archive pages; search memory.
Related MCP Servers
- AlicenseBqualityCmaintenanceMCP Server for accessing Raindrop.io bookmark manager.37224 npm191MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access and manage Raindrop.io bookmarks, collections, tags, and highlights through the Model Context Protocol. Supports CRUD operations, advanced search, file uploads, and bulk editing of bookmarks.MIT
- FlicenseAqualityDmaintenanceEnables to manage Raindrop.io bookmarks programmatically—add, search, and organize bookmarks from LLM apps.415-
- AlicenseAqualityDmaintenanceEnables Claude Code and other MCP clients to manage bookmarks, collections, and tags in Raindrop.io accounts via natural language.152MIT