Skip to main content
Glama
raindrop-mcp

raindrop-mcp

by aderaaij

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

collection_list

All collections, flat

get_collection_tree

Collections as a hierarchy with breadcrumb paths

collection_manage

Create / update / delete a collection

cleanup_collections

Remove empty collections (dry-run unless confirm: true)

bookmark_search

Full-text search with tag / domain / type / date / flag filters

bookmark_manage

Create / update / delete a bookmark

get_raindrop

One bookmark by ID (with highlights)

list_raindrops

Bookmarks in a collection, paginated

bulk_edit_raindrops

Bulk update / move / remove

library_audit

Count (and list) broken links and duplicates

empty_trash

Permanently empty Trash (dry-run unless confirm: true)

remove_duplicates

Delete same-URL duplicates, keeping the oldest (dry-run by default)

tag_manage

Rename / merge / delete tags

highlight_manage

Create / update / delete highlights

get_suggestions

Suggested tags + collections for a URL or bookmark

suggest_tags

Suggested tags for a URL

diagnostics

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 token

Get 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/mcp

stdio (clients that spawn the server locally):

uv run start

systemd 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.target

The 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-After once on HTTP 429 (Raindrop allows 120 req/min).

  • skipCache parameters are accepted for compatibility but are no-ops — this server doesn't cache.

License

MIT

Available Tools

17 tools
bookmark_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

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

    B3.2/5.0

    Scored across 17 tools

    Disambiguation5/5

    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 Consistency3/5

    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.

    Tool Count5/5

    17 tools is well-scoped for a bookmark management server. It covers all necessary CRUD operations and utilities without unnecessary clutter, earning its place.

    Completeness5/5

    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

    Related MCP Servers