Skip to content
Back to search

raindrop-mcp

Raindrop MCP Server

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/adeze--raindrop-mcp/badge.svg)](/listings/adeze--raindrop-mcp)

HTML

<a href="/listings/adeze--raindrop-mcp"><img src="/api/listings/adeze--raindrop-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Quick Start (One-Liners)

| Tool | One-Liner Command | | :----------------- | :----------------------------------------------------------------- | | **Gemini CLI** | `gemini extensions install https://github.com/adeze/raindrop-mcp` | | **Codex CLI** | `codex mcp add raindrop -- npx -y @adeze/raindrop-mcp` | | **Claude Code** | `claude mcp add raindrop -- npx -y @adeze/raindrop-mcp` | | **GitHub Copilot** | `gh copilot config mcp add raindrop -- npx -y @adeze/raindrop-mcp` | | **Vercel Skills** | `npx skills add adeze/raindrop-mcp` |

> **Note**: For tools adding an MCP server via `npx`, you must have the `RAINDROP_ACCESS_TOKEN` environment variable set in your shell or the tool's environment config.

Vercel Skills (npx skills)

This project is compatible with the [Vercel Skills](https://github.com/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 --global

To contribute this to the [Vercel Skills Registry](https://github.com/vercel/skills/tree/main/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:

- Releases: https://github.com/adeze/raindrop-mcp/releases

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-mcp

Manual 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"
      }
    }
  }
}

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 33 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Raindrop.io MCP Server
  2. Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
  3. ## Capabilities
  4. - **Bookmark Management**: Create, update, and delete collections and bookmarks.
  5. - **Search & Filtering**: Advanced search by tags, domain, type, date, and more.
  6. - **Tag Management**: List, rename, merge, and delete tags.
  7. - **Highlights**: Read and manage highlights from bookmarks.
  8. - **Organization**: AI-powered suggestions for tags and collections.
  9. - **Maintenance**: Scan library for broken links, duplicates, and untagged items.
  10. ## Usage
  11. ### Organization
  12. "Analyze my recent bookmarks and suggest a collection for them."
  13. "Suggest tags for this URL: https://example.com"
  14. ### Search
  15. "Find all bookmarks from last month about 'TypeScript'."
  16. "Search for bookmarks with tag 'recipe' and domain 'nytimes.com'."
  17. ### Cleanup
  18. "Scan my library for broken links."
  19. "Empty my trash."
  20. ## Configuration
  21. Requires a `RAINDROP_ACCESS_TOKEN` from your Raindrop.io integrations settings: https://app.raindrop.io/settings/integrations
README.md · README · 294 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Raindrop.io MCP Server
  2. [![smithery badge](https://smithery.ai/badge/@adeze/raindrop-mcp)](https://smithery.ai/server/@adeze/raindrop-mcp)
  3. [![npm version](https://badge.fury.io/js/%40adeze%2Fraindrop-mcp.svg)](https://www.npmjs.com/package/@adeze/raindrop-mcp)
  4. [![Claude Desktop MCPB](https://img.shields.io/badge/Claude%20Desktop-MCPB-5B61FF?logo=claude&logoColor=white)](https://github.com/adeze/raindrop-mcp/releases)
  5. Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
  6. > 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.
  7. ## What it can do
  8. - Create, update, and delete collections and bookmarks
  9. - Search bookmarks by tags, domain, type, date, and more
  10. - Manage tags (list, rename, merge, delete)
  11. - Read highlights from bookmarks
  12. - Bulk edit bookmarks in a collection
  13. - Audit broken links and duplicates, and manage trash
  14. ## Tools
  15. - **diagnostics** - Server diagnostic information and library health metrics
  16. - **collection_list** - List all collections as a flat list
  17. - **get_collection_tree** - Hierarchical view of collections with full breadcrumb paths
  18. - **collection_manage** - Create, update, or delete collections
  19. - **bookmark_search** - Advanced search with filters, tags, and pagination
  20. - **bookmark_manage** - Create, update, or delete bookmarks
  21. - **get_raindrop** - Fetch a single bookmark by ID
  22. - **list_raindrops** - List bookmarks for a collection with pagination
  23. - **get_suggestions** - AI-powered organization advice (tags/collections) for a URL or bookmark
  24. - **suggest_tags** - Suggest relevant tags from bookmark metadata using AI-assisted analysis
  25. - **bulk_edit_raindrops** - Bulk update, move, or remove bookmarks in a specific collection
  26. - **tag_manage** - Rename, merge, or delete tags
  27. - **highlight_manage** - Create, update, or delete highlights
  28. - **library_audit** - Scan library for broken links, duplicates, and untagged items
  29. - **empty_trash** - Permanently empty the trash (requires confirmation)
  30. - **cleanup_collections** - Remove empty collections (requires confirmation)
  31. - **remove_duplicates** - Find and remove duplicate bookmarks with safe confirmation flow
  32. ## Install
  33. ### Quick Start (One-Liners)
  34. | Tool | One-Liner Command |
  35. | :----------------- | :----------------------------------------------------------------- |
  36. | **Gemini CLI** | `gemini extensions install https://github.com/adeze/raindrop-mcp` |
  37. | **Codex CLI** | `codex mcp add raindrop -- npx -y @adeze/raindrop-mcp` |
  38. | **Claude Code** | `claude mcp add raindrop -- npx -y @adeze/raindrop-mcp` |
  39. | **GitHub Copilot** | `gh copilot config mcp add raindrop -- npx -y @adeze/raindrop-mcp` |
  40. | **Vercel Skills** | `npx skills add adeze/raindrop-mcp` |
  41. > **Note**: For tools adding an MCP server via `npx`, you must have the `RAINDROP_ACCESS_TOKEN` environment variable set in your shell or the tool's environment config.
  42. ### Vercel Skills (npx skills)
  43. This project is compatible with the [Vercel Skills](https://github.com/vercel/skills) system. All necessary manifests are present:
  44. - `manifest.json`: Standard MCP manifest for server definition.
  45. - `SKILL.md`: Standardized skill description for agent discovery.
  46. - `mcp.json`: Root configuration for MCP clients and registries.
  47. To add this server to your local skill directory:
  48. ```bash
  49. npx skills add adeze/raindrop-mcp --global
  50. ```
  51. To contribute this to the [Vercel Skills Registry](https://github.com/vercel/skills/tree/main/registry), submit a Pull Request adding this repository URL to the registry.
  52. ### Claude Desktop (MCPB)
  53. Download the latest raindrop-mcp.mcpb from the GitHub Release and add it to Claude Desktop:
  54. - Releases: https://github.com/adeze/raindrop-mcp/releases
  55. In Claude Desktop, add the bundle and set this environment variable:
  56. - RAINDROP_ACCESS_TOKEN (from your Raindrop.io integrations settings)
  57. ### NPX (CLI)
  58. Set your API token as an environment variable and run:
  59. ```bash
  60. export RAINDROP_ACCESS_TOKEN=YOUR_RAINDROP_ACCESS_TOKEN
  61. npx @adeze/raindrop-mcp
  62. ```
  63. ### Manual MCP config (mcp.json)
  64. Add this to your MCP client configuration:
  65. ```json
  66. {
  67. "servers": {
  68. "raindrop": {
  69. "type": "stdio",
  70. "command": "npx",
  71. "args": ["@adeze/raindrop-mcp@latest"],
  72. "env": {
  73. "RAINDROP_ACCESS_TOKEN": "YOUR_RAINDROP_ACCESS_TOKEN"
  74. }
  75. }
  76. }
  77. }
  78. ```
  79. ### HTTP
  80. `bun run start:http` serves `/mcp` on `127.0.0.1:3002`; set `HTTP_PORT` to
  81. change the port. HTTP tools use the server's `RAINDROP_ACCESS_TOKEN`. Host and
  82. Origin checks prevent DNS rebinding but do not authenticate callers. For remote
  83. access, place an authenticated reverse proxy in front of the loopback endpoint.
  84. ## Requirements
  85. - A Raindrop.io account
  86. - A Raindrop.io API Access Token: https://app.raindrop.io/settings/integrations
  87. ## Support
  88. - Issues: https://github.com/adeze/raindrop-mcp/issues
  89. ## Release
  90. This repository uses `semantic-release` as the only supported release flow.
  91. ### How publishing works
  92. - Releases run from pushes to `master` via `.github/workflows/publish.yml` after validation passes.
  93. - Release runs are serialized; only the release job receives repository write and OIDC permissions.
  94. - `semantic-release` analyzes Conventional Commit messages, computes the next version, updates `CHANGELOG.md`, tags/releases on GitHub, and publishes npm.
  95. - During release preparation, `.releaserc.json` syncs `manifest.json`, `mcp.json`, and `gemini-extension.json`, then builds `raindrop-mcp.mcpb` so the GitHub Release includes the bundle.
  96. ### Pre-release dry-run
  97. - In GitHub Actions, select **Validate and Publish** → **Run workflow** on `master`. Leave `dry_run` enabled to preview a release; disable it to run semantic-release publishing.
  98. - This validates semantic version calculation, registry auth, and release pipeline behavior without publishing.
  99. ### Required secrets
  100. - `GITHUB_TOKEN` is provided by GitHub Actions for release automation.
  101. ### npm trusted publishing
  102. - npm publishing is configured via GitHub Actions OIDC trusted publishing.
  103. - Keep the trusted publisher workflow filename set to `publish.yml`, including manual dry runs.
  104. - `NPM_TOKEN` is not required for the standard CI release path.
  105. ### Local validation before merge
  106. Use Node 24.15+ and Bun 1.4.3+. The published server requires Node 22.19+.
  107. Vite+ 1.1 manages lint, formatting, type checks, tests, and packaging through
  108. `vite.config.ts`; Bun remains the package manager.
  109. ```bash
  110. bun install --frozen-lockfile
  111. bun run check
  112. bun run test
  113. bun run test:coverage
  114. bun run docs
  115. ```
  116. `bun run build` runs `vp pack`, preserving `build/index.js`, `build/server.js`,
  117. source maps, and bundled dependencies. Tests build first so package checks work
  118. from a clean checkout. `bun run dev` and `bun run dev:http` retain Bun's server
  119. watch mode; `bunx vp run dev` runs the same script. `vp dev` starts a Vite web
  120. server and is not this MCP server's development command.
  121. The server uses TypeScript 7.0.2. TypeDoc and OpenAPI type generation currently need the TypeScript 6 compiler
  122. API, so `tooling/compiler-api` keeps its own TypeScript 6.0.3 dependency. Install from the
  123. root; `bun run docs` still generates the existing documentation.
  124. `bun run update:deps` refreshes dependencies while keeping coverage aligned with
  125. Vite+'s bundled Vitest 5.0.3. Update those pins together when upgrading Vite+.
  126. The migration removed the generated `clearMocks: false` setting after the same
  127. 61 tests passed with Vitest 5 defaults. Coverage resolves the same 16 files as
  128. Vitest 4; no thresholds or exclusions were relaxed. No tsdown compatibility
  129. settings were needed because the original build used Bun.
  130. The unused Java/Axios generator stack was removed; typed `openapi-fetch` remains
  131. the shared client. Both current OpenAPI generators tested require the older
  132. TypeScript compiler API: Hey API 0.99.0 fails under TypeScript 7 before CLI help.
  133. The isolated, tested generator avoids changes to authentication, rate limiting
  134. and cache behavior.
  135. Release tooling still pulls `braces` 3.0.3, affected by
  136. [GHSA-vfj7-8cjw-p6xm](https://github.com/advisories/GHSA-vfj7-8cjw-p6xm);
  137. no patched version is published. This dependency is not included in the server
  138. bundle. Do not feed untrusted glob patterns to release tooling.
  139. ### Breaking changes and reviewed fixes
  140. - Deleting bookmarks, collections, tags or highlights, and bulk removal now
  141. requires `confirm: true`. Cleanup tools keep their existing preview flow.
  142. - HTTP binds to `127.0.0.1`; OAuth callbacks require matching, unexpired,
  143. single-use browser state. Remote access requires an authenticated proxy.
  144. - Bulk moves/updates/removals use the source collection's API endpoint.
  145. Bookmark updates preserve `collectionId`; omit URL/title when changing only
  146. other fields. Collection `0` means All and cannot be used for bulk mutations;
  147. `-1` means Unsorted.
  148. - Tags use upstream search operators, preserving pagination and total counts.
  149. Collection paths no longer depend on API ordering; mutations invalidate
  150. affected bookmark, search and collection-count caches.
  151. - Permanent upstream errors are not retried. Resource templates use the MCP
  152. SDK; unsupported resource subscriptions are no longer advertised.
  153. - MCPB packages contain bundled runtime code rather than development
  154. dependencies. Environment files, logs and local Codex state are excluded.
  155. These fixes address the substance of [PR #52](https://github.com/adeze/raindrop-mcp/pull/52)
  156. and [issues #54/#55](https://github.com/adeze/raindrop-mcp/issues/55).
  157. Older SDK v1/Zod 3 migrations are superseded by this SDK v2 setup. Framework
  158. replacement was unnecessary: existing SDK APIs and shared service helpers
  159. eliminated redundant code. Live Raindrop mutations and OAuth provider login
  160. remain manual validation steps.
  161. ### Commit message examples
  162. - `fix: handle empty tag merge payload`
  163. - `feat: add collection path filter`
  164. - `feat!: remove deprecated search parameter`
  165. Do not manually bump versions, push release tags, or run manual npm publish commands for normal releases.
  166. ## 📋 Recent Enhancements (v2.4.x)
  167. ### Smart Organization & Hierarchy
  168. - **AI Suggestions**: New `get_suggestions` tool provides organizational advice using Raindrop's API and MCP Sampling.
  169. - **Collection Tree**: `get_collection_tree` tool provides a hierarchical view with full breadcrumb paths.
  170. - **Bulk Move**: Added `move` operation to `bulk_edit_raindrops` for efficient library organization.
  171. - **Pagination Support**: Standardized `list_raindrops` and `bookmark_search` with pagination for large libraries.
  172. ### Safety & Quality
  173. - **Confirmation Logic**: Destructive tools (`empty_trash`, `cleanup_collections`) now require explicit confirmation.
  174. - **Standardized Naming**: All tools now use consistent snake_case naming conventions.
  175. - **CI/CD Pipeline**: Enhanced GitHub Actions with automated linting, type-checking, and cross-transport tests.
  176. - **Code Quality**: Established ESLint and Prettier configurations for maintainable development.
  177. ## 📋 Previous Enhancements (v2.3.3)
  178. ### Advanced Cleanup & Library Audit
  179. ## 📋 Previous Enhancements (v2.3.2)
  180. ### MCP Resource Links Implementation
  181. - Modern `resource` content following current MCP SDK best practices
  182. - Efficient data access: tools return lightweight links instead of full payloads
  183. - Better performance: clients fetch full bookmark/collection data only when needed
  184. - Seamless integration with dynamic resource system (`mcp://raindrop/{id}`)
  185. ### SDK & API Updates
  186. - Updated to the latest supported MCP SDK in this repository
  187. - Modern tool registration with improved descriptions
  188. - Fixed API endpoints and path parameters
  189. - All core tools fully functional
  190. ### Tool Optimization
  191. - Resource-efficient responses for bookmark/collection lists
  192. - Dynamic resource access via `mcp://collection/{id}` and `mcp://raindrop/{id}`
  193. - Better client UX with lighter list payloads
  194. - Full MCP compliance with official SDK patterns
  195. ### Service Layer Improvements
  196. - Reduced code through extracted common helpers
  197. - Consistent error handling and response processing
  198. - Enhanced type safety with generic handlers
  199. - Centralized endpoint building
  200. ### Testing Improvements
  201. - Stronger end-to-end coverage for MCP tool execution
  202. - Expanded integration tests for real-world client flows
  203. ### MCP 2.0 Preparation (Bulk Ops)
  204. - Laying groundwork for MCP 2.0 bulk-operation workflows and tooling
  205. ### OAuth (Coming Soon)
  206. - OAuth-based auth flow to simplify setup without manual tokens
  207. ### Note
  208. Apologies to anyone affected by the last couple of builds. Thank you for the patience and reports.
  209. ## License
  210. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.