reMarkable MCP Server (Read/Write)

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/praveensehgal-remarkable

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

5 read · 3 write · 1 delete · 1 not yet classified

Secrets

1 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Python package

Tools (10)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• remarkable_browse

  <usecase>Browse your reMarkable library or search for documents.</usecase> <instructions> Three modes: 1. Browse mode (default): List contents of a folder - Use path="/" for root folder - Use path="/FolderName" to navigate into folders 2. Search mode: Find documents by name - Set query="search term" to search across all documents 3. Filter by tags: Find documents with specific tags - Set tags=["tag1", "tag2"] to filter by tags - Works in both browse and search modes Results include document names, types, modification dates, and tags. Note: If REMARKABLE_ROOT_PATH is configured…

• remarkable_deleteDelete Document or Foldercan change or delete data

  <usecase>Delete a document or folder from your reMarkable tablet.</usecase> <instructions> Permanently deletes the item at the given path. This cannot be undone. For folders, all contents are deleted recursively. Use remarkable_browse to verify the path before deleting. </instructions> <parameters> - path: Exact path to the document or folder to delete </parameters> <examples> - remarkable_delete("/01 Work/Old Project") - remarkable_delete("/05 Personal/Reading/finished-book.pdf") </examples>

• remarkable_image

  <usecase>Get an image of a specific page from a reMarkable document.</usecase> <instructions> Renders a notebook or document page as an image (PNG or SVG). This is useful for: - Viewing hand-drawn diagrams, sketches, or UI mockups - Getting visual context that text extraction might miss - Implementing designs based on hand-drawn wireframes - SVG format for scalable vector graphics that can be edited ## Response Formats By default, images are returned as embedded resources (EmbeddedResource) which include the full image data inline: - PNG: Returned as BlobResourceContents with base64-encoded …

• remarkable_mkdirCreate Folder

  <usecase>Create a folder (or nested folders) on your reMarkable tablet.</usecase> <instructions> Creates the folder at the given path. If intermediate folders don't exist, they are created automatically (like mkdir -p). Use this to set up your folder structure before uploading documents. </instructions> <parameters> - path: Full folder path to create (e.g., "/01 Work/NN Inc/Galaxy") </parameters> <examples> - remarkable_mkdir("/01 Work") - remarkable_mkdir("/01 Work/USMS-JPATS/JMISFIN") - remarkable_mkdir("/05 Personal/Reading") </examples>

• remarkable_moveMove or Rename

  <usecase>Move or rename a document/folder on your reMarkable tablet.</usecase> <instructions> Move a document or folder to a new location, optionally renaming it. To rename without moving, set destination to the current parent folder. To move without renaming, omit new_name. </instructions> <parameters> - source: Current path of the item - destination: New parent folder path - new_name: Optional new name for the item </parameters> <examples> - remarkable_move("/Meeting Notes", "/01 Work/USMS-JPATS") - remarkable_move("/old-name.pdf", "/", new_name="new-name.pdf") - remarkable_move("/01 Work/D…

• remarkable_read

  <usecase>Read and extract text content from a reMarkable document.</usecase> <instructions> Extracts content from a document with pagination to preserve context window. Content types: - "text" (default): Full extracted text (PDF/EPUB content + annotations) - "raw": Original PDF/EPUB text only (no annotations). SSH mode only. - "annotations": Only annotations, highlights, and handwritten notes Use pagination to read large documents without overwhelming context: - Start with page=1 (default) - Check "more" field - if true, there's more content - Use "next_page" value to get the next page Use …

• remarkable_recent

  <usecase>Get your most recently modified documents.</usecase> <instructions> Returns documents sorted by modification date (newest first). Optionally includes a text preview of each document's content. Use this to quickly find what you were working on recently. Note: If REMARKABLE_ROOT_PATH is configured, only documents within that folder are included. </instructions> <parameters> - limit: Maximum documents to return (default: 10, max: 50 without preview, 10 with preview) - include_preview: Include first ~200 chars of text content (default: False) </parameters> <examples> - remarkable_recent…

• remarkable_search

  <usecase>Search across multiple documents and return matching content.</usecase> <instructions> Searches document names for the query, then optionally searches content with grep. Can filter by tags to narrow results. Returns summaries from multiple documents in a single call. This is efficient for finding information across your library without making many individual tool calls. Limits: - Max 5 documents per search (to keep response size manageable) - Returns first page (~8000 chars) of each matching document - Use grep to filter to relevant sections </instructions> <parameters> - query: Sea…

• remarkable_status

  <usecase>Check connection status and authentication with reMarkable Cloud.</usecase> <instructions> Returns authentication status and diagnostic information. Use this to verify your connection or troubleshoot issues. </instructions> <examples> - remarkable_status() </examples>

• remarkable_uploadUpload Document

  <usecase>Upload a PDF or EPUB file to your reMarkable tablet.</usecase> <instructions> Uploads a local file from your computer to the tablet. Only PDF and EPUB formats are supported. The destination is a folder path on the tablet where the file will be placed. If the destination folder doesn't exist, use remarkable_mkdir first. </instructions> <parameters> - file_path: Absolute path to the local PDF or EPUB file - destination: Folder path on tablet (default: "/" for root) </parameters> <examples> - remarkable_upload("/Users/praveen/report.pdf", "/01 Work/USMS-JPATS") - remarkable_upload("/tmp…

Signals

Stars

3

Forks

0

Open issues

0

Weekly downloads

29

Last commit

Mar 18, 2026 (7 months ago)

Last release

Mar 18, 2026 (7 months ago)

Last package publish

Mar 18, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.praveensehgal/remarkable

Version

0.2.3

Auth

API key

Packages

pypi remarkable-mcp-rw

License

MIT

Repository

github.com/praveensehgal/remarkable-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql