reMarkable MCP Server

reMarkable MCP Server

Unlock the full potential of your reMarkable tablet as a second brain for AI assistants. This MCP server lets Claude, VS Code Copilot, and other AI tools read, search, and traverse your entire reMarkable library — including handwritten notes via OCR.

Why rm-mcp?

Your reMarkable tablet is a powerful tool for thinking, note-taking, and research. But that knowledge stays trapped on the device. This MCP server changes that:

• Full library access — Browse folders, search documents, read any file
• Typed text extraction — Native support for Type Folio and typed annotations
• Handwriting OCR — Convert handwritten notes to searchable text
• PDF & EPUB support — Extract text from documents, plus your annotations
• Smart search — Find content across your entire library
• Organise your library — Rename, move, and create folders (nothing is ever deleted)
• Second brain integration — Use with Obsidian, note-taking apps, or any AI workflow

Whether you're researching, writing, or developing ideas, rm-mcp lets you leverage everything on your reMarkable through AI.

Quick Install

Uses the reMarkable Cloud API. Requires a reMarkable Connect subscription.

One-command setup (recommended)

uvx rm-mcp --setup

This opens your browser, prompts for the one-time code, and prints the ready-to-paste config for Claude Code and Claude Desktop.

Manual setup

1. Get a One-Time Code

Go to my.remarkable.com/device/browser/connect and generate a code.

2. Convert to Token

uvx rm-mcp --register YOUR_CODE

3. Add to your MCP client

Claude Code:

claude mcp add remarkable \  -e REMARKABLE_TOKEN='<paste token from step 2>' \  -e REMARKABLE_OCR_BACKEND=sampling \  -- uvx rm-mcp@latest

Claude Desktop — add to claude_desktop_config.json (use full path to uvx, e.g. from which uvx):

{  "mcpServers": {    "remarkable": {      "command": "/Users/YOU/.local/bin/uvx",      "args": ["rm-mcp@latest"],      "env": {        "REMARKABLE_TOKEN": "<paste token from step 2>"      }    }  }}

Tools

All tools are read-only and return structured JSON with hints for next actions.

📖 Full Tools Documentation

Smart Features

• Multi-page read — Read all pages at once with pages="all", or a range like pages="1-3"
• Grep auto-redirect — grep automatically finds and jumps to the matching page
• Auto-redirect — Browsing a document path returns its content automatically
• Auto-OCR — Notebooks with no typed text automatically enable OCR (opt out with auto_ocr=False)
• Full-text search — Reading a document indexes it for fast future searches
• Compact mode — Use compact_output=True to reduce token usage in responses
• Batch search — Search across multiple documents in one call
• Vision support — Get page images for visual context (diagrams, mockups, sketches)
• Sampling OCR — Use client's AI for OCR on images (no API key needed)

Example Usage

# Read a documentremarkable_read("Meeting Notes")
# Read all pages at onceremarkable_read("Meeting Notes", pages="all")
# Read a range of pagesremarkable_read("Research Paper", pages="1-3")
# Search for keywords (auto-redirects to matching page)remarkable_read("Project Plan", grep="deadline")
# Enable OCR for handwritten notesremarkable_read("Journal", include_ocr=True)
# Browse your libraryremarkable_browse("/Work/Projects")
# Search across documentsremarkable_search("meeting", grep="action items")
# Get recent documents with previewsremarkable_recent(limit=5, include_preview=True)
# Get a page imageremarkable_image("UI Mockup", page=1)
# Get image with OCR text extractionremarkable_image("Handwritten Notes", include_ocr=True)

Resources

Documents are automatically registered as MCP resources:

📖 Full Resources Documentation

OCR for Handwriting

rm-mcp uses sampling OCR — your MCP client's AI model extracts text from handwritten notes. No additional API keys or services needed.

How It Works

When you use include_ocr=True, rm-mcp sends page images to your client's LLM (Claude, GPT-4, etc.) via MCP sampling. The model reads the handwriting and returns the text.

Usage

# OCR on a page imageremarkable_image("Handwritten Notes", include_ocr=True)
# OCR when reading a notebookremarkable_read("Journal", include_ocr=True)

Requirements

• Your MCP client must support the sampling capability (VS Code + Copilot, Claude Desktop, etc.)
• REMARKABLE_OCR_BACKEND=sampling (this is the default)

Advanced Configuration

Root Path Filtering

Limit the MCP server to a specific folder on your reMarkable. All operations will be scoped to this folder:

{  "servers": {    "remarkable": {      "command": "uvx",      "args": ["rm-mcp"],      "env": {        "REMARKABLE_TOKEN": "your-token",        "REMARKABLE_ROOT_PATH": "/Work"      }    }  }}

With this configuration:

• remarkable_browse("/") shows contents of /Work
• remarkable_browse("/Projects") shows /Work/Projects
• Documents outside /Work are not accessible

Useful for:

• Focusing on work documents during office hours
• Separating personal and professional notes
• Limiting scope for specific AI workflows

Custom Background Color

Set the default background color for image rendering:

{  "servers": {    "remarkable": {      "command": "uvx",      "args": ["rm-mcp"],      "env": {        "REMARKABLE_TOKEN": "your-token",        "REMARKABLE_BACKGROUND_COLOR": "#FFFFFF"      }    }  }}

Supported formats:

• #RRGGBB — RGB hex (e.g., #FFFFFF for white)
• #RRGGBBAA — RGBA hex (e.g., #00000000 for transparent)

Default is #FBFBFB (reMarkable paper color). This affects both the remarkable_image tool and image resources.

All Environment Variables

Most users only need REMARKABLE_TOKEN. The rest are for advanced tuning.

Use Cases

Research & Writing

Use rm-mcp while working in an Obsidian vault or similar to transfer knowledge from your handwritten notes into structured documents. AI can read your research notes and help develop your ideas.

Daily Review

Ask your AI assistant to summarize your recent notes, find action items, or identify patterns across your journal entries.

Document Search

Find that half-remembered note by searching across your entire library — including handwritten content.

Knowledge Management

Treat your reMarkable as a second brain that AI can access. Combined with tools like Obsidian, you can build a powerful personal knowledge system.

Documentation

Development

git clone https://github.com/wavyrai/rm-mcp.gitcd rm-mcpuv sync --all-extrasuv run pytest test_server.py -v

📖 Development Guide

License

MIT

Built with rmscene, PyMuPDF, and inspiration from ddvk/rmapi.