reMarkable MCP Server (Read/Write)

io.github.praveensehgal由 GitHub 帳號 praveensehgal 發布v0.2.3更新於 Oct 24, 2026

Read, write, and manage your reMarkable tablet — browse, upload, create folders, move, delete, OCR

已驗證STDIO僅桌面檔案與儲存知識與記憶

概覽

AI 產生的概覽

本機 MCP 伺服器,讓 AI 助理瀏覽、讀取、搜尋、OCR、上傳、移動和刪除 reMarkable 平板上的文件。

可以做什麼
瀏覽、搜尋與列出文件:在資料夾間瀏覽、依標籤篩選、查看最近修改的檔案、檢查連線狀態,並支援跨文件內容搜尋與單一文件內關鍵字查找。讀取與擷取文字:取得鍵入文字、PDF 與 EPUB 內容,以及 PNG 或 SVG 頁面影像。辨識手寫:透過用戶端取樣、Google Vision 或 Tesseract 對筆記做 OCR。管理資料庫:上傳 PDF 或 EPUB、建立多層資料夾、移動或重新命名項目、刪除文件或資料夾。將文件註冊為 MCP 資源,提供文字、原始 PDF/EPUB 和頁面影像。
適用情境
適合把筆記、研究資料或日記存放在 reMarkable 平板,並希望助理讀取、搜尋或摘要這些內容(包含手寫頁面),或代為上傳檔案、整理資料庫的情境。也適合與 Obsidian 等個人知識管理流程搭配使用。
執行需求
以 Python 套件(uvx)透過 stdio 在桌面本機執行。需要可連線的 reMarkable 平板:啟用 USB 網頁介面、使用開發者模式的 SSH 模式,或使用需 reMarkable Connect 訂閱並註冊權杖的雲端模式。SSH 模式使用 REMARKABLE_SSH_HOST 與密鑰 REMARKABLE_SSH_PASSWORD。選用的 Google Vision OCR 需要 GOOGLE_VISION_API_KEY。
安裝前請注意
伺服器可寫入平板:上傳、建立資料夾、移動、重新命名和刪除,其中刪除具破壞性。SSH 模式需要開發者模式,README 稱這涉及回復原廠設定。SSH 密碼屬於裝置憑證,不要放入共用設定。Google Vision OCR 在免費額度用盡後會把頁面影像傳送給付費第三方服務。雲端模式需要訂閱。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 reMarkable MCP Server (Read/Write),將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

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 remarkable-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
  • Second brain integration — Use with Obsidian, note-taking apps, or any AI workflow

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


Quick Install

🔌 USB Web Interface (Recommended)

Connect via USB and enable the web interface in your tablet's Storage Settings.

[Install USB Web Mode in VS Code] [Install USB Web Mode in VS Code Insiders]

Setup:

  1. Connect your reMarkable via USB
  2. On your tablet: Settings → Storage → Enable "USB web interface"
  3. Install via the button above

Why USB Web?

  • ✅ Fast offline access over USB
  • ✅ No subscription required
  • ✅ Simple — just enable in Storage Settings
📋 Manual USB Web Configuration

Add to .vscode/mcp.json:

json
{  "servers": {    "remarkable": {      "command": "uvx",      "args": ["remarkable-mcp", "--usb"],      "env": {        "GOOGLE_VISION_API_KEY": "your-api-key"      }    }  }}

Troubleshooting:

  • Make sure your reMarkable is connected via USB and unlocked
  • Verify USB web interface is enabled in Settings → Storage
  • The tablet should be accessible at http://10.11.99.1

⚡ SSH Mode (Advanced)

For power users who need direct filesystem access. Faster than USB Web but requires developer mode (factory reset).

[Install SSH Mode in VS Code] [Install SSH Mode in VS Code Insiders]

Requirements: Developer mode enabled + USB connection to your reMarkable

📋 Manual SSH Configuration

Add to .vscode/mcp.json:

json
{  "servers": {    "remarkable": {      "command": "uvx",      "args": ["remarkable-mcp", "--ssh"],      "env": {        "GOOGLE_VISION_API_KEY": "your-api-key"      }    }  }}

See SSH Setup Guide for detailed instructions.


☁️ Cloud Mode (Wireless)

For wireless or remote access when USB isn't available. Requires a reMarkable Connect subscription and is significantly slower than USB modes.

📋 Cloud Mode Setup
1. Get a One-Time Code

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

2. Convert to Token
bash
uvx remarkable-mcp --register YOUR_CODE
3. Install

[Install Cloud Mode in VS Code] [Install Cloud Mode in VS Code Insiders]

Or configure manually in .vscode/mcp.json:

json
{  "inputs": [    {      "type": "promptString",      "id": "remarkable-token",      "description": "reMarkable API Token",      "password": true    },    {      "type": "promptString",      "id": "google-vision-key",      "description": "Google Vision API Key",      "password": true    }  ],  "servers": {    "remarkable": {      "command": "uvx",      "args": ["remarkable-mcp"],      "env": {        "REMARKABLE_TOKEN": "${input:remarkable-token}",        "GOOGLE_VISION_API_KEY": "${input:google-vision-key}"      }    }  }}


Connection Modes

Choose the connection method that works best for you:

ModeSetup DifficultySpeedRequirementsBest For
🔌 USB Web (Recommended)✅ EasyFastUSB cable, enable in Storage SettingsEveryone
⚡ SSH⚠️ AdvancedVery FastDeveloper mode, USB connectionPower users
☁️ Cloud✅ EasySlowreMarkable Connect subscriptionRemote/wireless access

📖 Detailed Setup Guides:

  • USB Web Interface Setup — Recommended — simple setup, full feature support
  • SSH Setup Guide — For advanced users who need filesystem access
  • Cloud setup is documented in the Quick Install section above

OpenClaw Integration

remarkable-mcp works as an OpenClaw skill. Add to your openclaw.json:

json
{  "mcpServers": {    "remarkable": {      "command": "uvx",      "args": ["remarkable-mcp", "--usb"]    }  }}

Install from ClawHub:

bash
clawhub install remarkable-mcp

Or copy the SKILL.md from this repository into your ~/.openclaw/skills/remarkable-mcp/ directory.


Tools

ToolDescription
remarkable_readRead and extract text from documents (with pagination and search)
remarkable_browseNavigate folders, search by document name, or filter by tags
remarkable_searchSearch content across multiple documents (with tag filtering)
remarkable_recentGet recently modified documents
remarkable_statusCheck connection status
remarkable_imageGet PNG/SVG images of pages (supports OCR via sampling)
remarkable_uploadUpload a PDF or EPUB file to a folder on the tablet
remarkable_mkdirCreate folders with nested path support (mkdir -p)
remarkable_deleteDelete a document or folder (destructive)
remarkable_moveMove or rename documents and folders

All tools return structured JSON with hints for next actions.

📖 Full Tools Documentation

Claude Code Integration

Add to your ~/.claude/settings.json:

json
{  "mcpServers": {    "remarkable": {      "command": "uvx",      "args": ["remarkable-mcp-rw", "--wifi"],      "env": {        "REMARKABLE_HOST": "http://YOUR_TABLET_IP"      }    }  }}

WiFi Setup

  1. On your reMarkable: Settings → Storage → Enable "USB web interface"
  2. Find your tablet's IP: Settings → General → About → IP address
  3. Set REMARKABLE_HOST to http://YOUR_IP in the config above
  4. The USB web interface works over both USB and WiFi on the same network

Smart Features

  • Auto-redirect — Browsing a document path returns its content automatically
  • Auto-OCR — Notebooks with no typed text automatically enable OCR
  • 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)
  • Tag support — Filter and organize documents by tags

Example Usage

python
# Read a documentremarkable_read("Meeting Notes")
# Search for keywordsremarkable_read("Project Plan", grep="deadline")
# Enable OCR for handwritten notesremarkable_read("Journal", include_ocr=True)
# Browse your libraryremarkable_browse("/Work/Projects")
# Filter by tagsremarkable_browse("/", tags=["important"])remarkable_browse("/Work", tags=["project", "active"])
# Search across documentsremarkable_search("meeting", grep="action items")
# Search with tag filterremarkable_search("project", tags=["work"])
# Get recent documentsremarkable_recent(limit=10)
# Get a page image (for visual content like UI mockups or diagrams)remarkable_image("UI Mockup", page=1)
# Get SVG for editing in design toolsremarkable_image("Wireframe", output_format="svg")
# Get image with OCR text extraction (uses sampling if configured)remarkable_image("Handwritten Notes", include_ocr=True)
# Transparent background for compositingremarkable_image("Logo Sketch", background="#00000000")
# Compatibility mode: return resource URI instead of embedded resourceremarkable_image("Diagram", compatibility=True)

Resources

Documents are automatically registered as MCP resources:

URI SchemeDescription
remarkable:///{path}.txtExtracted text content
remarkableraw:///{path}.pdfOriginal PDF file (SSH only)
remarkableraw:///{path}.epubOriginal EPUB file (SSH only)
remarkableimg:///{path}.page-{N}.pngPNG image of page N (notebooks only)
remarkablesvg:///{path}.page-{N}.svgSVG vector image of page N (notebooks only)

📖 Full Resources Documentation


OCR for Handwriting

For handwritten content, remarkable-mcp offers several OCR backends. Choose based on your setup and requirements:

BackendSetupQualityOfflineBest For
SamplingNo API keyDepends on client model✅Users with capable AI clients
Google VisionAPI keyExcellent❌Best handwriting accuracy
TesseractSystem installPoor for handwriting✅Printed text, offline fallback

Quick Setup

Set REMARKABLE_OCR_BACKEND in your MCP config:

json
{  "env": {    "REMARKABLE_OCR_BACKEND": "sampling"  }}

Options: sampling, google, tesseract, auto

📖 Sampling OCR (No API Key)

Uses your MCP client's AI model for OCR. Works with clients that support MCP sampling (VS Code + Copilot, Claude Desktop, etc.).

Pros:

  • No additional API keys needed
  • Quality depends on your client's model (GPT-4, Claude, etc.)
  • Private — handwriting stays local to your client

Cons:

  • Only available with sampling-capable clients
  • Falls back to Google Vision (if API key configured) or Tesseract if sampling unavailable
📖 Google Cloud Vision

Provides consistently excellent handwriting recognition.

Setup:

  1. Enable Cloud Vision API
  2. Create an API key
  3. Add to config: "GOOGLE_VISION_API_KEY": "your-key"

Cost: 1,000 free requests/month, then ~$1.50 per 1,000.

📖 Full Google Vision Setup Guide

📖 Tesseract (Fallback)

Open-source OCR designed for printed text. Poor results with handwriting, but useful as an offline fallback.

bash
# Install Tesseract# macOSbrew install tesseract
# Ubuntu/Debiansudo apt install tesseract-ocr
# Windowschoco install tesseract

Default Behavior (auto)

When REMARKABLE_OCR_BACKEND=auto (default):

  1. Google Vision (if GOOGLE_VISION_API_KEY is set)
  2. Tesseract (fallback)

SSH vs Cloud Comparison

FeatureSSH ModeCloud API
Speed⚡ 10-100x fasterSlower
Offline✅ Yes❌ No
Subscription✅ Not required❌ Connect required
Raw files✅ PDFs, EPUBs❌ Not available
SetupDeveloper modeOne-time code

📖 SSH Setup Guide


Advanced Configuration

Root Path Filtering

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

json
{  "servers": {    "remarkable": {      "command": "uvx",      "args": ["remarkable-mcp", "--ssh"],      "env": {        "REMARKABLE_ROOT_PATH": "/Work",        "GOOGLE_VISION_API_KEY": "your-api-key"      }    }  }}

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:

json
{  "servers": {    "remarkable": {      "command": "uvx",      "args": ["remarkable-mcp", "--ssh"],      "env": {        "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.


Use Cases

Research & Writing

Use remarkable-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

GuideDescription
SSH SetupEnable developer mode and configure SSH
Google Vision SetupSet up handwriting OCR
Tools ReferenceDetailed tool documentation
Resources ReferenceMCP resources documentation
Capability NegotiationMCP protocol capabilities
DevelopmentContributing and development setup
Future PlansRoadmap and planned features

Development

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

📖 Development Guide


License

MIT


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

來源:README.md,提交 d385834

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.2.3最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分