remarkable-mcp

remarkable-mcp is a skill for Claude Code, Codex from lukaisailovic/remarkable-mcp. It costs 98 tokens per session (1,903 once invoked), scanned A, original, MIT.

Instructions for using an MCP server that manages reMarkable tablet notebooks, folders, PDFs, EPUBs, pages, and handwriting. reMarkable is an e-ink tablet for reading and writing notes.

In plain words
What is it for?
Use it for reMarkable notebooks and notes, PDF or EPUB uploads, handwriting exports, and Mermaid diagrams drawn on the tablet.
Why use it?
It explains how an agent can find, read, create, edit, upload, and organize tablet content without guessing the server’s conventions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for reMarkable notebooks and notes, PDF or EPUB uploads, handwriting exports, and Mermaid diagrams drawn on the tablet.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lukaisailovic/remarkable-mcp/remarkable-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add lukaisailovic/remarkable-mcp --skill remarkable-mcp
Clone the repo
git clone --depth 1 https://github.com/lukaisailovic/remarkable-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for remarkable-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukaisailovic/remarkable-mcp/remarkable-mcp/github.svg)](https://agentmods.dev/skills/lukaisailovic/remarkable-mcp/remarkable-mcp)
Your own site
<a href="https://agentmods.dev/skills/lukaisailovic/remarkable-mcp/remarkable-mcp"><img src="https://agentmods.dev/badge/skills/lukaisailovic/remarkable-mcp/remarkable-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for remarkable-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/lukaisailovic/remarkable-mcp/remarkable-mcp"><img src="https://agentmods.dev/badge/skills/lukaisailovic/remarkable-mcp/remarkable-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,903 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.01903
Opus 5 $0.00049 $0.00951
Sonnet 5 $0.00020 $0.00381
Haiku 4.5 $0.00010 $0.00190

Measured 9d ago against content hash 685cd9eb0a2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

remarkable-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/remarkable-mcp/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

remarkable-mcp

The client exposes one tool: remarkable_execute. Pass a JavaScript async arrow function. Methods live on rme. No TypeScript. No process / require / fetch.

async () => {
  const folder = await rme.mkdir({ name: "Projects" });
  await rme.createNotebook({ name: "Ideas", parent: folder.id });
  await rme.writeText({
    notebook: "Ideas",
    newPage: true,
    blocks: [
      { text: "Ship it", style: "title" },
      { text: "Talk to design", style: "checkbox" },
    ],
  });
  return await rme.read({ notebook: "Ideas", page: 2 });
};

Batch related work in one call. Writes apply once after the function returns (SSH restarts xochitl; rmfakecloud commits sync). Do not call refresh() unless you need an extra apply mid-script. Return only what the user asked for.

Resolve

  • notebook (also used for folders, PDFs, EPUBs): UUID, unique visible name, or /Folder/Name. Duplicate names throw ambiguous name.
  • page: 1-based. Write defaults: last page. exportPage defaults to page 1.
  • Ink points: [x, y] in 0–1 from the top-left.
  • remove = trash (parent: "trash"), not unlink.

Item: { id, name, type, fileType, parent, path, pageCount, tags, lastModified, trashed, page?, pages? }. type is notebook | folder | pdf | epub.

Page writes (writeText / writeInk / writeMermaid / addPage / removePage / exportPage) are for notebooks. PDFs/EPUBs have no ink pages — read extracts text, download returns bytes.

Handwriting is not OCR'd. Typed Type Folio text is in read. Ink is in exportPage.

search matches name/path (optional tag), not page text. To find content, list/browse then read.

Discover

Call Args Returns
rme.list { includeTrash?, folder? } Library. Trash hidden unless includeTrash. folder limits to that folder's children.
rme.browse { path? } One folder (default /). A notebook path returns that single item.
rme.search { query, tag? } Name/path substring. tag is an extra filter.
rme.info { notebook } One item. Notebooks include pages[].title (first title/heading, else first line).
rme.tags {} Sorted unique tag names on the tablet.

Read the full file on GitHub · 158 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 158 lines · 98 tokens per session scan A 685cd9eb0a2c

Subscribe to this mod's changes

remarkable-mcp is a skill published in the GitHub repository lukaisailovic/remarkable-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 98 tokens to every session and 1,903 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories