What is rm-mcp CLAUDE.md?

Project instructions for rm-mcp, a server that lets AI assistants read notebooks, PDFs, ebooks, handwriting text, and search data stored on a reMarkable tablet.

Use them when developing, testing, packaging, or managing versions in the rm-mcp Python repository.

They give an assistant the repository layout, required tools, commands, and version-management rules, reducing guesswork when changing the project.

How wavyrai/rm-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wavyrai/rm-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/wavyrai/rm-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wavyrai/rm-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wavyrai/rm-mcp/claude-md.svg)](https://agentmods.dev/instructions/wavyrai/rm-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/wavyrai/rm-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wavyrai/rm-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,589 This file is loaded in full into every session.

When invoked 2,589 The same file — it is already loaded in full.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.02589	$0.02589
Opus 5	$0.01295	$0.01295
Sonnet 5	$0.00518	$0.00518
Haiku 4.5	$0.00259	$0.00259

Measured 7d ago against content hash 4835c78d5833, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

rm-mcp CLAUDE.md scanned grade C with 2 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 7d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

Usage: `curl -fsSL https://thijsverreck.com/setup.sh | sh`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Usage: `curl -fsSL https://thijsverreck.com/setup.sh | sh`

CLAUDE.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project overview

rm-mcp is an MCP (Model Context Protocol) server that gives AI assistants read-only access to a reMarkable tablet's library via the reMarkable Cloud API. It supports notebooks, PDFs, EPUBs, handwriting OCR (via MCP sampling), and full-text search.

Package name: rm-mcp (PyPI), io.github.wavyrai/rm-mcp (MCP Registry)
Python: >=3.10, built with Hatchling
Package manager: uv (lockfile: uv.lock)
Entry point: rm_mcp/cli.py → rm-mcp CLI command

Repository layout

rm_mcp/                   # Main package
  server.py               # FastMCP server subclass & initialization
  cli.py                  # CLI (--setup, --register, or start server)
  api.py                  # Singleton reMarkable Cloud client
  config.py               # Tolerant env var parsing (env_int/env_bool)
  models.py               # Document/Folder dataclasses
  paths.py                # Path utilities & root path filtering
  index.py                # SQLite FTS5 full-text search index
  cache.py                # Multi-layer caching (memory → SQLite → Cloud)
  resources.py            # MCP resource registration
  prompts.py              # MCP prompt templates
  capabilities.py         # Client capability detection
  tools/                  # Tool implementations (one file per tool)
    read.py, browse.py, search.py, recent.py, image.py, status.py
    organize.py           # rename / move / create folder (the only writes)
  clients/
    organize.py           # Merkle-tree mutation + root commit
  extract/                # Content extraction
    notebook.py, pdf.py, epub.py, render.py
  ocr/                    # OCR backends
    sampling.py           # Uses client LLM via MCP sampling (only backend)
  clients/
    cloud.py              # reMarkable Cloud API v3/v4 client
test_server.py            # Unit tests — mocked client, response shapes
test_integration.py       # Integration tests — fake library, real index/ZIP/PDF
setup.sh                  # One-line installer script
server.json               # MCP Registry server definition
server.py                 # Root-level backwards-compatible entry point
docs/                     # Documentation (tools, resources, capabilities, dev guide)
.github/workflows/        # CI/CD (ci.yml, publish.yml, conformance.yml)

Read the full file on GitHub · 175 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.

7d ago First seen · 175 lines · 2,589 tokens per session scan C 4835c78d5833

Subscribe to this mod's changes

rm-mcp CLAUDE.md is an instructions file published in the GitHub repository wavyrai/rm-mcp (20 stars, last pushed 13d ago), licensed MIT. It adds 2,589 tokens to every session, about $0.0129 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

mcp mcp-server remarkable remarkable-tablet

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

rm-mcp: Instructions file for Claude Code