agentmods.dev

readwise-mcp-server: Instructions file for Claude Code

CLAUDE.md

readwise-mcp-server CLAUDE.md is an instructions file for Claude Code from ngpestelos/readwise-mcp-server. It costs 3,130 tokens per session, scanned A, original, MIT.

A set of project instructions for a small Python server that connects Readwise to the Model Context Protocol. Readwise is a service for saving and reviewing reading highlights, while the Model Context Protocol lets AI tools call external services in a standard way.

In plain words
What is it for?
Use it when working on this Readwise integration, especially for understanding its architecture, available tools, data syncing, duplicate handling, and filename rules.
Why use it?
It gives an AI coding agent the project’s intended structure, priorities, and tested approaches. That reduces the chance of adding unnecessary complexity or breaking existing behavior.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ngpestelos/readwise-mcp-server's own configuration. It tells Claude Code how to work on readwise-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything readwise-mcp-server configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/ngpestelos/src/readwise-mcp-server/venv/bin/python.

not rated 0repo 1mo ago A scan 3,130 tokens original MIT
View source ↗ ngpestelos/readwise-mcp-server
Reuse

Borrowing it

Nothing to install: this file belongs to ngpestelos/readwise-mcp-server. 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/ngpestelos/readwise-mcp-server/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ngpestelos/readwise-mcp-server

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.

agentmods badge for readwise-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ngpestelos/readwise-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/ngpestelos/readwise-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ngpestelos/readwise-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ngpestelos/readwise-mcp-server/claude-md/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 readwise-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ngpestelos/readwise-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ngpestelos/readwise-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,130 This file is loaded in full into every session.
When invoked 3,130 The same file — it is already loaded in full.
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 $0.03130 $0.03130
Opus 5.5 $0.01252 $0.01252
Sonnet 5.5 $0.00626 $0.00626
Haiku 4.5 $0.00313 $0.00313

Measured 2mo ago against content hash 416c608e1f40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

readwise-mcp-server CLAUDE.md 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 2mo 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.

CLAUDE.md · 432 lines

How it starts

The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Readwise MCP Server - Project Instructions

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Minimal Python MCP Server for Readwise Integration

This is a token-efficient, single-file Python MCP server that provides Readwise API access through the Model Context Protocol (MCP). It replaces a broken Node.js implementation with a clean, maintainable Python implementation using the FastMCP framework.

Status: Production-ready (2026-01-23)

Core Philosophy

Simplicity Over Abstraction

  • Single-file architecture (~371 lines)
  • No unnecessary abstractions or over-engineering
  • Clear, readable code over clever tricks
  • Direct approach: one function = one purpose

Token Efficiency

  • 8 essential tools vs 13+ in previous implementation
  • Combined operations (fetch + dedupe + save)
  • Smart defaults minimize required parameters
  • Structured returns, no raw markdown dumps
  • ~60% token overhead reduction

Battle-Tested Logic

Reuses proven logic from .claude/scripts/readwise-backfill.py:

  • State management
  • Synced range optimization
  • Filesystem deduplication
  • Filename sanitization
  • ID extraction

Project Structure

readwise-mcp-server/
├── server.py              # Main MCP server (371 lines)
├── test_server.py         # Test suite (340 lines, 21 tests)
├── requirements.txt       # Python dependencies (6 packages)
├── README.md              # User documentation
├── CLAUDE.md              # This file - Claude Code instructions
├── IMPLEMENTATION_SUMMARY.md  # Technical implementation details
└── venv/                  # Python virtual environment

Technical Stack

  • Framework: FastMCP (official Anthropic MCP library)
  • HTTP Client: requests (simple, reliable)
  • Testing: pytest + pytest-asyncio
  • Python: 3.9+ (uses timezone.utc for compatibility)
  • Type Hints: Full typing for IDE support

8 Essential Tools

  1. readwise_daily_review() - Fetch today's highlights to Daily Reviews/
  2. readwise_import_recent(category, limit) - Import recent docs since last import
  3. readwise_backfill(target_date, category) - Paginate to target with optimization
  4. readwise_book_highlights(title, book_id) - Get book highlights
  5. readwise_search_highlights(query, limit) - Search highlights by text
  6. readwise_state_info() - Show current state and synced ranges
  7. readwise_init_ranges() - Scan filesystem to build synced_ranges
  8. readwise_reset_state(clear_ranges) - Clear state file

Read the full file on GitHub · 432 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. 2mo ago First seen · 432 lines · 3,130 tokens per session scan A 416c608e1f40

Subscribe to this mod's changes

readwise-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ngpestelos/readwise-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 3,130 tokens to every session, about $0.0125 per session on Opus 5.5. 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

readwise-mcp-server CLAUDE.md compared with instructions from other repositories

readwise-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
readwise-mcp-server CLAUDE.mdngpestelos/readwise-mcp-serverInstructions file01mo agoMITA3,130Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode