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.
npx agentmods add instructions/xinthink/reader-mcp-server/claude-mdgit clone --depth 1 https://github.com/xinthink/reader-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/xinthink/reader-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/xinthink/reader-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/xinthink/reader-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00707 | $0.00707 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
reader-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Model Context Protocol (MCP) server that integrates with Readwise Reader API. It exposes a list_documents tool that allows MCP-compatible clients like Claude Desktop to interact with a user's Readwise Reader library.
Commands for Development
Running the Server
To run the server locally:
uv run main.py
Dependencies
This project uses uv for dependency management. Key dependencies include:
mcp[cli]- The Model Context Protocol Python SDKhttpx- For async HTTP requests to the Readwise APIdotenv- For loading environment variables
To install dependencies:
uv sync
Environment Setup
The server requires an ACCESS_TOKEN environment variable with a Readwise Reader API token. This can be provided either:
- As an environment variable
- In a
.envfile in the project directory
Code Architecture
Core Components
-
main.py - The main server implementation:
- Uses FastMCP from the MCP Python SDK
- Implements the
list_documentstool - Manages the Readwise API client lifecycle
- Handles parameter validation and API communication
-
models.py - Data models:
ReaderDocument- Represents a document from Readwise ReaderListDocumentResponse- Response format for the document list API
Key Implementation Details
- The server uses the FastMCP framework which handles all MCP protocol details
- It connects to the Readwise Reader API at
https://readwise.io/api/v3 - The
list_documentstool supports filtering by location, update time, content inclusion, and pagination - Authentication is handled via the ACCESS_TOKEN environment variable
- The server implements proper error handling and logging
MCP Integration
The server exposes one tool:
list_documents- Lists documents from the Readwise Reader library with flexible filtering options
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.
- 3d ago First seen · 100 lines · 707 tokens per session scan A c7ad64d8f42d
reader-mcp-server CLAUDE.md is an instructions file published in the GitHub repository xinthink/reader-mcp-server (11 stars, last pushed 5mo ago), licensed MIT. It adds 707 tokens to every session, about $0.0035 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 2026-08-30.
Other instructions, from other repositories
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
agent-plugins copilot-instructions.md
Instructions for dmgrok/agent-plugins, covering agent skills directory - ai agent instructions, project overview, architecture, core components and critical workflows.
NovelAI-Image-MCP AGENTS.md
Instructions for xinvxueyuan/NovelAI-Image-MCP, covering agents.md, 项目是什么, 仓库布局（uv + pnpm monorepo，turbo 编排）, 常用命令 and 硬约束（不要触碰）.
claude-plugins CLAUDE.md
Instructions for sshh12/claude-plugins, covering claude-plugins, repo structure, adding a plugin, docs and skills authoring reference.
skrills AGENTS.md
Instructions for athola/skrills, covering ai agent development guidelines, guiding principles, development workflow, implementation cycle and when stuck.
skills CLAUDE.md
Instructions for cel-expr/skills, covering common expression language (cel) skills, project structure & architecture, build and test commands, go cli and bazel.