agentmods.dev

calibre-mcp: Instructions file for Claude Code

CLAUDE.md

calibre-mcp CLAUDE.md is an instructions file for Claude Code from caelum29/calibre-mcp. It costs 1,746 tokens per session, scanned A, original, MIT.

A set of instructions for building and maintaining a TypeScript MCP server that connects to Calibre, an application for managing ebook and PDF libraries. It describes the target setup, required behavior, and restrictions that edits must preserve.

In plain words
What is it for?
Developing the Calibre server, preserving compatibility with Claude Desktop, Claude Code CLI, and Cowork, handling library metadata, and avoiding known concurrency and argument-format problems.
Why use it?
It gives a coding agent the project’s fixed assumptions and known failure points, reducing the risk of changes that break reading, writing, search, or client compatibility.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is caelum29/calibre-mcp's own configuration. It tells Claude Code how to work on calibre-mcp 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 calibre-mcp configures →

not rated 13repo +1 19d ago A scan 1,746 tokens original MIT
View source ↗ caelum29/calibre-mcp npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to caelum29/calibre-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/caelum29/calibre-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/caelum29/calibre-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.

agentmods badge for calibre-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/caelum29/calibre-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/caelum29/calibre-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/caelum29/calibre-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/caelum29/calibre-mcp/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 calibre-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/caelum29/calibre-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/caelum29/calibre-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,746 This file is loaded in full into every session.
When invoked 1,746 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 $0.01746 $0.01746
Opus 5 $0.00873 $0.00873
Sonnet 5 $0.00349 $0.00349
Haiku 4.5 $0.00175 $0.00175

Measured 9d ago against content hash 7d4f50659d02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

calibre-mcp 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 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.

CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Calibre MCP Server

Macro goal

Build the most capable Calibre MCP server in existence — a single, reliable TypeScript server that replaces the current two-server hack (FaceDeer/calibre_full_mcp_server for reads + shell-command-mcp/calibredb for writes) running in Claude Desktop today.

It must:

  1. Match the full tool surface of every known Calibre MCP server (feature parity baseline).
  2. Add semantic search — the headline differentiator no existing TS server has.
  3. Fix the write path that breaks in Cowork (MCP error -32602, args-as-strings).

Target environment (ground-truth, do not re-derive)

  • Calibre 9.10, macOS Apple Silicon (macOS 26 beta), Node v24.
  • Library: ~801 books in Programming Books (default) + a Reaserch Books lib, under ~/Documents/Books/.
  • Mostly PDF/EPUB, technical, EN + RU. Many have raw filenames (795731065, top.dvi, B0CZS7H23N.pdf) → metadata recovery matters.
  • Calibre GUI is normally running + Content Server live on :8080.
  • Clients: Claude Desktop, Claude Code CLI, Cowork. Transport: stdio.

Hard constraints / gotchas (these killed earlier attempts)

  • GUI-concurrency lock is real (reproduced). With the app open, direct calibredb/SQLite/DB-API access is refused or dangerous. Safe live paths: Content Server HTTP (reads) or calibredb routed through the server URL. Treat the DB as read-mostly; never race the GUI on writes. Write path RESOLVED (docs/dev/CAPABILITIES.md §2): route writes through the running server — shell calibredb --with-library http://localhost:8080/#Lib (it speaks /cdb/cmd for us), the server permitting writes via --enable-local-write; a direct /cdb/set-fields HTTP client is a LATER opt.
  • -32602 serialization bug (our Cowork failure) is client-side, confirmed, unfixed. Defense = Zod coercion on every input: z.coerce.number(), z.preprocess(JSON.parse, …) for arrays/objects, unions for ids. Never z.coerce.boolean() on "false".
  • stdout is sacred on stdio — all logs to stderr. One stray console.log corrupts the stream.
  • FTS is book-level only (no PDF page / EPUB spine location) and not enabled on this library yet. Calibre has no OCR; PDF is the worst conversion/extraction input.
  • Writes gated by default — read-only unless an explicit env flag + per-tool annotations allow it.
  • Clients strip structuredContent (Claude Desktop drops it from the tool-result notification; some clients surface only text blocks). Anything the model must act on — ranked hits, excerpts, nextCursor tokens — must ALSO appear in the text content; the cover-board widget refetches its data via the widget-internal calibre_board_data tool for the same reason (#26, D-017).

Read the full file on GitHub · 91 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 · 91 lines · 1,746 tokens per session scan A 7d4f50659d02

Subscribe to this mod's changes

calibre-mcp CLAUDE.md is an instructions file published in the GitHub repository caelum29/calibre-mcp (13 stars, last pushed 19d ago), licensed MIT. It adds 1,746 tokens to every session, about $0.0087 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.

anthropiccalibreclaudeclaude-desktopebook-managementebooks
Related

Other instructions, from other repositories

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 · 5,153 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens