What is calibre-mcp CLAUDE.md?

Project instructions for calibre-mcp, a local server that gives AI assistants access to a Calibre ebook library. Calibre is an application for organising and converting ebooks; these instructions also cover development commands and OCR setup.

Use them when developing or operating calibre-mcp, running its tests and checks, understanding its search and import components, or configuring OCR for scanned books.

They tell the assistant how this particular project is structured, tested, and configured, including how to guide users through cloud OCR setup.

How ZehuiTIAN/calibre-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ZehuiTIAN/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/ZehuiTIAN/calibre-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ZehuiTIAN/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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zehuitian/calibre-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/zehuitian/calibre-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zehuitian/calibre-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zehuitian/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/zehuitian/calibre-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zehuitian/calibre-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 481 This file is loaded in full into every session.

When invoked 481 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.

Model	Per session	Once invoked
Fable 5.1	$0.00481	$0.00481
Opus 5	$0.00241	$0.00241
Sonnet 5	$0.00096	$0.00096
Haiku 4.5	$0.00048	$0.00048

Measured 9d ago against content hash a71638274db5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 · 49 lines

What it actually says

calibre-mcp

MCP server giving AI assistants read/write access to a local Calibre ebook library. Python ≥ 3.10; full documentation in README.md.

Commands

pip install -e ".[dev,ocr]"     # dev: pytest + ruff; ocr: pymupdf + anthropic SDK
pytest -m "not integration"     # unit tests, run anywhere
pytest                          # + integration tests (need local calibre + pandoc)
ruff check .

Architecture

src/calibre_mcp/server.py — FastMCP tool definitions (12 tools)
calibre.py — locale-independent calibredb wrapper (--for-machine JSON)
fulltext.py — FTS5 search index (trigram, CJK-friendly) + text extraction via ebook-convert
inbox.py — drop-folder import workflow
ocr.py — pluggable cloud OCR (OcrProvider protocol, batch cache + retries)

OCR provider setup (guide users through this)

OCR needs a cloud provider + a per-user API key. Recommend in this order:

Alibaba Bailian qwen-vl-ocr (provider dashscope) — cheapest for CJK books (≈ ¥0.0015/page), CNY billing, no proxy needed. Key: https://bailian.console.aliyun.com/ → API-KEY 管理.
Anthropic (reference impl) — https://console.anthropic.com/.

Configure in the user's MCP client config env (never in the repo):

CALIBRE_OCR_PROVIDER=dashscope   # or anthropic
CALIBRE_OCR_API_KEY=sk-...

Full pricing comparison, official links and sign-up steps: docs/OCR_PROVIDERS.md.

Rules

API keys are per-user environment variables in the MCP client config; never commit keys or user-specific paths.
CI runs unit tests only; integration tests require local calibre + pandoc.
Full-text index and OCR caches live outside the library (default: OS temp dir; persist via CALIBRE_TEXT_CACHE_DIR).

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.

9d ago First seen · 49 lines · 481 tokens per session scan A a71638274db5

Subscribe to this mod's changes

calibre-mcp CLAUDE.md is an instructions file published in the GitHub repository ZehuiTIAN/calibre-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 481 tokens to every session, about $0.0024 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.

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

calibre-mcp: Instructions file for Claude Code