What is pdf-reader-mcp CLAUDE.md?

A set of coding instructions for a local server that reads and examines PDF files. It covers the server’s purpose, its 19 tools, and which questions it should answer.

It helps an agent read text and images, render pages, search content, summarize files, inspect structure and fonts, extract tables, and report metadata, annotations, signatures, tags, and other PDF objects.

It keeps PDF reading separate from checking whether a PDF follows a standard. This helps prevent the reader from treating observations about a file as pass-or-fail judgments.

How shuji-bonji/pdf-reader-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shuji-bonji/pdf-reader-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/shuji-bonji/pdf-reader-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shuji-bonji/pdf-reader-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/shuji-bonji/pdf-reader-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/shuji-bonji/pdf-reader-mcp/claude-md)

Your own site

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

Per session 1,349 This file is loaded in full into every session.

When invoked 1,349 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	$0.01349	$0.01349
Opus 5.5	$0.00540	$0.00540
Sonnet 5.5	$0.00270	$0.00270
Haiku 4.5	$0.00135	$0.00135

Measured 21d ago against content hash cc3ab9166410, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pdf-reader-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 21d 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pdf-reader-mcp - 開発ガイド

仕様の正本は openspec/specs/（OpenSpec）。仕様 ID・PR の種類・承認の記録の規則は AGENTS.md。

プロジェクト概要

PDF の中身を読み取り・報告する MCP サーバ。PDF family における「実体」担当。

層	サーバ	一行定義
正典	pdf-spec-mcp	仕様は何を要求するか
実体	本サーバ	中身に何があるか（合否は言わない）
判定	pdf-verify-mcp	それは本物で、規格に適っているか
生成	pdf-writer-mcp	仕様どおりに書けるか

残タスク: docs/TASKS.md
責務分担の提案: mcps/pdf-family-role-architecture.md
上位仕様: pdf-agent-stack/docs/foundation/pdf-reader-mcp.md

ツール一覧（18・3 tier）

Tier	ツール
1 基本	`read_text` / `read_url` / `read_images` / `render_page` / `search_text` / `get_metadata` / `get_page_count` / `summarize`
2 構造検査	`inspect_structure` / `inspect_catalog` / `inspect_fonts` / `inspect_annotations` / `inspect_signatures` / `inspect_tags` / `extract_tables` / `extract_structured_text` / `locate_objects`
3 比較	`compare_structure`

境界ルール（ツール追加時の判断基準）

ISO 規格等に照らした compliant / valid / pass-fail を返すなら pdf-verify-mcp、観測結果を返すだけなら本サーバ。

本サーバは「何があるか」を報告する。「それでいいのか」は判定せず、利用者（LLM）に委ねる。

inspect_signatures は署名フィールドの存在を報告する（暗号検証は verify の verify_signatures）
inspect_tags は構造ツリーを報告する（PDF/UA 準拠の判定は verify の validate_conformance）

この規則の例外だった Tier 3 の validate_tagged / validate_metadata は削除した（変更 remove-validate-tools。経緯は docs/TASKS.md の B-1）。新しい validate_* をここに足さないこと —— openspec/specs/tools-list の SPEC-READER-TOOLS-LIST-002 と受入テスト tests/tier1/tools-list.test.ts が止める。

アーキテクチャの要点

index.ts → tools/{tier1,tier2,tier3}/*.ts（zod スキーマ + ハンドラ）
  services/pdfjs-service.ts  : pdfjs 依存（構造ツリー・オペレータリスト）
  services/pdflib-service.ts : pdf-lib 依存（辞書レベル）
  utils/formatter.ts         : markdown 化

ツール追加は該当 tier に 1 ファイル + 登録
console.log 禁止（MCP の stdio を汚染する）。ログは stderr へ

Read the full file on GitHub · 92 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.

21d ago Changed · -12 lines · -213 tokens per session cc3ab9166410
23d ago Changed · +2 lines · +44 tokens per session 4449993f6d9d
24d ago Changed · +5 tokens per session 92dd4dcaeb88
1mo ago Changed · -5 tokens per session e768cc49af37
2mo ago First seen · 102 lines · 1,518 tokens per session scan A 9578621cf1c0

Subscribe to this mod's changes

pdf-reader-mcp CLAUDE.md is an instructions file published in the GitHub repository shuji-bonji/pdf-reader-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 1,349 tokens to every session, about $0.0054 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.

Documents PDF mcp-server pdf-decipher pdf-reader

pdf-reader-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pdf-reader-mcp CLAUDE.mdshuji-bonji/pdf-reader-mcp	Instructions file	2	yesterday	MIT	A	1,349	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

pdf-reader-mcp: Instructions file for Claude Code