@shuji-bonji/pdf-reader-mcp 0.2.0

package/CHANGELOG.md

@@ -0,0 +1,44 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.2.0] - 2026-02-08
+
+### Added
+
+- **Tier 3 tools**: `validate_tagged`, `validate_metadata`, `compare_structure`
+- **E2E test suite**: 146 tests across 9 test suites with performance baseline tracking
+- **CI/CD**: GitHub Actions workflow for automated testing (Node 18/20/22) and npm publishing
+- **Batch processor utility**: `processInBatches()` and `processAndReduce()` for large PDF handling
+- **`analyzeTagsFromDoc()`**: Pre-loaded document variant for shared document lifecycle
+
+### Changed
+
+- **Parallel page processing**: `extractTextFromDoc`, `searchText`, `countImagesFromDoc`, `extractImages`, `checkSignatures`, `analyzeAnnotations`, `analyzeTags` now use `Promise.all` for concurrent page access
+- **`validateTagged()`**: Eliminated double document load — now loads once and runs `analyzeTagsFromDoc` + `countImagesFromDoc` in parallel via `Promise.all`
+- **Test infrastructure**: Extracted constants (`constants.ts`), cached baseline reads, added `measureAndCheck()` helper for DRY performance tests
+- **Test naming**: All test descriptions translated to English for international readability
+
+### Performance
+
+- `searchText`: ~68% faster (parallel text extraction across pages)
+- `getMetadata`: ~27% faster (parallel signature check)
+- `validateMetadata`: ~25% faster
+- `analyzeFonts`: ~57% faster
+- `getMetadata-all-7` (batch): ~17% faster
+
+## [0.1.0] - 2026-02-07
+
+### Added
+
+- **Tier 1 tools** (7): `get_page_count`, `get_metadata`, `read_text`, `search_text`, `read_images`, `read_url`, `summarize`
+- **Tier 2 tools** (5): `inspect_structure`, `inspect_tags`, `inspect_fonts`, `inspect_annotations`, `inspect_signatures`
+- Input validation with Zod schemas and path security checks
+- Y-coordinate-based text extraction preserving natural reading order
+- Unit tests for core utilities and pdfjs-service
+
+[0.2.0]: https://github.com/shuji-bonji/pdf-reader-mcp/compare/v0.1.0...v0.2.0
+[0.1.0]: https://github.com/shuji-bonji/pdf-reader-mcp/releases/tag/v0.1.0

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 shuji-bonji
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.ja.md

@@ -0,0 +1,190 @@
+# PDF Reader MCP Server
+
+[![npm version](https://img.shields.io/npm/v/@shuji-bonji/pdf-reader-mcp)](https://www.npmjs.com/package/@shuji-bonji/pdf-reader-mcp)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Built with Claude Code](https://img.shields.io/badge/Built%20with-Claude%20Code-blueviolet?logo=anthropic)](https://claude.ai/code)
+
+[English](./README.md) | **日本語**
+
+PDF 内部構造解析に特化した MCP (Model Context Protocol) サーバー。
+
+既存の pdf-reader-mcp がテキスト抽出の薄いラッパーに留まるのに対し、本プロジェクトは **PDF の内部構造を読み解く** ことに焦点を当てています。[pdf-spec-mcp](https://github.com/nicholasgriffintn/pdf-spec-mcp) と組み合わせることで、仕様知識に基づいた構造解析・検証が可能になります。
+
+## ツール一覧
+
+### Tier 1: 基本機能 ✅ (v0.1.0)
+
+| ツール           | 説明                                                |
+| ---------------- | --------------------------------------------------- |
+| `get_page_count` | ページ数の軽量取得                                  |
+| `get_metadata`   | メタデータ抽出（タイトル、著者、PDF版、タグ有無等） |
+| `read_text`      | テキスト抽出（Y座標ベースの読み順保持）             |
+| `search_text`    | 全文検索（前後コンテキスト付き）                    |
+| `read_images`    | 画像抽出（base64、メタデータ付き）                  |
+| `read_url`       | URLからリモートPDFを取得して処理                    |
+| `summarize`      | 全体概要レポート（メタデータ + テキスト + 画像数）  |
+
+### Tier 2: 構造解析 ✅ (v0.1.0)
+
+| ツール                | 説明                                         |
+| --------------------- | -------------------------------------------- |
+| `inspect_structure`   | オブジェクトツリー・カタログ辞書の解析       |
+| `inspect_tags`        | Tagged PDF のタグツリー可視化                |
+| `inspect_fonts`       | フォント一覧（埋め込み/サブセット/Type判定） |
+| `inspect_annotations` | 注釈一覧（タイプ別分類）                     |
+| `inspect_signatures`  | 電子署名フィールドの構造解析                 |
+
+### Tier 3: 検証・分析 ✅ (v0.2.0)
+
+| ツール              | 説明                                           |
+| ------------------- | ---------------------------------------------- |
+| `validate_tagged`   | PDF/UA タグ構造の検証（8項目チェック）         |
+| `validate_metadata` | メタデータの仕様適合チェック（10項目チェック） |
+| `compare_structure` | 2つのPDFの構造差分比較（プロパティ＋フォント） |
+
+## セットアップ
+
+### Claude Desktop
+
+`claude_desktop_config.json` に追加:
+
+```json
+{
+	"mcpServers": {
+		"pdf-reader-mcp": {
+			"command": "node",
+			"args": ["/path/to/pdf-reader-mcp/dist/index.js"]
+		}
+	}
+}
+```
+
+### Claude Code
+
+```bash
+claude mcp add pdf-reader-mcp node /path/to/pdf-reader-mcp/dist/index.js
+```
+
+### 開発用
+
+```bash
+git clone https://github.com/shuji-bonji/pdf-reader-mcp.git
+cd pdf-reader-mcp
+npm install
+npm run build
+```
+
+## 使用例
+
+### ページ数の取得
+
+```
+get_page_count({ file_path: "/path/to/document.pdf" })
+→ 42
+```
+
+### テキスト検索
+
+```
+search_text({
+  file_path: "/path/to/spec.pdf",
+  query: "digital signature",
+  pages: "1-20",
+  max_results: 10
+})
+→ Found 5 matches (page 3, 7, 12, 15, 18)
+```
+
+### PDF概要
+
+```
+summarize({ file_path: "/path/to/document.pdf" })
+→ | Pages | 42 |
+  | PDF Version | 2.0 |
+  | Tagged | Yes |
+  | Signatures | No |
+  | Images | 15 |
+```
+
+### PDF/UA タグ検証
+
+```
+validate_tagged({ file_path: "/path/to/document.pdf" })
+→ ✅ [TAG-001] Document is marked as tagged
+  ✅ [TAG-002] Structure tree root exists
+  ⚠️ [TAG-004] Heading hierarchy has gaps: H1, H3
+  ❌ [TAG-005] Document has 3 image(s) but no Figure tags
+```
+
+### メタデータ検証
+
+```
+validate_metadata({ file_path: "/path/to/document.pdf" })
+→ ✅ [META-001] Title: "Annual Report 2025"
+  ⚠️ [META-002] Author is missing
+  ✅ [META-006] PDF version: 2.0
+```
+
+### 構造比較
+
+```
+compare_structure({
+  file_path_1: "/path/to/v1.pdf",
+  file_path_2: "/path/to/v2.pdf"
+})
+→ | Page Count  | 10 | 12 | ❌ |
+  | PDF Version | 1.7 | 2.0 | ❌ |
+  | Tagged      | true | true | ✅ |
+```
+
+## 技術スタック
+
+- **TypeScript** + MCP TypeScript SDK
+- **pdfjs-dist** (Mozilla) — テキスト/画像抽出
+- **pdf-lib** (Tier 2〜) — 低レベル構造解析
+- **Vitest** — テスト
+- **Zod** — 入力バリデーション
+
+## テスト
+
+```bash
+npm test          # テスト実行
+npm run test:watch  # ウォッチモード
+```
+
+## アーキテクチャ
+
+```
+pdf-reader-mcp/
+├── src/
+│   ├── index.ts           # MCP Server エントリーポイント
+│   ├── constants.ts       # 定数
+│   ├── types.ts           # 型定義
+│   ├── tools/
+│   │   ├── tier1/         # 基本ツール（7ツール）
+│   │   ├── tier2/         # 構造解析（5ツール）
+│   │   ├── tier3/         # 検証・分析（3ツール）
+│   │   └── index.ts       # ツール登録の集約
+│   ├── services/          # PDF ライブラリラッパー
+│   │   ├── pdfjs-service.ts      # pdfjs-dist ラッパー
+│   │   ├── pdflib-service.ts     # pdf-lib ラッパー
+│   │   ├── validation-service.ts # 検証・比較ロジック
+│   │   └── url-fetcher.ts        # URL取得
+│   ├── schemas/           # Zod バリデーションスキーマ
+│   └── utils/             # ユーティリティ
+└── tests/
+```
+
+## pdf-spec-mcp との連携
+
+pdf-spec-mcp は PDF 仕様（ISO 32000-2 等）の知識を提供する MCP サーバーです。両方を有効にすることで、LLM は以下のようなワークフローを実行できます:
+
+1. `summarize` で PDF の概要を把握
+2. `inspect_tags` でタグ構造を確認
+3. pdf-spec-mcp の `get_requirements` で PDF/UA 要件を取得
+4. `validate_tagged` で適合性を検証
+5. `compare_structure` で修正前後の構造差分を確認
+
+## ライセンス
+
+MIT

package/README.md

@@ -0,0 +1,206 @@
+# PDF Reader MCP Server
+
+[![npm version](https://img.shields.io/npm/v/@shuji-bonji/pdf-reader-mcp)](https://www.npmjs.com/package/@shuji-bonji/pdf-reader-mcp)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Built with Claude Code](https://img.shields.io/badge/Built%20with-Claude%20Code-blueviolet?logo=anthropic)](https://claude.ai/code)
+
+**English** | [日本語](./README.ja.md)
+
+An MCP (Model Context Protocol) server specialized in **deciphering PDF internal structures**.
+
+While typical PDF MCP servers are thin wrappers for text extraction, this project focuses on **reading and analyzing the internal structure** of PDF documents. Pair it with [pdf-spec-mcp](https://github.com/nicholasgriffintn/pdf-spec-mcp) for specification-aware structural analysis and validation.
+
+## Features
+
+**15 tools** organized into three tiers:
+
+### Tier 1: Basic Operations
+
+| Tool             | Description                                              |
+| ---------------- | -------------------------------------------------------- |
+| `get_page_count` | Lightweight page count retrieval                         |
+| `get_metadata`   | Full metadata extraction (title, author, PDF version...) |
+| `read_text`      | Text extraction with Y-coordinate reading order          |
+| `search_text`    | Full-text search with surrounding context                |
+| `read_images`    | Image extraction as base64 with metadata                 |
+| `read_url`       | Fetch and process remote PDFs from URLs                  |
+| `summarize`      | Quick overview report (metadata + text + image count)    |
+
+### Tier 2: Structure Inspection
+
+| Tool                  | Description                                      |
+| --------------------- | ------------------------------------------------ |
+| `inspect_structure`   | Object tree and catalog dictionary analysis      |
+| `inspect_tags`        | Tagged PDF structure tree visualization          |
+| `inspect_fonts`       | Font inventory (embedded/subset/type detection)  |
+| `inspect_annotations` | Annotation listing (categorized by subtype)      |
+| `inspect_signatures`  | Digital signature field structure analysis        |
+
+### Tier 3: Validation & Analysis
+
+| Tool                | Description                                          |
+| ------------------- | ---------------------------------------------------- |
+| `validate_tagged`   | PDF/UA tag structure validation (8 checks)           |
+| `validate_metadata` | Metadata conformance checking (10 checks)            |
+| `compare_structure` | Structural diff between two PDFs (properties + fonts)|
+
+## Installation
+
+### npx (recommended)
+
+```bash
+npx @shuji-bonji/pdf-reader-mcp
+```
+
+### Claude Desktop
+
+Add to your `claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "pdf-reader-mcp": {
+      "command": "npx",
+      "args": ["-y", "@shuji-bonji/pdf-reader-mcp"]
+    }
+  }
+}
+```
+
+### Claude Code
+
+```bash
+claude mcp add pdf-reader-mcp -- npx -y @shuji-bonji/pdf-reader-mcp
+```
+
+### From Source
+
+```bash
+git clone https://github.com/shuji-bonji/pdf-reader-mcp.git
+cd pdf-reader-mcp
+npm install
+npm run build
+```
+
+## Usage Examples
+
+### Get Page Count
+
+```
+get_page_count({ file_path: "/path/to/document.pdf" })
+→ 42
+```
+
+### Search Text
+
+```
+search_text({
+  file_path: "/path/to/spec.pdf",
+  query: "digital signature",
+  pages: "1-20",
+  max_results: 10
+})
+→ Found 5 matches (page 3, 7, 12, 15, 18)
+```
+
+### Summarize
+
+```
+summarize({ file_path: "/path/to/document.pdf" })
+→ | Pages | 42 |
+  | PDF Version | 2.0 |
+  | Tagged | Yes |
+  | Signatures | No |
+  | Images | 15 |
+```
+
+### Validate Tagged Structure (PDF/UA)
+
+```
+validate_tagged({ file_path: "/path/to/document.pdf" })
+→ ✅ [TAG-001] Document is marked as tagged
+  ✅ [TAG-002] Structure tree root exists
+  ⚠️ [TAG-004] Heading hierarchy has gaps: H1, H3
+  ❌ [TAG-005] Document has 3 image(s) but no Figure tags
+```
+
+### Validate Metadata
+
+```
+validate_metadata({ file_path: "/path/to/document.pdf" })
+→ ✅ [META-001] Title: "Annual Report 2025"
+  ⚠️ [META-002] Author is missing
+  ✅ [META-006] PDF version: 2.0
+```
+
+### Compare Structure
+
+```
+compare_structure({
+  file_path_1: "/path/to/v1.pdf",
+  file_path_2: "/path/to/v2.pdf"
+})
+→ | Page Count  | 10 | 12 | ❌ |
+  | PDF Version | 1.7 | 2.0 | ❌ |
+  | Tagged      | true | true | ✅ |
+```
+
+## Tech Stack
+
+- **TypeScript** + MCP TypeScript SDK
+- **pdfjs-dist** (Mozilla) — text/image extraction, tag tree, annotations
+- **pdf-lib** — low-level object structure analysis
+- **Vitest** — unit + E2E testing (185 tests)
+- **Biome** — linting + formatting
+- **Zod** — input validation
+
+## Testing
+
+```bash
+npm test              # Run all tests (unit + E2E)
+npm run test:e2e      # E2E tests only (146 tests)
+npm run test:watch    # Watch mode
+```
+
+## Architecture
+
+```
+pdf-reader-mcp/
+├── src/
+│   ├── index.ts              # MCP Server entry point
+│   ├── constants.ts          # Shared constants
+│   ├── types.ts              # Type definitions
+│   ├── tools/
+│   │   ├── tier1/            # Basic tools (7)
+│   │   ├── tier2/            # Structure inspection (5)
+│   │   ├── tier3/            # Validation & analysis (3)
+│   │   └── index.ts          # Tool registration
+│   ├── services/
+│   │   ├── pdfjs-service.ts        # pdfjs-dist wrapper (parallel page processing)
+│   │   ├── pdflib-service.ts       # pdf-lib wrapper
+│   │   ├── validation-service.ts   # Validation & comparison logic
+│   │   └── url-fetcher.ts          # URL fetching
+│   ├── schemas/              # Zod validation schemas
+│   └── utils/
+│       ├── pdf-helpers.ts    # PDF utilities (page range parsing, file I/O)
+│       ├── batch-processor.ts # Batch processing for large PDFs
+│       ├── formatter.ts      # Output formatting
+│       └── error-handler.ts  # Error handling
+└── tests/
+    ├── tier1/                # Unit tests
+    └── e2e/                  # E2E tests (9 suites, 146 tests)
+```
+
+## Pairing with pdf-spec-mcp
+
+[pdf-spec-mcp](https://github.com/nicholasgriffintn/pdf-spec-mcp) provides PDF specification knowledge (ISO 32000-2, etc.). With both servers enabled, an LLM can perform specification-aware workflows:
+
+1. `summarize` — get a PDF overview
+2. `inspect_tags` — examine the tag structure
+3. pdf-spec-mcp `get_requirements` — fetch PDF/UA requirements
+4. `validate_tagged` — check conformance
+5. `compare_structure` — diff before/after fixes
+
+## License
+
+MIT

package/dist/constants.d.ts

@@ -0,0 +1,22 @@
+/**
+ * pdf-reader-mcp shared constants
+ */
+/** Maximum response size in characters */
+export declare const CHARACTER_LIMIT = 25000;
+/** Maximum PDF file size in bytes (50MB) */
+export declare const MAX_FILE_SIZE: number;
+/** Default page limit for text extraction */
+export declare const DEFAULT_PAGE_LIMIT = 50;
+/** Maximum number of search results to return */
+export declare const MAX_SEARCH_RESULTS = 100;
+/** Default context characters around search matches */
+export declare const DEFAULT_SEARCH_CONTEXT = 80;
+/** Server info */
+export declare const SERVER_NAME = "pdf-reader-mcp";
+export declare const SERVER_VERSION = "0.2.0";
+/** Response format enum */
+export declare enum ResponseFormat {
+    MARKDOWN = "markdown",
+    JSON = "json"
+}
+//# sourceMappingURL=constants.d.ts.map

package/dist/constants.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"constants.d.ts","sourceRoot":"","sources":["../src/constants.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,0CAA0C;AAC1C,eAAO,MAAM,eAAe,QAAS,CAAC;AAEtC,4CAA4C;AAC5C,eAAO,MAAM,aAAa,QAAmB,CAAC;AAE9C,6CAA6C;AAC7C,eAAO,MAAM,kBAAkB,KAAK,CAAC;AAErC,iDAAiD;AACjD,eAAO,MAAM,kBAAkB,MAAM,CAAC;AAEtC,uDAAuD;AACvD,eAAO,MAAM,sBAAsB,KAAK,CAAC;AAEzC,kBAAkB;AAClB,eAAO,MAAM,WAAW,mBAAmB,CAAC;AAC5C,eAAO,MAAM,cAAc,UAAU,CAAC;AAEtC,2BAA2B;AAC3B,oBAAY,cAAc;IACxB,QAAQ,aAAa;IACrB,IAAI,SAAS;CACd"}

package/dist/constants.js

@@ -0,0 +1,23 @@
+/**
+ * pdf-reader-mcp shared constants
+ */
+/** Maximum response size in characters */
+export const CHARACTER_LIMIT = 25_000;
+/** Maximum PDF file size in bytes (50MB) */
+export const MAX_FILE_SIZE = 50 * 1024 * 1024;
+/** Default page limit for text extraction */
+export const DEFAULT_PAGE_LIMIT = 50;
+/** Maximum number of search results to return */
+export const MAX_SEARCH_RESULTS = 100;
+/** Default context characters around search matches */
+export const DEFAULT_SEARCH_CONTEXT = 80;
+/** Server info */
+export const SERVER_NAME = 'pdf-reader-mcp';
+export const SERVER_VERSION = '0.2.0';
+/** Response format enum */
+export var ResponseFormat;
+(function (ResponseFormat) {
+    ResponseFormat["MARKDOWN"] = "markdown";
+    ResponseFormat["JSON"] = "json";
+})(ResponseFormat || (ResponseFormat = {}));
+//# sourceMappingURL=constants.js.map

package/dist/constants.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"constants.js","sourceRoot":"","sources":["../src/constants.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,0CAA0C;AAC1C,MAAM,CAAC,MAAM,eAAe,GAAG,MAAM,CAAC;AAEtC,4CAA4C;AAC5C,MAAM,CAAC,MAAM,aAAa,GAAG,EAAE,GAAG,IAAI,GAAG,IAAI,CAAC;AAE9C,6CAA6C;AAC7C,MAAM,CAAC,MAAM,kBAAkB,GAAG,EAAE,CAAC;AAErC,iDAAiD;AACjD,MAAM,CAAC,MAAM,kBAAkB,GAAG,GAAG,CAAC;AAEtC,uDAAuD;AACvD,MAAM,CAAC,MAAM,sBAAsB,GAAG,EAAE,CAAC;AAEzC,kBAAkB;AAClB,MAAM,CAAC,MAAM,WAAW,GAAG,gBAAgB,CAAC;AAC5C,MAAM,CAAC,MAAM,cAAc,GAAG,OAAO,CAAC;AAEtC,2BAA2B;AAC3B,MAAM,CAAN,IAAY,cAGX;AAHD,WAAY,cAAc;IACxB,uCAAqB,CAAA;IACrB,+BAAa,CAAA;AACf,CAAC,EAHW,cAAc,KAAd,cAAc,QAGzB"}

package/dist/index.d.ts

@@ -0,0 +1,9 @@
+#!/usr/bin/env node
+/**
+ * pdf-reader-mcp - MCP server for PDF structure analysis.
+ *
+ * Provides tools to read, inspect, and validate PDF internals.
+ * Designed to work alongside pdf-spec-mcp for specification-aware analysis.
+ */
+export {};
+//# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AACA;;;;;GAKG"}

package/dist/index.js

@@ -0,0 +1,35 @@
+#!/usr/bin/env node
+/**
+ * pdf-reader-mcp - MCP server for PDF structure analysis.
+ *
+ * Provides tools to read, inspect, and validate PDF internals.
+ * Designed to work alongside pdf-spec-mcp for specification-aware analysis.
+ */
+// IMPORTANT: Guard stdout before any imports.
+// pdfjs-dist's warn() uses console.log (= stdout), which corrupts the
+// stdio JSON-RPC stream. Redirect console.log/console.warn to stderr.
+const _originalConsoleLog = console.log;
+const _originalConsoleWarn = console.warn;
+console.log = (...args) => console.error('[log]', ...args);
+console.warn = (...args) => console.error('[warn]', ...args);
+import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
+import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
+import { SERVER_NAME, SERVER_VERSION } from './constants.js';
+import { registerAllTools } from './tools/index.js';
+const server = new McpServer({
+    name: SERVER_NAME,
+    version: SERVER_VERSION,
+});
+// Register all tools
+registerAllTools(server);
+// Start the server with stdio transport
+async function main() {
+    const transport = new StdioServerTransport();
+    await server.connect(transport);
+    console.error(`${SERVER_NAME} v${SERVER_VERSION} running via stdio`);
+}
+main().catch((error) => {
+    console.error('Fatal error:', error);
+    process.exit(1);
+});
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AACA;;;;;GAKG;AAEH,8CAA8C;AAC9C,sEAAsE;AACtE,sEAAsE;AACtE,MAAM,mBAAmB,GAAG,OAAO,CAAC,GAAG,CAAC;AACxC,MAAM,oBAAoB,GAAG,OAAO,CAAC,IAAI,CAAC;AAC1C,OAAO,CAAC,GAAG,GAAG,CAAC,GAAG,IAAe,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,OAAO,EAAE,GAAG,IAAI,CAAC,CAAC;AACtE,OAAO,CAAC,IAAI,GAAG,CAAC,GAAG,IAAe,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,QAAQ,EAAE,GAAG,IAAI,CAAC,CAAC;AAExE,OAAO,EAAE,SAAS,EAAE,MAAM,yCAAyC,CAAC;AACpE,OAAO,EAAE,oBAAoB,EAAE,MAAM,2CAA2C,CAAC;AACjF,OAAO,EAAE,WAAW,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAC7D,OAAO,EAAE,gBAAgB,EAAE,MAAM,kBAAkB,CAAC;AAEpD,MAAM,MAAM,GAAG,IAAI,SAAS,CAAC;IAC3B,IAAI,EAAE,WAAW;IACjB,OAAO,EAAE,cAAc;CACxB,CAAC,CAAC;AAEH,qBAAqB;AACrB,gBAAgB,CAAC,MAAM,CAAC,CAAC;AAEzB,wCAAwC;AACxC,KAAK,UAAU,IAAI;IACjB,MAAM,SAAS,GAAG,IAAI,oBAAoB,EAAE,CAAC;IAC7C,MAAM,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;IAChC,OAAO,CAAC,KAAK,CAAC,GAAG,WAAW,KAAK,cAAc,oBAAoB,CAAC,CAAC;AACvE,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,OAAO,CAAC,KAAK,CAAC,cAAc,EAAE,KAAK,CAAC,CAAC;IACrC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}

package/dist/schemas/common.d.ts

@@ -0,0 +1,14 @@
+/**
+ * Common Zod schemas shared across tools.
+ */
+import { z } from 'zod';
+import { ResponseFormat } from '../constants.js';
+/** File path parameter for local PDF files */
+export declare const FilePathSchema: z.ZodString;
+/** Optional page range parameter */
+export declare const PagesSchema: z.ZodOptional<z.ZodString>;
+/** Response format parameter */
+export declare const ResponseFormatSchema: z.ZodDefault<z.ZodNativeEnum<typeof ResponseFormat>>;
+/** URL parameter for remote PDFs */
+export declare const UrlSchema: z.ZodString;
+//# sourceMappingURL=common.d.ts.map

package/dist/schemas/common.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"common.d.ts","sourceRoot":"","sources":["../../src/schemas/common.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AACxB,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AAEjD,8CAA8C;AAC9C,eAAO,MAAM,cAAc,aAGqD,CAAC;AAEjF,oCAAoC;AACpC,eAAO,MAAM,WAAW,4BAGmE,CAAC;AAE5F,gCAAgC;AAChC,eAAO,MAAM,oBAAoB,sDAGsD,CAAC;AAExF,oCAAoC;AACpC,eAAO,MAAM,SAAS,aAGmC,CAAC"}

package/dist/schemas/common.js

@@ -0,0 +1,26 @@
+/**
+ * Common Zod schemas shared across tools.
+ */
+import { z } from 'zod';
+import { ResponseFormat } from '../constants.js';
+/** File path parameter for local PDF files */
+export const FilePathSchema = z
+    .string()
+    .min(1, 'File path is required')
+    .describe('Absolute path to a local PDF file (e.g., "/path/to/document.pdf")');
+/** Optional page range parameter */
+export const PagesSchema = z
+    .string()
+    .optional()
+    .describe('Page range to process. Format: "1-5", "3", or "1,3,5-7". Omit for all pages.');
+/** Response format parameter */
+export const ResponseFormatSchema = z
+    .nativeEnum(ResponseFormat)
+    .default(ResponseFormat.MARKDOWN)
+    .describe('Output format: "markdown" for human-readable, "json" for structured data');
+/** URL parameter for remote PDFs */
+export const UrlSchema = z
+    .string()
+    .url('Must be a valid URL')
+    .describe('URL pointing to a PDF file (HTTP or HTTPS)');
+//# sourceMappingURL=common.js.map

package/dist/schemas/common.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"common.js","sourceRoot":"","sources":["../../src/schemas/common.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AACxB,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AAEjD,8CAA8C;AAC9C,MAAM,CAAC,MAAM,cAAc,GAAG,CAAC;KAC5B,MAAM,EAAE;KACR,GAAG,CAAC,CAAC,EAAE,uBAAuB,CAAC;KAC/B,QAAQ,CAAC,mEAAmE,CAAC,CAAC;AAEjF,oCAAoC;AACpC,MAAM,CAAC,MAAM,WAAW,GAAG,CAAC;KACzB,MAAM,EAAE;KACR,QAAQ,EAAE;KACV,QAAQ,CAAC,8EAA8E,CAAC,CAAC;AAE5F,gCAAgC;AAChC,MAAM,CAAC,MAAM,oBAAoB,GAAG,CAAC;KAClC,UAAU,CAAC,cAAc,CAAC;KAC1B,OAAO,CAAC,cAAc,CAAC,QAAQ,CAAC;KAChC,QAAQ,CAAC,0EAA0E,CAAC,CAAC;AAExF,oCAAoC;AACpC,MAAM,CAAC,MAAM,SAAS,GAAG,CAAC;KACvB,MAAM,EAAE;KACR,GAAG,CAAC,qBAAqB,CAAC;KAC1B,QAAQ,CAAC,4CAA4C,CAAC,CAAC"}