npx @shuji-bonji/pdf-reader-mcp

{
  "mcpServers": {
    "pdf-reader-mcp": {
      "command": "npx",
      "args": ["-y", "@shuji-bonji/pdf-reader-mcp"]
    }
  }
}

claude mcp add pdf-reader-mcp -- npx -y @shuji-bonji/pdf-reader-mcp

git clone https://github.com/shuji-bonji/pdf-reader-mcp.git
cd pdf-reader-mcp
npm install
npm run build

get_page_count({ file_path: "/path/to/document.pdf" })
→ 42

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({ file_path: "/path/to/document.pdf" })
→ | Pages | 42 |
  | PDF Version | 2.0 |
  | Tagged | Yes |
  | Signatures | No |
  | Images | 15 |

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({ 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({
  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 | ✅ |

extract_tables({ file_path: "/path/to/kaisei-tsutatsu.pdf", pages: "1" })
→ # Extracted Tables
  - **Tagged**: Yes / **Pages Scanned**: 1 / **Tables Found**: 1

  ## Page 1 — Table 1

  | 改正後 | 改正前 |
  | --- | --- |
  | …第２条第 16 項《定義》… | …第２条第 15 項《定義》… |

read_text({ file_path: "/path/to/older-shinkyu.pdf", split_columns: 2 })
→ // Plain Y-sort would interleave columns:
//   "改正後セル1   改正前セル1\n 改正後セル2   改正前セル2..."
//
// With split_columns: 2 the left column is emitted first, then the right:
//   "改正後セル1\n改正後セル2\n…\n\n改正前セル1\n改正前セル2\n…"

read_text({ file_path: "/path/to/form.pdf", compact_whitespace: true })
→ // Original PDF uses U+3000 fullwidth space as visual indentation:
//   " (   )   自   年   月   日   法   有 （   年   月   日）   有   有"
//
// With compact_whitespace: true:
//   "( ) 自 年 月 日 法 有 （ 年 月 日） 有 有"
//
// Empirically reduces character count by ~40% on form PDFs.

npm test              # Run all tests (unit: 39 tests)
npm run test:e2e      # E2E tests only (132 tests)
npm run test:watch    # Watch mode

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 (6)
│   │   ├── 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, 132 tests)

{
  "error": "The file does not appear to be a valid PDF.",
  "code": "INVALID_PDF",
  "hint": "ファイルが破損していないか確認してください。",
  "next_actions": [
    {
      "action": "inspect_structure",
      "reason": "PDF が壊れている可能性があります。Catalog / Pages 等の構造を確認してください"
    }
  ],
  "detail": { "cause": "Invalid PDF structure" }
}