v2.1.0

2.1.0 (2025-12-17)

v2.0.8

2.0.8 (2025-12-05)

v2.0.7

2.0.7 (2025-12-03)

v2.0.3

2.0.3 (2025-11-30)

v2.0.2

2.0.2 (2025-11-27)

v2.0.1

2.0.1 (2025-11-27)

v2.0.0

2.0.0 (2025-11-27)

v1.4.0

✨ Features

• migrate documentation from VitePress to Leaf (dd1d9ee)

🐛 Bug Fixes

• ci: use explicit path for lefthook in prepare script (40c3655)
• security: override js-yaml to fix vulnerability (ce7acc8)
• ci: allow bun install without frozen-lockfile for Dependabot PRs (af10706)
• upgrade to SDK 1.0.0 and Zod 4 for proper JSON Schema support (e9e21d5)
• improve image extraction timeout handling (c9e6f55)
• critical security and performance improvements (19c7451)

♻️ Refactoring

• migrate from @modelcontextprotocol/sdk to @sylphx/mcp-server-sdk (98efbbb)
• add structured logging system (a337d93)
• deduplicate image extraction logic (2e6ef33)
• implement proper PDF document resource cleanup (7893cf6)

📚 Documentation

• add installation guides for VS Code, Claude Code, Cursor, Windsurf, Cline, Warp (28a3bf1)

🔧 Chores

• upgrade @sylphx/bump to v0.12.1 (9c597fb)
• upgrade @sylphx/doctor to v1.23.3 and @sylphx/bump to v0.10.2 (ff6849e)
• upgrade @sylphx/doctor to v1.23.2 (9ab92cf)
• migrate tooling to @sylphx ecosystem (fc2471f)
• upgrade all packages to latest versions (8b6730b)
• cleanup unused files and folders (8834d09)
• migrate from Vitest to Bun test runner (7382d1b)
• adjust coverage thresholds after adding defensive code (3780190)

v1.3.2

Patch Changes

• c97a5c0: Refactor CI workflows to use company release standard. Simplified CI workflow for validation only and enhanced release workflow with full configuration.

v1.2.0 - Content Ordering Based on Y-Coordinates

Features

Content Ordering: Preserve exact text and image order based on Y-coordinates

• Content items within each page are now sorted by their vertical position
• Enables AI to see content in the same order as it appears in the PDF
• Text and images are interleaved based on document layout
• Example: page 1 [text, image, text, image, image, text]
• Uses PDF.js transform matrices to extract Y-coordinates
• Automatically groups text items on the same line
• Returns ordered content parts for optimal AI consumption

Internal Changes

• New extractPageContent() function combines text and image extraction with positioning
• New PageContentItem interface tracks content type, position, and data
• Handler updated to generate content parts in document-reading order
• Improved error handling to return descriptive error messages as text content

Code Quality

• All tests passing (91 tests)
• Coverage maintained at 97.76% statements, 90.95% branches
• TypeScript strict mode compliance
• Zero linting errors

Install

npm install -g @sylphx/pdf-reader-mcp
# or
pnpm add -g @sylphx/pdf-reader-mcp