Release: v0.5.6

What's Changed

Dependencies

• Bump @modelcontextprotocol/sdk from 1.25.2 to 1.26.0
  • Security fix for cross-client response data leak (GHSA-345p-7cg4-v4c7)
• Bump hono from 4.11.4 to 4.11.7
• Bump lodash from 4.17.21 to 4.17.23

Full Changelog: v0.5.5...v0.5.6

Release: v0.5.5

Security

• Updated hono from 4.11.3 to 4.11.4 to fix JWT algorithm confusion vulnerability
  • See: GHSA-f67f-6cw9-8mq4
  • See: GHSA-3vhc-576x-3qv4

Release: v0.5.4

Security

• Update @modelcontextprotocol/sdk to 1.25.2 to fix ReDoS vulnerability in UriTemplate regex patterns

Release: v0.5.3

Dependencies

Bump qs from 6.14.0 to 6.14.1 (#35)

Updated qs package (indirect dependency via express) to fix minor bugs:

• Ensure arrayLength applies to [] notation as well
• Fix parse to ignore key when custom decoder returns null

CI Improvements

Add production dependency validation (#36)

Added report-missing-dependencies to CI pipeline to automatically detect when devDependencies are incorrectly used in production code. This prevents MODULE_NOT_FOUND errors when installing via npx.

Full Changelog

v0.5.2...v0.5.3

Release v0.5.2

Dependencies

• Bump jws from 4.0.0 to 4.0.1 (security fix for GHSA-869p-cjfg-cm3x)
• Bump @modelcontextprotocol/sdk from 1.22.0 to 1.24.0

Release v0.5.1

What's Changed

Dependencies

• Bump express from 5.1.0 to 5.2.1 (#28)

Full Changelog: v0.5.0...v0.5.1

Release v0.5.0

New Features

• Purpose parameter: New purpose parameter allows specifying intended use (e.g., "cookbook cover", "social media post") to tailor visual style and details
• Improved prompt generation: Restructured to follow Google's Subject-Context-Style format for better image quality

Documentation

• Added purpose parameter to API Reference

Release v0.4.2

Security

• Update body-parser from 2.2.0 to 2.2.1 to address CVE-2025-13466 (GHSA-wqch-xfxh-vrr4)

Dependencies

• body-parser: 2.2.0 -> 2.2.1

Release v0.4.1

✨ New Feature

Google Search Grounding Integration

• Added useGoogleSearch parameter to enable real-time web information access during image generation
• Allows the model to ground image generation with current, factual data from the web
• Ideal for prompts requiring time-sensitive or up-to-date information (e.g., current events, recent fashion trends, latest technology)
• Automatically disabled for creative, fictional, historical, or timeless content to preserve artistic freedom

🔧 Technical Details

• New useGoogleSearch boolean parameter in generate_image tool
• Implements Google Search grounding via Gemini API tools parameter
• Comprehensive test coverage with 233 lines of new tests
• Updated documentation with usage guidelines

---

Full Changelog: v0.4.0...v0.4.1

Release v0.4.0

Update

⚡ Gemini API Update

• Updated @google/genai from 1.22.0 to 1.30.0
• Enhanced compatibility with latest Google AI features

🍌 Nano Banana Pro Integration

• Upgraded to Gemini 3 Pro Image (gemini-3-pro-image-preview)
• Added 4K image generation support
• Improved image quality and performance

🔧 Infrastructure Improvements

• Migrated server.json to 2025-10-17 schema format
• Updated dependency ecosystem for better stability
• Enhanced authentication library support

📦 Dependency Updates

• @google/genai: 1.22.0 → 1.30.0
• @modelcontextprotocol/sdk: 1.17.4 → 1.22.0
• google-auth-library: 9.x → 10.x
• ajv: 6.x → 8.x (with ajv-formats support)
• gaxios: 6.x → 7.x
• node-fetch: 2.x → 3.x

🚀 What's New

✨ Better image generation quality with Gemini 3 Pro Image
📐 4K resolution support for high-quality outputs
🔒 Enhanced security with updated auth libraries
⚙️ Improved MCP protocol compatibility