v2.5.1: Modular Architecture + Connection Pooling
🚀 Highlights
- Modular Restructure: github_mcp.py reduced from 10,857 to ~50 lines (99.5% reduction)
- Connection Pooling: 97% latency reduction (4000ms → 108ms for subsequent calls)
- 109 Tools across 21 categories
- 297 Tests, 15/15 live integration tests passing
🏗️ Architecture
- Tools organized in src/github_mcp/tools/ (21 modules)
- Models in src/github_mcp/models/
- Utilities in src/github_mcp/utils/
- Clean imports (no backward compatibility hacks)
🔧 Fixes
- Multiline code execution (was truncating at first line)
- Dict to Pydantic model conversion in callMCPTool (now works with plain objects)
- list_branches no longer requires auth for public repos
- .env loading in test scripts
⚡ Performance
| Metric | Before | After | Improvement |
|---|---|---|---|
| Execution latency | ~4000ms | ~108ms | 97% faster |
| Token usage | ~70,000 | ~800 | 98% reduction |
| github_mcp.py | 10,857 lines | ~50 lines | 99.5% smaller |
📦 What's Included
- 21 tool modules (105 GitHub tools + 3 workspace tools + execute_code)
- Connection pooling with health checks and idle cleanup
- JSON protocol for multiline code support
- Comprehensive architecture documentation
- Updated CLAUDE.md for AI assistants
🙏 Dogfooding
This release was developed using the GitHub MCP Server itself - creating issues, managing branches, and even creating this release via execute_code!