Releases: alaturqua/mcp-trino-python
Releases · alaturqua/mcp-trino-python
v0.7.1 - SDK Alignment
What's New
Improvements
- SDK Best Practices: Aligned with MCP Python SDK recommendations
- FastMCP Configuration: Now uses host, port, stateless_http=True, json_response=True in initialization
- Environment Variables: Added MCP_HOST/MCP_PORT support for containerized deployments
Changes
- server.py: Settings-based configuration via environment variables with defaults (127.0.0.1:8000)
- Dockerfile: Added MCP_HOST=0.0.0.0 and MCP_PORT=8000 defaults
- docker-compose.yml: Simplified to use environment variables instead of CLI arguments
Technical Details
- stateless_http=True for better HTTP transport behavior
- json_response=True for consistent response formatting
- Transport handling uses mcp.settings for dynamic configuration
v0.7.0 - Multi-transport Support
What's New
Features
- Multi-transport support: stdio, streamable-http, and sse transports
- Updated Dockerfile optimized for all transport modes
- Docker Compose with dedicated services for each transport
- Improved CLI with better help text and examples
Documentation
- Added Quick Start guide
- Updated VS Code and Claude Desktop configuration examples
- Added Docker usage examples for all transports
Breaking Changes
- Python 3.12+ now required (previously 3.11+)
v0.6.0
What's Changed
- feat: add Docker support and implement SSE in MCP server by @alaturqua in #6
Full Changelog: v0.5.0...v0.6.0
v0.5.0
v0.4.0
Changelog
All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog
and this project adheres to Semantic Versioning.
[v0.4.0] - 2025-04-19
Added
- Initial release of MCP Trino Python connector
- Core functionality for Model Context Protocol integration with Trino
- Python 3.12+ compatibility
- Trino connector implementation
- Basic logging setup with loguru
- CLI support through MCP integration
- Environment configuration support with python-dotenv
Changed
- N/A (Initial Release)
Known Issues
- None