- Remove incorrect Docker-based configuration methods from README.md
- Clarify in DOCKER.md that Docker cannot be used for Claude Desktop integration
- Add proper local Python execution examples for Claude Desktop
- Explain MCP stdio protocol limitations with Docker containers
- Add Windows-specific configuration example
- Add Docker-specific Claude Desktop configuration examples
- Document both docker exec and docker run methods
- Explain stdio communication requirements for MCP protocol
- Include prerequisites and important notes for Docker usage
- Update both README.md and DOCKER.md with consistent information
The documentation now properly explains how to connect Claude Desktop
to the MCP servers running in Docker containers, addressing the
special requirements of stdio-based communication.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update docker-compose.yml to use pre-built images from GitLab registry
- Replace individual environment variables with unified env_file directive
- Create comprehensive .env.example with detailed instructions and troubleshooting
- Add push-to-registry.sh script for building and pushing images to registry
- Add docker-compose.prod.yml as reference for production deployments
- Update documentation to reflect simplified deployment process
Users can now deploy with just:
cp .env.example .env
docker-compose pull
docker-compose up -d
All 7 MCP server images are available at:
git.oe74.net/adelorenzo/portainer-mcp/portainer-*:latest
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create individual Dockerfiles for each of the 7 MCP servers
- Add docker-compose.yml for orchestrating all services
- Create build-docker.sh script for easy container building
- Add comprehensive Docker deployment documentation (DOCKER.md)
- Update main README with Docker installation instructions
- Add .env.example template for environment configuration
- Configure each server with dedicated ports (3000-3006)
- Implement security best practices (non-root user, minimal base image)
- Add production deployment considerations and troubleshooting guide
Each server can now be run individually or all together using Docker Compose,
making deployment and scaling much easier for production environments.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add documentation links in main README overview section
- Create new Documentation section listing all README files
- Ensure all README files are properly referenced
- All server documentation is now easily discoverable
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace outdated single-server documentation with comprehensive suite overview
- Document all 7 specialized MCP servers with their capabilities
- Add proper installation and configuration instructions for the suite
- Include usage examples for each server type
- Update Claude Desktop configuration examples
- Add security considerations and troubleshooting guide
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major configuration and tooling updates:
Authentication Changes:
- Remove username/password authentication support
- Require PORTAINER_URL and PORTAINER_API_KEY (both mandatory)
- Simplify PortainerConfig class and validation logic
- Update all documentation to reflect API key requirement
Multiple Runtime Support:
- Add uvx support for running without installation
- Add uv support with dedicated wrapper script
- Add npx support with Node.js wrapper script
- Maintain backward compatibility with direct Python execution
Documentation Updates:
- Comprehensive README.md with all execution methods
- Detailed USAGE.md with step-by-step instructions
- Updated .env.example with clear required vs optional sections
- Enhanced docstrings in server.py and config.py
Tooling Support:
- package.json for npm/npx support with cross-platform wrapper
- scripts/run-with-uv.py for uv integration
- bin/portainer-core-mcp Node.js wrapper for npx
- test_uvx.py for uvx functionality testing
Configuration Improvements:
- Clear separation of required vs optional environment variables
- Better validation error messages
- Simplified authentication flow
- Enhanced project metadata in pyproject.toml
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>