Open-Source
73 posts
The Full McGinnis Stack: An Opinionated Python Developer Setup
How to wire together ContextSwitch, python-skills, makefile-mcp, mutmut-mcp, Rampart, and the rest into a complete AI-powered Python development workflow.
uv Changed How I Think About Python Projects
After years of pip, virtualenv, poetry, and conda, uv has quietly become the only Python packaging tool I recommend. Here's why.
A Full SDLC with MCP Servers
How I use a collection of MCP servers to cover the full software development lifecycle, from task management to testing to deployment.
Rating Systems Compared: Choosing the Right Algorithm
A head-to-head comparison of Elo, Glicko, TrueSkill, DWZ, Colley Matrix and other rating systems. Know when to use each algorithm.
mutmut-mcp: Tests, CI, and Survivor Prioritization
mutmut-mcp gets 23 tests, CI, and a refresher on how to use mutation testing to systematically find gaps in your test suite.
writing-tools-mcp: Still Useful, Now With uvx
A quick update on writing-tools-mcp, the MCP server I use on every blog post for readability, keywords, and AI detection.
todolist-mcp: Dependencies, Kanban, and Where It Fits Now
todolist-mcp now has task dependencies, a kanban web UI, and CI. Plus some thoughts on how it fits alongside ContextSwitch.
Ensemble Rating Systems: Combining the Best of All Worlds
Combine multiple rating algorithms like Elo, Glicko, and TrueSkill to get better predictions. Learn how Elote's ensemble approach works.
Sentinel: Using MCP Sampling to Analyze Your Own Tool Security
Building an MCP server that uses sampling to discover your connected tools and analyze them for security risks, with no API keys required.
The Colley Matrix: A Linear Algebra Approach to Ratings
The Colley Matrix uses linear algebra to solve for optimal ratings simultaneously. Originally designed for college football rankings.