For background, MCP is a protocol that standardizes how you connect tools to AI assistants. We're both engineers at large software companies, and when we worked on MCP integrations we saw how long setup took and how often the spec was changing. So we built a platform to handle the MCP infrastructure, letting you keep doing normal API work and expose it to AI when you're ready.
Right now we're creating a 1:1 mapping from APIs to MCP tools, but we're working on improving tool discovery so the AI doesn't get overwhelmed by 100 endpoints at the start of every conversation.
Still early. Would love feedback!
What is a viable path in very late 2025 for a hobbyist to get started?
The Sky Is Getting Brighter Despite lower power use, satellite data shows global skyglow is increasing by ~2% yearly (Science Advances, 2016). Why?
White LEDs (often 4000K–5000K) emit intense blue light, which scatters 3× more in the atmosphere than HPS’s amber glow. Poorly shielded fixtures leak upward—even “retrofit” kits in old housings often lack proper optics. Cheaper operating costs encourage over-lighting (Jevons paradox). Real Ecological Harm Peer-reviewed studies confirm:
Insects swarm blue-rich LEDs → local population collapse (Biol. Lett., 2018). Migratory birds collide with buildings due to disorientation from skyglow. Bats, frogs, and other nocturnal species show disrupted foraging and reproduction. The AMA even warned in 2016 that high-CCT streetlights suppress melatonin and increase glare—reducing nighttime safety.
A Better Path This isn’t anti-LED—it’s pro-systems thinking. Solutions exist:
Use ≤2700K LEDs (less blue, better visual comfort)
Mandate full-cutoff fixtures (zero uplight)
Dim lights after midnight via motion or scheduling
Cities like Tucson and Davis prove you can cut energy and protect the night.