blog

Technical posts from the everyrow team.

February 25, 2026·Rafael Poyiadzi

How to get large files to your MCP server without blowing up the context window

Inlining data in MCP tool calls eats the LLM's context window. We show how to use presigned URLs so Claude can upload files directly to your server, keeping the context clean with a 36-character artifact ID.

February 24, 2026·Robert Gambee

The Hidden Incompatibilities Between LLM Providers

LLM APIs look interchangeable on paper. In practice, they diverge in subtle ways that break your code. We document the provider-specific quirks we've hit while running thousands of LLM calls per day across Anthropic, Google, and OpenAI.