I’ve been working on a small open-source repo for AI-agent workflows around the MEXC API. The...
Building safer AI-agent workflows for the MEXC API
Related
MCP Scorecard: 4-Layer Pre-flight Check Before You Publish a Server
Every tool description in a registered MCP server is sent to the LLM on every turn. I published mcp-scorecard on PyPI to grade that surface across four layers: passive token footpr...
Mozilla adopted my Firefox DevTools MCP, but I didn't build it to browse the web
A little while ago I wrote an MCP server that lets an AI agent inspect and control Firefox through...
Why your agent keeps repeating facts you already corrected
Every agent I build eventually does the same thing. It repeats a fact I already corrected, stated...