Building with MCP servers is both fun and a bit chaotic. The official MCP spec keeps evolving, but agents aren't always quick to catch up, and it isn't always obvious where the gaps are. This talk is part commiseration, and part survival guide. I'll share what we've learned the hard way: from designing tools agents actually use, to experimenting when client support falls short. In a space moving this quickly, hacking and experimenting are our new \"first principles.\"
talk-data.com
M
Speaker
Macey Baker
1
talks
Community Engineer
Tessl
As Tessl's Founding Community Engineer, Macey Baker is helping to shape the future of AI-native development (and helping you build it too). Now an AI code generation obsessive, she got her start as an early employee at unicorn Intercom in San Francisco before crossing the Atlantic and roaming the London startup scene, focusing on big data and ML houses. Some of her best friends are LLMs.
Bio from: Agentic AI and Model Context Protocol (MCP)
Filter by Event / Source
Talks & appearances
1 activities · Newest first