What the MCP protocol actually standardises
It settles how capabilities are described and discovered. Every decision about whether to trust them is still yours.
Series
5 Days of MCP for Production AI
What the Model Context Protocol actually standardises, and what it leaves to you. Hosts, clients and servers, the three primitives, transport as an ownership decision, and when a direct API is the better call.
Posts in this series
Where your MCP server runs is a production decision
Transport looks like a technical detail during the demo. It is really a choice about ownership, reachability and trust.
Tools, resources and prompts are not interchangeable
Choosing the wrong primitive hands the model authority a person was supposed to hold.
A clean connector does not make a reliable agent
Connector correctness and agent behaviour are separate problems. Most teams only test the first one.
When MCP earns its overhead, and when a direct API is better
One question settles most of these arguments: will more than one AI application need this capability?
