MCP/connectors are not the product. The approval UX is the product.
Summary
A statement arguing that the approval user experience, not the MCP or connectors themselves, constitutes the real product.
Similar Articles
MCP is the new 'build it and they will come'
An opinion piece arguing that MCP servers often fail because teams build them without confirming real user demand, and recommends validating with actual struggling users and early usage instrumentation before committing.
What is a product?
An essay arguing that AI-generated prototypes are not real products; a real product requires real users, a real market, and solves real problems. It critiques the hype around AI demos and reminds builders that without users, what they've built is just a toy.
Where should approval for MCP write tools be enforced?
The article discusses where to enforce approval for write actions in MCP tools, considering client-side and server-side approaches, and what to log for checking against approved actions.
@svpino: MCP is not dead. For the people who keep saying "bUt McP pUts GaRbaGe iN yOuR cOntExT", that's an outdated complaint: N…
A defense of MCP (Model Context Protocol) against criticism that it puts garbage in context, noting that modern tools like Claude Code, Codex, and Cursor implement progressive disclosure and load MCP tools on demand, making the complaint outdated. The author argues MCP is best for cloud-hosted platforms requiring authentication and discoverability.
Why MCP Was Always a Bad Idea?
The article argues that MCP, originally useful for connecting LLMs to external services, has become outdated due to advancements in LLMs that can now handle API calls directly, rendering many MCP servers unnecessary.