alt Hacker NewsWhy don't you just have the agent write scripts against the APIs? The skills-based workflow doesn't confine you to bash only.
Why don't you just have the agent write scripts against the APIs? The skills-based workflow doesn't confine you to bash only.
If you do that, you end up with all the problems that MCP attempts to solve: how to authorize using a standard mechanism, how to summarize operations in a better way than just dumping the OpenAPI spec on the LLM, providing structured input/output, providing answers to users that the LLM cannot see (for sensitive data or just avoiding polluting the context) and so on.
Authorization, in my opinion, is the big problem you need MCP for, though the current MCP Authorization spec still needs some refinement.