a lot of folks are assuming the primary users of mcp are the end users connecting their claude/vscode/etc to whatever saas platform they’re working on. While this is a huge benefit and super cool to use, imo the main benefit is for things like giving complex tool access to centralized agents. Where the mcp servers allow you to build agents that have the tools to do a sort of “custom deep research.” - HN

MCP brings nothing to the table that I could not do with a “proper” API using completely standard tooling.

• 7 erreurs fatales avec MCP qui tuent les projets d’IA - MCP will throttle production traffic (in case its overload)
  • MCP is not a data retrieval mechanism (no SQL)
  • security theater - need to think about security first
  • magical performance - external information introduce noise to internal workflowss and can degrade overall performance
  • MCP per microservice - latency / security / audit
• MCP excels at:
  • for internal analysis
  • bridging complex workflow accross system
  • summarizing things

see also

• MCP overlooks hard-won lessons from distributed systems / HN