Tool Invocation at Scale: The Server Manager

~12 min read

The Server Manager keeps an agent's active toolset intentionally narrow and context-driven — loading tools dynamically, only when needed, instead of exposing everything from every server at once.

Tool Invocation at Scale: The Server Manager is a Pro topic

Sign in, then upgrade to Pro or Power to unlock this topic and the full AI Engineering curriculum.

Key points

  • The Server Manager keeps the agent's active toolset intentionally narrow and context-driven, rather than exposing every tool at once
  • It loads tools dynamically only when needed, and discovers which server is appropriate for the current task
  • It provides semantic search over all available tools across servers, even ones not currently loaded into context
  • Enabling it is as simple as setting use_server_manager=True on the agent
  • It becomes the orchestrator deciding which server to activate and which tools to surface, directly addressing tool overload at its source