- Optionally restrict which MCP servers and tools this agent can use. Leave empty to allow all (subject to key/team permissions). + Configure which models, agents, and MCP tools this agent is allowed to use. Leave fields empty to allow all (subject to key/team permissions).
+ +- Only accept this agent being invoked with a trace-id (e.g. when used as a sub-agent). -
-- Requires LLM/MCP calls made by this agent to include x-litellm-trace-id for session tracking. -
-Hard cap on LLM calls per session
-Max spend per trace before returning 429
-- Global rate limits applied across all callers of this agent. + const renderObservabilityStep = () => ( +
+ Only accept this agent being invoked with a trace-id (e.g. when used as a sub-agent).
-- Rate limits per session (x-litellm-trace-id). Each session gets its own counters. -
-+ Requires LLM/MCP calls made by this agent to include x-litellm-trace-id for session tracking. +
+Hard cap on LLM calls per session
+Max spend per trace before returning 429
++ Global rate limits applied across all callers of this agent. +
++ Rate limits per session (x-litellm-trace-id). Each session gets its own counters. +
++ Apply guardrails to this agent. Selected guardrails will run on all calls made by this agent. +
+