Admin Dashboard: Resilience
Resilience shows one circuit breaker per MCP server. Breakers stop repeated calls to a failing dependency from degrading every agent turn.
Read the states
Section titled “Read the states”- Closed: calls flow normally.
- Open: consecutive failures crossed the threshold, so calls fail fast.
- Half-open: the cooldown elapsed and a probe is testing recovery.
The page polls every five seconds and shows failure count and the most recent failure time.
Reset a recovered server
Section titled “Reset a recovered server”- Fix or verify the upstream MCP server first.
- Open Resilience and locate its breaker.
- Choose Reset only for an open or half-open breaker.
- Confirm the state returns to Closed, then run a representative agent tool call.
The expected result is a closed breaker and a successful tool call. Resetting does not repair authentication, transport, catalog, or upstream failures.
Troubleshooting
Section titled “Troubleshooting”Use MCP Servers to refresh tools/list and inspect connection status. Use Tool Call Log for arguments, timing, and result status. When a live SSE transport disconnects, pending requests fail immediately with a safe error and the transport reconnects. If a server sends an SSE event larger than 1 MiB, reduce or split its response so each event stays within the supported size.