Operating

Troubleshooting

The MCP ships with diagnostics. Start with doctor, then drill in.

Health checks

loopover-mcp doctor
loopover-mcp status
loopover-mcp whoami

Or hit the public API endpoint directly to confirm reachability:

GET https://api.loopover.ai/health

http

Self-host Docker observability

The Docker stack exposes three different operator signals: structured logs from the loopover container, Prometheus metrics at /metrics, and optional OpenTelemetry traces through the observability profile. Metrics answer how much work is happening; traces answer where time went inside a review job.

# Enable the collector + Tempo/Grafana stack.
docker compose --profile observability up -d

# Export app queue-job and AI-provider spans to Tempo.
OTEL_TRACES_EXPORTER=otlp
OTEL_TRACES_SAMPLER=parentbased_traceidratio
OTEL_TRACES_SAMPLER_ARG=0.05
OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4318

bash

App traces are off unless OTEL_TRACES_EXPORTER includes otlp. When enabled, the self-host runtime exports durable queue-job spans and AI-provider attempt spans over OTLP/HTTP; the default collector endpoint is normalized to /v1/traces. Span attributes are bounded to operational labels such as job type, queue backend, provider, model, and request kind.

Trace data stays operational

Do not put request bodies, prompts, diffs, credentials, or private config in trace attributes. The built-in self-host spans intentionally avoid those fields.

Common issues

Confirm you can reach github.com/login/device in your browser. Re-run loopover-mcp login and paste the new code.

"Stale fidelity" warning

Upstream Gittensor changed. See Upstream drift for what that means and how to interpret cached analysis until fidelity recovers.

MCP not appearing in my editor

Re-run the appropriate init-client command and restart the editor. See MCP client setup for per-editor config locations.

401 Unauthorized from the API

Your LoopOver session expired. Run loopover-mcp login again. Static bearer tokens are not user-facing.

API status & offline mode

The site continuously monitors the LoopOver API and surfaces problems through a banner under the header and a single deduped toast with a Recheck button.

You're offline

We detected your browser is offline (navigator.onLine === false). Live API actions in the API reference are paused. Reconnect and the site auto-rechecks /health within a few seconds.

API unreachable

/health couldn't be reached at all. This usually means a network problem between you and the API edge. Try the Recheck button in the banner, or run curl https://api.loopover.ai/health from your machine to confirm.

API timing out

/health didn't respond within the 4-second probe window. The API may be slow or restarting. Retry — most timeouts resolve within a minute.

API degraded

/health returned a non-2xx response. Some endpoints may still work; check the Roadmap for incident notes or wait for the recheck cycle to clear.

← PreviousPrivacy & security