/status

description: Check MCP access and native Claude telemetry configuration without changing them

Logfire connection status

Check the two connections separately. This command is for Claude Code.

1. Inspect the plugin's resolved MCP endpoint and authentication status. A small authenticated read may verify access; report network/authentication failure without changing the server or opening a new login flow. MCP configuration commands may exit zero even when connection failed; inspect their reported status, not just the process exit code. 2. Run `python3 "${CLAUDE_PLUGIN_ROOT}/scripts/agent_runtime.py"` without `--install`. This must not install dependencies during a status check. 3. If ready, use its returned executable to run `--beta --no-input --output json agent claude --data-dir <data_dir> status`. Never open/print SDK credential files or read OAuth secrets. If the runtime or project credentials are missing, report telemetry status as unknown, not disabled: settings installed through another workflow may still be active. 4. Report ingestion only if a bounded MCP query in the confirmed telemetry destination finds matching recent Claude events. Otherwise say not verified.

Keep the result to three short rows: MCP access, session capture (including destination/mode), and delivery evidence (or "Not verified"). Include one next action only when needed. `needs_update` is not healthy delivery. Offer `/logfire:connect` for repairs; do not repair or reinstall automatically.