Read Grafana health, rings, and dashboard data, then push log records with approval
Connect Grafana and your agent can check server health, inspect Loki and Mimir ring status, read license state, and query panels on public dashboards for real numbers during an incident. When it needs to write, such as sending OTLP log records into Loki, it shows the payload first and waits for your approval. Luumen authenticates with a bearer token.
11 tools: 9 read, 2 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Grafana run looks like inside Luumen.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create otlp v1 logs, post acs — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Grafana — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.