Manage dashboards, data sources, annotations, and alert rules on any Grafana instance.
Grafana ships in the w6w first-party pack. It declares 8 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.grafanaGrafana puts a monitoring stack under workflow control — reading and creating dashboards, inspecting configured data sources, dropping an annotation onto a specific panel or the whole board, and auditing what alert rules are currently armed — against a self-hosted, on-prem or Grafana Cloud instance alike, since a team’s own stack can live at any hostname.
Alert rule actions read what is currently configured to fire and under what conditions, useful for auditing an instance’s alerting setup or feeding it into a broader monitoring workflow. Because every Grafana instance’s API looks the same regardless of where it is hosted, the app targets whatever base URL a team’s own instance lives at, so one app definition works against any deployment a team happens to run.
Three routes to the same 8 actions. The Workflow tab is generated from Grafana's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
annotation-create Add an annotation, optionally scoped to a dashboard/panel or spanning a time range.
dashboard-create-update Create a new dashboard, or overwrite an existing one by UID.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Grafana's real ids.
{
"manifestVersion": "2",
"name": "grafana-example",
"steps": [
{
"id": "alert-rule-get",
"uses": {
"app": "io.w6w.grafana",
"action": "alert-rule-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"uid": "<uid>"
}
}
]
}alert-rule-get alert-rule-list annotation-create dashboard-create-update dashboard-get +3 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Grafana, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Grafana. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "dashboard-create-update",
payload: {
dashboard: "<value>",
// folderUid: "<value>",
// overwrite: "<value>",
// message: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action dashboard-create-update --payload '{"dashboard":"<value>"}' Give an AI agent Grafana — without giving it Grafana's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.grafana#alert-rule-get",
"input": {
"uid": "<uid>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Grafana connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Grafana's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Grafana itself is MIT, and the runtime that executes it is source-available (FSL).
Grafana declares its own checks, so its health is a property of the app rather than something the host guesses at.
Unauthenticated `GET /api/health` against this connection's endpoint — Grafana's own liveness probe, which needs no credential.