Read Base44 workspace analytics, users, apps, and Superagents, and stream Enterprise audit log events and app security-scan findings.
Base44 ships in the w6w first-party pack. It declares 11 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.base44Base44 is a platform for building and running AI-powered apps, and this app reads the operational side of a Base44 workspace: usage analytics, member and app inventories, and — on the Enterprise plan — a stream of audit log events and security-scan findings.
Pull workspace-wide KPIs and credit consumption, drill into a specific app’s or Superagent’s usage, and see who owns what across the workspace. The audit log actions surface authentication, entity, app-lifecycle and workspace-admin events, filterable by type, app, user or date, and security-scan findings come back alongside their own coverage status so a clean result can be told apart from a scan that never ran.
Everything here is a read: this app is built for visibility into a workspace’s health, usage and security posture rather than for managing the apps or Superagents themselves, and the audit log and security-scan actions specifically require an Enterprise-plan workspace.
Three routes to the same 11 actions. The Workflow tab is generated from Base44'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.
get-analytics Workspace-level KPIs, user/app distribution, the shared credit pool, member credit-limit aggregates, and credits consumed.
get-app-analytics Engagement, deployment, and governance metrics for one app. `avgSessionDurationSec` is always 0 — the vendor documents session tracking as not yet implemented for that field.
get-security-scan-findings Findings and per-section coverage for one security scan run. Get `runId` from an `app.security.check_run` audit event. An empty findings array only means "clean" for a section whose coverage is `completed`.
get-superagent-analytics Active-user and credit-usage metrics for one Superagent, over a required date range.
list-apps Workspace-wide app inventory with owner, visibility, publish state, and credit usage.
list-audit-logs Paginated workspace audit log events — auth, entity CRUD, app lifecycle, workspace admin, and security-scan events. Requires a workspace key scoped to `audit_logs:read`.
list-superagents Workspace-wide Superagent inventory with owner, activity, and credit usage.
list-user-apps App IDs created by one workspace member. Feed each into `get-app-analytics`.
list-user-superagents Superagent IDs owned by one workspace member. Feed each into `get-superagent-analytics`.
list-users Every workspace member, with profile data and credit consumption for a date range.
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 Base44's real ids.
{
"manifestVersion": "2",
"name": "base44-example",
"steps": [
{
"id": "get-app-analytics",
"uses": {
"app": "io.w6w.base44",
"action": "get-app-analytics",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"appId": "<appId>",
"from": "<from>",
"to": "<to>"
}
}
]
}get-app-analytics get-analytics get-security-scan-findings get-superagent-analytics get-user +6 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 Base44, 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 Base44. 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: "get-app-analytics",
payload: {
appId: "<value>",
from: "<value>",
to: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action get-app-analytics --payload '{"appId":"<value>","from":"<value>","to":"<value>"}' Give an AI agent Base44 — without giving it Base44'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.base44#get-app-analytics",
"input": {
"appId": "<appId>",
"from": "<from>",
"to": "<to>"
}
}
}
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 Base44 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.
Base44'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. Base44 itself is MIT, and the runtime that executes it is source-available (FSL).
Base44 declares its own checks, so its health is a property of the app rather than something the host guesses at.
No usable machine-readable status surface: base44.statuspage.io is an unclaimed Statuspage decoy, and status.base44.com is Cloudflare-gated behind a bot challenge.
Probes the unauthenticated `GET /health` on the Monitoring API this app calls.