Read, create, update and delete entries on any Strapi content type, and browse the media library.
Strapi ships in the w6w first-party pack. It declares 6 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.strapiStrapi reads, creates, updates and deletes entries on any Strapi content type and browses the media library, working against any self-hosted or cloud Strapi instance rather than one fixed host. Because every Strapi install lives at its own address, the instance’s own URL is set once when the connection is created, and every action builds its request from that.
The app is entirely collection-agnostic: every entry action names the content type to work against, so one connection reaches every collection a given Strapi project defines rather than a fixed handful. Entries can be listed with filters, sorting and pagination, read individually, created, updated and deleted, and Strapi’s own entry-id conventions are passed through unchanged whether the instance uses the older numeric ids or the newer document-id form.
Authentication uses Strapi’s own long-lived API tokens — scoped to read-only, full access, or custom permissions — rather than the separate end-user login flow, since a workflow credential should belong to the integration, not to a human account. Content-type schema editing is left entirely to Strapi’s own admin panel; this app works only with the data those content types hold.
Three routes to the same 6 actions. The Workflow tab is generated from Strapi'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.
entry-list List entries of a content type, with Strapi's filter/sort/pagination syntax.
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 Strapi's real ids.
{
"manifestVersion": "2",
"name": "strapi-example",
"steps": [
{
"id": "entry-create",
"uses": {
"app": "io.w6w.strapi",
"action": "entry-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"collection": "<collection>",
"data": "<data>"
}
}
]
}entry-create entry-get entry-list entry-update media-list +1 more action 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 Strapi, 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 Strapi. 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: "entry-create",
payload: {
collection: "<value>",
data: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action entry-create --payload '{"collection":"<value>","data":"<value>"}' Give an AI agent Strapi — without giving it Strapi'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.strapi#entry-create",
"input": {
"collection": "<collection>",
"data": "<data>"
}
}
}
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 Strapi 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.
Strapi'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. Strapi itself is MIT, and the runtime that executes it is source-available (FSL).
Strapi declares its own checks, so its health is a property of the app rather than something the host guesses at.
Unauthenticated `GET /_health` against this connection's endpoint — Strapi's own built-in liveness route, present on every instance.