Read and manage Contentful spaces, content types, entries, assets and locales.
Contentful ships in the w6w first-party pack. It declares 10 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.contentfulContentful reads and writes structured content from a workflow — listing and fetching entries, creating and updating them, and reading the content types that define their shape, so a workflow can adapt to a space’s schema instead of assuming a fixed set of fields.
Assets and locales are available too: assets can be listed and fetched for use alongside the entries that reference them, and locales can be listed to handle a space that publishes in more than one language correctly rather than assuming a single default.
Useful for keeping Contentful in sync with another system — publishing a new entry when content is approved elsewhere, updating one as source data changes, or pulling entries and their assets into another step of a workflow for further processing or distribution.
Three routes to the same 10 actions. The Workflow tab is generated from Contentful'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.
delete-entry Delete an entry via the Management API. The entry must be unpublished first.
list-assets List assets in a space/environment. Walks one page; pass `skip` to paginate.
update-entry Replace an entry's fields via the Management API. Requires the current version for optimistic locking.
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 Contentful's real ids.
{
"manifestVersion": "2",
"name": "contentful-example",
"steps": [
{
"id": "create-entry",
"uses": {
"app": "io.w6w.contentful",
"action": "create-entry",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"contentTypeId": "<contentTypeId>",
"fields": "<fields>"
}
}
]
}create-entry get-asset get-content-type get-entry list-assets +5 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 Contentful, 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 Contentful. 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: "create-entry",
payload: {
contentTypeId: "<value>",
fields: "<value>",
// spaceId: "<value>",
// environmentId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action create-entry --payload '{"contentTypeId":"<value>","fields":"<value>"}' Give an AI agent Contentful — without giving it Contentful'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.contentful#create-entry",
"input": {
"contentTypeId": "<contentTypeId>",
"fields": "<fields>"
}
}
}
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 Contentful 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.
Contentful'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. Contentful itself is MIT, and the runtime that executes it is source-available (FSL).
Contentful declares its own checks, so its health is a property of the app rather than something the host guesses at.
Atlassian Statuspage rollup for www.contentfulstatus.com, with per-component detail. Unauthenticated and unsigned.
Per-second and per-hour allowances remaining, read off the `X-Contentful-RateLimit-*` headers.