Read and manage an Inoreader account: subscriptions, folders and tags, unread counts, stream contents and item ids, read/starred state.
Inoreader ships in the w6w first-party pack. It declares 15 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.inoreaderInoreader is an RSS and news reader. Its developer API (a Google-Reader-compatible surface at www.inoreader.com/reader/api/0) lets a workflow list a user’s subscriptions, folders and tags, read unread counts, pull article streams and item ids, follow or unfollow feeds, and change article state (read, starred, custom tags). Connect a user’s account through OAuth 2.0 with an Inoreader developer application. The API is only available to paid (Pro and above) plans, and is metered in two daily zones: zone 1 for reads and zone 2 for writes.
Three routes to the same 15 actions. The Workflow tab is generated from Inoreader'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.
item-tags-edit Add or remove a tag (read, starred, liked, broadcast or a custom label) on articles.
mark-all-as-read Mark every article in a feed, folder or tag read, up to a timestamp.
stream-contents Fetch the articles of a feed, folder, tag or system stream (up to 100 per call).
stream-preferences-list Folder-level preferences such as subscription ordering and expanded state.
stream-preferences-set Save the manual order of the feeds and folders inside a folder (or the root).
subscription-add Subscribe the user to a feed. Following a feed already followed is not an error.
subscription-edit Rename a feed, move it between folders, follow it, or unfollow it.
subscriptions-list List the feeds the user follows, with their folders. Not paginated.
tags-list List the user's folders, tags and active searches, optionally with unread counts.
unread-counts Unread counters for every feed, folder and tag, plus the overall total.
user-info Basic information about the connected Inoreader user (id, name, email, signup time).
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 Inoreader's real ids.
{
"manifestVersion": "2",
"name": "inoreader-example",
"steps": [
{
"id": "item-ids",
"uses": {
"app": "io.w6w.inoreader",
"action": "item-ids",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"streamId": "<streamId>"
}
}
]
}item-ids item-tags-edit items-mark-read mark-all-as-read stream-contents +10 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 Inoreader, 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 Inoreader. 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: "item-ids",
payload: {
streamId: "<value>",
// count: "<value>",
// order: "<value>",
// newerThan: "<value>",
// excludeRead: "<value>",
// onlyLabel: "<value>",
// continuation: "<value>",
// onlyManualTags: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action item-ids --payload '{"streamId":"<value>"}' Give an AI agent Inoreader — without giving it Inoreader'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.inoreader#item-ids",
"input": {
"streamId": "<streamId>"
}
}
}
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 Inoreader 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.
Inoreader'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. Inoreader itself is MIT, and the runtime that executes it is source-available (FSL).
Inoreader declares its own checks, so its health is a property of the app rather than something the host guesses at.
Unauthenticated GET https://www.inoreader.com/reader/api/0/user-info. A 403 'AppId required' (or a 401 'OAuth token not found') proves the API and its auth layer are answering. Credential validity is the derived `auth:*` check's job.
Zone 1 (read) and zone 2 (write) usage vs limit from the X-Reader-Zone* headers. Polling spends one zone-1 request, so it runs at most every 6 hours.