Feedly
Read team AI Feeds, folders and boards, search across them, and manage Feedly's enterprise webhooks.
About
Feedly ships in the w6w first-party pack. It declares 14 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.feedly- Version
- 0.1.0
- Author
- w6w
- Licence
- MIT
- Categories
- Productivity · Security & Identity
Overview
Feedly’s current public API is entirely the Feedly for Threat Intelligence (Enterprise) surface — every endpoint in this app lives under that product, and a self-service API token is only issued to Enterprise accounts (an admin generates it from https://feedly.com/i/team/api). There is no OAuth2 dance to build against: once an Enterprise team has a token, every call is a plain Authorization: Bearer header against api.feedly.com, so this app is a straightforward bearer-token integration — the gate is commercial (who can get a token), not technical (what the token can do).
Within that surface, this app covers the general content-reading and team-collaboration actions rather than the security-analyst-specific ones (CVE/threat-actor/malware insight cards, the Vulnerability/Cyberattacks/TTP Agents, entity lookups, Ask AI): collecting and searching articles across a team’s AI Feeds, folders and boards, reading one or many articles’ full enriched metadata, adding annotations, managing team boards and webhooks, and listing an enterprise account’s folders, AI Feeds and users.
Build with Feedly
Three routes to the same 14 actions. The Workflow tab is generated from Feedly'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.
List AI Feeds
ai-feeds-list List the enterprise team's AI Feeds (Feedly's internal API name: "alerts").
Get Article
article-get Fetch one article's full enriched metadata (entities, summary, sources, …) by id.
Collect Articles
articles-collect Page through the articles in a team AI Feed, folder or board (a "stream").
Get Multiple Articles
articles-get-multiple Batch-fetch full metadata for up to 1,000 articles by id in one call.
Search Articles
articles-search Search for articles across your team's sources using Feedly AI's query language.
List Enterprise Users
enterprise-users-list List every user in the enterprise account with their role and activity metrics. Requires the connected token to belong to a team admin.
Create or Update Webhook
webhook-upsert Create a new webhook, or update an existing one when an id is given. Feedly sends a test event to the URL immediately.
List Webhooks
webhooks-list List configured webhooks (NewEntrySaved, NewAnnotation, NewEntryPrioritized).
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 Feedly's real ids.
{
"manifestVersion": "2",
"name": "feedly-example",
"steps": [
{
"id": "article-annotate",
"uses": {
"app": "io.w6w.feedly",
"action": "article-annotate",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"entryId": "<entryId>",
"comment": "<comment>"
}
}
]
}Here are some of the things you can do
-
Annotate Article
performarticle-annotate -
List AI Feeds
readai-feeds-list -
Get Article
readarticle-get -
Collect Articles
readarticles-collect -
Get Multiple Articles
readarticles-get-multiple
+9 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 Feedly, 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 Feedly. 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: "article-annotate",
payload: {
entryId: "<value>",
comment: "<value>",
// highlightStart: "<value>",
// highlightEnd: "<value>",
// highlightText: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action article-annotate --payload '{"entryId":"<value>","comment":"<value>"}'Give an AI agent Feedly — without giving it Feedly'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.feedly#article-annotate",
"input": {
"entryId": "<entryId>",
"comment": "<comment>"
}
}
}
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 Feedly connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
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.
A tool surface scoped to the caller
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.
A durable workflow in one call
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.
Health-aware discovery
Feedly'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. Feedly itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Feedly declares its own checks, so its health is a property of the app rather than something the host guesses at.
Feedly platform status
Resource status from status.feedly.com (Better Stack). The page's single monitored resource explicitly covers "the API" alongside the web and mobile apps.
Monthly request headroom
Calls made this cycle vs. the token's monthly cap, read from the X-RateLimit-* headers Feedly attaches to every response.