Create, list, and export Readwise highlights and books, manage tags, and read the daily review.
Readwise ships in the w6w first-party pack. It declares 20 actions, 1 health check, and the host runs its code in a sandbox that never sees the credential.
io.w6w.readwiseReadwise aggregates highlights and notes from Kindle, Instapaper, Pocket, Twitter, Apple Books and dozens of other reading apps into one account, then resurfaces them for spaced-repetition review.
This app covers Readwise’s classic Highlights API (api/v2), not the separate Reader product: creating highlights from your own application (with automatic de-duplication and update-by-highlight_url), exporting a user’s full highlight history for backup or sync, and the fuller CRUD surface for reading, updating and deleting individual highlights and books plus their tags. It also reads and completes the Daily Review, Readwise’s spaced-repetition resurfacing queue.
Authentication is a single access token, verified through Readwise’s dedicated /api/v2/auth/ endpoint rather than any read that could echo the token back.
Three routes to the same 20 actions. The Workflow tab is generated from Readwise'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.
highlight-create Save a highlight to the user's Readwise account. De-duped by Readwise itself.
highlight-export Pull a page of the user's highlight history, nested by book. Pass pageCursor to page through.
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 Readwise's real ids.
{
"manifestVersion": "2",
"name": "readwise-example",
"steps": [
{
"id": "book-get",
"uses": {
"app": "io.w6w.readwise",
"action": "book-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"bookId": "<bookId>"
}
}
]
}book-get book-list book-tag-create book-tag-get book-tag-list +15 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 Readwise, 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 Readwise. 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: "book-get",
payload: {
bookId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action book-get --payload '{"bookId":"<value>"}' Give an AI agent Readwise — without giving it Readwise'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.readwise#book-get",
"input": {
"bookId": "<bookId>"
}
}
}
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 Readwise 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.
Readwise'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. Readwise itself is MIT, and the runtime that executes it is source-available (FSL).
Readwise declares its own checks, so its health is a property of the app rather than something the host guesses at.
No public status page was found for Readwise as of 2026-08-29.