Send and receive messages through the LINE Messaging API: reply, push, multicast and broadcast, profiles, rich menus, and media.
LINE ships in the w6w first-party pack. It declares 17 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.lineLINE is the dominant chat platform in Japan (and widely used across Taiwan, Thailand and Indonesia), and the Messaging API is how a business account — a LINE Official Account — sends and receives chat messages, images, stickers and rich menus through it.
This app covers the core of that surface: replying to an inbound event with its one-time reply token, pushing or multicast/broadcasting a message outside that window, reading a bot’s own identity and a user’s profile, retrieving media a user sent, and managing rich menus (the tappable menu bar under a LINE Official Account’s chat). Message content itself — text, image, sticker, template, flex — is accepted as LINE’s own JSON message-object array rather than being re-modelled per type, since the vendor’s schema already covers dozens of message shapes and re-deriving each as a separate typed action would multiply this app’s surface without adding anything the vendor’s own object model doesn’t already say.
Authentication is a single long-lived channel access token, issued once from the LINE Developers Console and used as a Bearer token on every call — LINE’s more elaborate JWT-assertion token-issuance flow is left to the console rather than reimplemented here.
Three routes to the same 17 actions. The Workflow tab is generated from LINE'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.
content-get Download media (image, video, audio or file) a user sent, base64-encoded. Only works while LINE still hosts it, and only for content whose webhook event reported `contentProvider.type` as "line".
message-broadcast Send a message to every friend of this LINE Official Account. Up to 5 messages.
message-multicast Send the same message to up to 500 user IDs. Cannot target group or room chats.
message-push Send a message to a user, group chat or multi-person chat. Up to 5 messages.
message-quota-consumption-get Get the (approximate) number of messages sent so far this month.
message-quota-get Get this month's configured message-sending limit, if one is set.
message-reply Reply to a webhook event using its one-time reply token. Up to 5 messages.
rich-menu-create Define a rich menu object. Upload an image and set it default/linked to show it.
rich-menu-image-upload Attach an image (JPEG or PNG, 800-2500px wide, aspect ratio >= 1.45, max 1MB) to a rich menu. Can only be done once per rich menu.
rich-menu-link-to-user Show this rich menu to one user, replacing any rich menu already linked to them.
rich-menu-list List rich menus created through the Messaging API (not via Official Account Manager).
rich-menu-set-default Show this rich menu to every user with no per-user rich menu of their own linked. Replaces any previous default.
rich-menu-unlink-from-user Remove the per-user rich menu linked to a user, falling back to the app-wide default.
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 LINE's real ids.
{
"manifestVersion": "2",
"name": "line-example",
"steps": [
{
"id": "content-get",
"uses": {
"app": "io.w6w.line",
"action": "content-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"messageId": "<messageId>"
}
}
]
}content-get bot-info-get message-broadcast message-multicast message-push +12 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 LINE, 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 LINE. 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: "content-get",
payload: {
messageId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action content-get --payload '{"messageId":"<value>"}' Give an AI agent LINE — without giving it LINE'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.line#content-get",
"input": {
"messageId": "<messageId>"
}
}
}
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 LINE 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.
LINE'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. LINE itself is MIT, and the runtime that executes it is source-available (FSL).
LINE declares its own checks, so its health is a property of the app rather than something the host guesses at.
Component status from api.line-status.info, scoped to the "Messaging API" group only (its API and Webhook components) — the page also covers LINE Login, LIFF and the Developers Console/Site, which this app does not use.
This month's configured message-sending limit (if any) against messages sent so far, from GET /v2/bot/message/quota and GET /v2/bot/message/quota/consumption.