================== /// MCP /// /// LIN /// ================== [server:online] [protocol:ready]
line-bot-mcp-server
by line
MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
435
65
Specialized01
push_text_message
Push a simple text message to a specified LINE user.
02
push_flex_message
Push a customizable flex message to a specified LINE user.
03
broadcast_text_message
Broadcast a simple text message to all users who have followed the LINE Official Account.
04
broadcast_flex_message
Broadcast a flex message to all users who have added the LINE Official Account.
05
get_profile
Retrieve detailed profile information of a LINE user.
06
get_message_quota
Retrieve the message quota and current consumption of the LINE Official Account.
07
get_rich_menu_list
Retrieve the list of rich menus associated with the LINE Official Account.
08
delete_rich_menu
Delete a specified rich menu from the LINE Official Account.
09
set_rich_menu_default
Set a specified rich menu as the default rich menu.
10
cancel_rich_menu_default
Cancel the current default rich menu.
Installation
1. Prerequisites
• Node.js ≥ 18 and npm ≥ 9 installed.
• A LINE Official Account and a Messaging API channel created.
• The following credentials ready:
- LINE_CHANNEL_SECRET
- LINE_CHANNEL_ACCESS_TOKEN
2. Clone the repository
git clone https://github.com/line/line-bot-mcp-server.git
cd line-bot-mcp-server
3. Install dependencies
npm install
# or
yarn install
4. Configure environment variables (create an .env file or export them directly)
LINE_CHANNEL_SECRET=xxxxxxxxxxxxxxxxxxxxxx
LINE_CHANNEL_ACCESS_TOKEN=xxxxxxxxxxxxxxxxxxxxxx
PORT=3000 # optional – default 3000
5. Build the TypeScript sources
npm run build
6. Start the server
npm start # runs the compiled JavaScript from /dist
# or for development with hot-reload
npm run dev
7. Webhook setup
• In the LINE Developers Console, set the webhook URL to:
https://<your-domain>/webhook
• Enable the webhook switch.
8. Verify
• Send a message to your LINE Official Account; the MCP server should relay the event to your AI agent and return its response.
Documentation
License: Apache License 2.0
Updated 7/30/2025