
LINE Bot MCP Server
OfficialConnect AI agents to a LINE Official Account via the LINE Messaging API.
Add to your client
Copy the config for your MCP client and paste it into its config file.
npx @line/line-bot-mcp-serverPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"line-bot-mcp-server": {
"command": "npx",
"args": [
"@line/line-bot-mcp-server"
],
"env": {
"NPM_CONFIG_IGNORE_SCRIPTS": "true",
"CHANNEL_ACCESS_TOKEN": "FILL_HERE",
"DESTINATION_USER_ID": "FILL_HERE"
}
}
}
}Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf
Before you start
- Node.js v22 or later (for the npx installation)
- A LINE Official Account with the Messaging API enabled
- A LINE Channel Access Token (CHANNEL_ACCESS_TOKEN)
- Optionally a default recipient user ID (DESTINATION_USER_ID)
About LINE Bot MCP Server
An official MCP server by LINE that bridges AI agents (such as Claude Desktop or Cline) and the LINE Messaging API. It exposes 12 tools covering messaging (push and broadcast of text and flex messages), user profile retrieval, message quota, rich menu management, and follower ID listing. The server communicates over stdio and authenticates with a LINE Channel Access Token. It can be run via npx (Node.js v22+) or as a Docker container.
Tools & capabilities (12)
push_text_messagePush a simple text message to a user via LINE. Recipient defaults to DESTINATION_USER_ID if userId is not provided.
push_flex_messagePush a highly customizable flex message (bubble or carousel) to a user via LINE, with required alt text.
broadcast_text_messageBroadcast a simple text message to all users who have followed your LINE Official Account.
broadcast_flex_messageBroadcast a highly customizable flex message (bubble or carousel) to all users who have added your LINE Official Account.
get_profileGet detailed profile information of a LINE user including display name, profile picture URL, status message, and language.
get_message_quotaGet the message quota and consumption of the LINE Official Account, showing the monthly message limit and current usage.
get_rich_menu_listGet the list of rich menus associated with your LINE Official Account.
delete_rich_menuDelete a rich menu from your LINE Official Account by richMenuId.
set_rich_menu_defaultSet a rich menu as the default rich menu by richMenuId.
cancel_rich_menu_defaultCancel the default rich menu.
create_rich_menuCreate a rich menu from 1 to 6 actions (postback, message, uri, datetimepicker, camera, cameraRoll, location, richmenuswitch, clipboard), generate and upload an image, and set it as default.
get_follower_idsGet a list of user IDs of users who have added the LINE Official Account as a friend, with optional start continuation token and limit.
What this server can do
LINE Bot MCP Server provides tools for these capabilities — tap one to see every MCP server that does the same:
When to use it
- Letting an AI agent send notifications or replies to LINE users directly from a conversation
- Broadcasting announcements to all followers of a LINE Official Account
- Building and managing rich menus for a LINE Official Account programmatically
- Retrieving user profiles and follower IDs to drive personalized messaging
- Monitoring monthly message quota and consumption for the account
Security notes
Requires a LINE Channel Access Token (CHANNEL_ACCESS_TOKEN) passed as an environment variable; treat it as a secret. The npx config sets NPM_CONFIG_IGNORE_SCRIPTS=true to skip package install scripts. Broadcast tools send messages to all followers of the Official Account, so use with care.
LINE Bot MCP Server FAQ
Is this an official LINE project?
Yes. It is published by the LINE organization on GitHub and distributed as the @line/line-bot-mcp-server npm package. It is currently provided as a preview version.
What credentials do I need?
A LINE Channel Access Token (CHANNEL_ACCESS_TOKEN) is required. A DESTINATION_USER_ID is optional but required when a tool's input does not include a userId.
How can I run it?
Via npx with @line/line-bot-mcp-server (requires Node.js v22+), or via a Docker image you build from the repository. Both are configured as an mcpServers entry in your AI agent.
How do I test it locally?
After cloning, installing, and building, you can run the MCP Inspector with: npx @modelcontextprotocol/inspector node dist/index.js -e CHANNEL_ACCESS_TOKEN=... -e DESTINATION_USER_ID=...
Alternatives to LINE Bot MCP Server
Compare all alternatives →Connect your personal WhatsApp: search, read and send messages and media locally
Powerful Slack MCP with stdio/SSE/HTTP, DMs, group DMs and no-admin token auth
Full Telegram user-account MCP via MTProto: read chats, manage groups, send messages
Compare LINE Bot MCP Server with: