README

LINE Bot MCP Server (Custom - Core Edition)

Note: This is a customized fork from https://github.com/line/line-bot-mcp-server

⚡ Optimized for low memory usage - Rich menu tools disabled by default

Model Context Protocol (MCP) server implementation that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.

[!NOTE] This repository is provided as a preview version. While we offer it for experimental purposes, please be aware that it may not include complete functionality or comprehensive support.

Tools (Core Edition)

Available Tools:

1. push_text_message - Push a simple text message to a user via LINE.
2. push_flex_message - Push a highly customizable flex message to a user via LINE.
3. get_profile - Get detailed profile information of a LINE user.
4. get_message_quota - Get the message quota and consumption of the LINE Official Account.

Disabled Tools (to reduce memory usage):

• broadcast_text_message
• broadcast_flex_message
• get_rich_menu_list
• delete_rich_menu
• set_rich_menu_default
• cancel_rich_menu_default
• create_rich_menu (uses puppeteer - heavy memory usage)

If you need rich menu features, consider using them via LINE Messaging API directly or enable them manually in src/index.ts

Installation (Using npx)

requirements:

• Node.js v20 or later

Step 1: Create LINE Official Account

This MCP server utilizes a LINE Official Account. If you do not have one, please create it by following this instructions.

If you have a LINE Official Account, enable the Messaging API for your LINE Official Account by following this instructions.

Step 2: Configure AI Agent

Please add the following configuration for an AI Agent like Claude Desktop or Cline.

Set the environment variables or arguments as follows:

• CHANNEL_ACCESS_TOKEN: (required) Channel Access Token. You can confirm this by following this instructions.
• DESTINATION_USER_ID: (optional) The default user ID of the recipient. If the Tool's input does not include userId, DESTINATION_USER_ID is required. You can confirm this by following this instructions.

Note: Since this is a custom fork, you'll need to clone and build locally instead of using npx with the official package.

{
  "mcpServers": {
    "line-bot": {
      "command": "node",
      "args": [
        "YOUR_PATH/line-bot-mcp-server/dist/index.js"
      ],
      "env": {
        "CHANNEL_ACCESS_TOKEN" : "FILL_HERE",
        "DESTINATION_USER_ID" : "FILL_HERE"
      }
    }
  }
}

Installation (Using Docker)

Step 1: Create LINE Official Account

This MCP server utilizes a LINE Official Account. If you do not have one, please create it by following this instructions.

If you have a LINE Official Account, enable the Messaging API for your LINE Official Account by following this instructions.

Step 2: Build line-bot-mcp-server image

Clone this custom repository:

git clone https://github.com/YOUR_USERNAME/line-bot-mcp-server.git

Build the Docker image:

docker build -t custom/line-bot-mcp-server .

Step 3: Configure AI Agent

Please add the following configuration for an AI Agent like Claude Desktop or Cline.

Set the environment variables or arguments as follows:

• mcpServers.args: (required) The path to line-bot-mcp-server.
• CHANNEL_ACCESS_TOKEN: (required) Channel Access Token. You can confirm this by following this instructions.
• DESTINATION_USER_ID: (optional) The default user ID of the recipient. If the Tool's input does not include userId, DESTINATION_USER_ID is required. You can confirm this by following this instructions.

{
  "mcpServers": {
    "line-bot": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "CHANNEL_ACCESS_TOKEN",
        "-e",
        "DESTINATION_USER_ID",
        "custom/line-bot-mcp-server"
      ],
      "env": {
        "CHANNEL_ACCESS_TOKEN" : "FILL_HERE",
        "DESTINATION_USER_ID" : "FILL_HERE"
      }
    }
  }
}

Local Development with Inspector

You can use the MCP Inspector to test and debug the server locally.

Prerequisites

1. Clone the repository:

git clone https://github.com/Mbiz-consultant/line-bot-mcp
cd line-bot-mcp-server

2. Install dependencies:

npm install

3. Build the project:

npm run build

Run the Inspector

After building the project, you can start the MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js \
  -e CHANNEL_ACCESS_TOKEN="YOUR_CHANNEL_ACCESS_TOKEN" \
  -e DESTINATION_USER_ID="YOUR_DESTINATION_USER_ID"

This will start the MCP Inspector interface where you can interact with the LINE Bot MCP Server tools and test their functionality.

Versioning

This project respects semantic versioning

See http://semver.org/

Contributing

Please check CONTRIBUTING before making a contribution.