Skip to main content
Glama
LINE Bot MCP Server (SSE Support)

LINE Bot MCP Server (SSE Support)

by acquo

日本語版 READMEはこちら

LINE Bot MCP Server (with SSE Support)

npmjs Docker Hub

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 afork of the official LINE Bot MCP Server with additional SSE (Server-Sent Events) transport support. The original repository only supports stdio transport.

🔄 Fork Information

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.

Related MCP server: LINE Bot MCP Server

Transport Support

This MCP server supports multiple transport protocols:

  • stdio (default): Standard input/output for local integrations

  • SSE: Server-Sent Events over HTTP for web-based integrations

Tools

  1. push_text_message

    • Push a simple text message to a user via LINE.

    • Inputs:

      • user_id (string?): The user ID to receive a message. Defaults to DESTINATION_USER_ID. Either user_id or DESTINATION_USER_ID must be set.

      • message.text (string): The plain text content to send to the user.

  2. push_flex_message

    • Push a highly customizable flex message to a user via LINE.

    • Inputs:

      • user_id (string?): The user ID to receive a message. Defaults to DESTINATION_USER_ID. Either user_id or DESTINATION_USER_ID must be set.

      • message.altText (string): Alternative text shown when flex message cannot be displayed.

      • message.content (any): The content of the flex message. This is a JSON object that defines the layout and components of the message.

      • message.contents.type (enum): Type of the container. 'bubble' for single container, 'carousel' for multiple swipeable bubbles.

  3. broadcast_text_message

    • Broadcast a simple text message via LINE to all users who have followed your LINE Official Account.

    • Inputs:

      • message.text (string): The plain text content to send to the users.

  4. broadcast_flex_message

    • Broadcast a highly customizable flex message via LINE to all users who have added your LINE Official Account.

    • Inputs:

      • message.altText (string): Alternative text shown when flex message cannot be displayed.

      • message.content (any): The content of the flex message. This is a JSON object that defines the layout and components of the message.

      • message.contents.type (enum): Type of the container. 'bubble' for single container, 'carousel' for multiple swipeable bubbles.

  5. get_profile

    • Get detailed profile information of a LINE user including display name, profile picture URL, status message and language.

    • Inputs:

      • user_id (string?): The ID of the user whose profile you want to retrieve. Defaults to DESTINATION_USER_ID.

  6. get_message_quota

    • Get the message quota and consumption of the LINE Official Account. This shows the monthly message limit and current usage.

    • Inputs:

      • None

  7. get_rich_menu_list

    • Get the list of rich menus associated with your LINE Official Account.

    • Inputs:

      • None

  8. delete_rich_menu

    • Delete a rich menu from your LINE Official Account.

    • Inputs:

      • richMenuId (string): The ID of the rich menu to delete.

  9. set_rich_menu_default

    • Set a rich menu as the default rich menu.

    • Inputs:

      • richMenuId (string): The ID of the rich menu to set as default.

  10. cancel_rich_menu_default

    • Cancel the default rich menu.

    • Inputs:

      • None

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 user_id, DESTINATION_USER_ID is required. You can confirm this by following this instructions.

  • MCP_TRANSPORT: (optional) Transport protocol to use. Options: stdio (default), sse

  • MCP_PORT: (optional) Port for SSE transport. Default: 3000

Using stdio transport (default)

{
  "mcpServers": {
    "line-bot": {
      "command": "npx",
      "args": [
        "@line/line-bot-mcp-server"
      ],
      "env": {
        "CHANNEL_ACCESS_TOKEN" : "FILL_HERE",
        "DESTINATION_USER_ID" : "FILL_HERE"
      }
    }
  }
}

Using SSE transport

{
  "mcpServers": {
    "line-bot": {
      "command": "npx",
      "args": [
        "@line/line-bot-mcp-server"
      ],
      "env": {
        "CHANNEL_ACCESS_TOKEN" : "FILL_HERE",
        "DESTINATION_USER_ID" : "FILL_HERE",
        "MCP_TRANSPORT" : "sse",
        "MCP_PORT" : "3000"
      }
    }
  }
}

For SSE transport, the server will start an HTTP server with the following endpoints:

  • GET /sse - Establish SSE connection

  • POST /messages - Send messages to the server

  • GET /health - Health check endpoint

Installation (Using Docker)

You can use the pre-built Docker image from Docker Hub without building locally:

# Pull the latest image
docker pull acquojp/line-bot-mcp-server-sse:latest

# Run directly
docker run --rm -p 3000:3000 \
  -e CHANNEL_ACCESS_TOKEN="your_token" \
  -e DESTINATION_USER_ID="your_user_id" \
  acquojp/line-bot-mcp-server-sse:latest

Option B: Build from Source

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 repository:

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

Build the Docker image:

docker build -t line-bot-mcp-server-sse .

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 user_id, DESTINATION_USER_ID is required. You can confirm this by following this instructions.

  • MCP_TRANSPORT: (optional) Transport protocol to use. Options: stdio (default), sse

  • MCP_PORT: (optional) Port for SSE transport. Default: 3000

Using SSE transport (default) - Docker Hub Image

{
  "mcpServers": {
    "line-bot": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-p",
        "3000:3000",
        "-e",
        "CHANNEL_ACCESS_TOKEN",
        "-e",
        "DESTINATION_USER_ID",
        "acquojp/line-bot-mcp-server-sse:latest"
      ],
      "env": {
        "CHANNEL_ACCESS_TOKEN" : "FILL_HERE",
        "DESTINATION_USER_ID" : "FILL_HERE"
      }
    }
  }
}

Using stdio transport - Docker Hub Image

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

Versioning

This project respects semantic versioning

See http://semver.org/

Fork Information & Differences

This repository is a fork of the official LINE Bot MCP Server with the following enhancements:

✨ Added Features

  • SSE (Server-Sent Events) Transport Support: Enables web-based integrations and HTTP connections

  • Multi-Transport Architecture: Supports both stdio (original) and SSE transports

  • Docker Hub Distribution: Pre-built Docker images available for easy deployment

  • Production-Ready Configuration: Optimized for both development and production environments

🔄 Transport Comparison

Feature

stdio (Original)

SSE (Added)

Use Case

Local CLI tools, direct process communication

Web applications, HTTP-based integrations

Connection

Standard input/output streams

HTTP + Server-Sent Events

Deployment

Process-based

Server-based (HTTP)

Port

Not required

Requires port (default: 3000)

Scalability

Single process

Multiple concurrent connections

🐳 Docker Hub

Contributing

Please check CONTRIBUTING before making a contribution.

Contributing to This Fork

If you'd like to contribute to the SSE transport features or other enhancements in this fork, please:

  1. Fork this repository

  2. Create a feature branch

  3. Make your changes

  4. Submit a pull request

For contributions to the original LINE Bot MCP Server, please visit the official repository.

Available Tools

10 tools
broadcast_flex_messageA

Broadcast a highly customizable flex message via LINE to all users who have added your LINE Official Account. Supports both bubble (single container) and carousel (multiple swipeable bubbles) layouts. Please be aware that this message will be sent to all users.

Inputs: message (required).

broadcast_text_messageA

Broadcast a simple text message via LINE to all users who have followed your LINE Official Account. Use this for sending plain text messages without formatting. Please be aware that this message will be sent to all users.

Inputs: message (required).

cancel_rich_menu_defaultB

Cancel the default rich menu.

Inputs: no named parameters.

delete_rich_menuC

Delete a rich menu from your LINE Official Account.

Inputs: richMenuId (required).

get_message_quotaA

Get the message quota and consumption of the LINE Official Account. This shows the monthly message limit and current usage.

Inputs: no named parameters.

get_profileB

Get detailed profile information of a LINE user including display name, profile picture URL, status message and language.

Inputs: userId.

get_rich_menu_listB

Get the list of rich menus associated with your LINE Official Account.

Inputs: no named parameters.

push_flex_messageC

Push a highly customizable flex message to a user via LINE. Supports both bubble (single container) and carousel (multiple swipeable bubbles) layouts.

Inputs: message (required), userId.

push_text_messageB

Push a simple text message to a user via LINE. Use this for sending plain text messages without formatting.

Inputs: message (required), userId.

set_rich_menu_defaultC

Set a rich menu as the default rich menu.

Inputs: richMenuId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools have distinct purposes, such as broadcast vs. push for mass vs. individual messaging, and flex vs. text for message types. However, cancel_rich_menu_default and delete_rich_menu could be slightly confusing as both involve removing rich menus, though their descriptions clarify one cancels a default setting while the other deletes the menu entirely.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case, such as broadcast_flex_message, get_profile, and set_rich_menu_default. This uniformity makes the tool set predictable and easy to navigate for an agent.

    Tool Count5/5

    With 10 tools, the count is well-scoped for a LINE Bot server, covering core messaging, user profile management, rich menu operations, and quota checking. Each tool serves a clear purpose without redundancy or bloat.

    Completeness4/5

    The tool set covers essential LINE Bot operations, including message broadcasting/pushing, user profile retrieval, rich menu management, and quota monitoring. A minor gap is the lack of tools for creating or updating rich menus, which might limit full lifecycle management, but agents can still handle common workflows effectively.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      Model Context Protocol server implementation that integrates the LINE Messaging API to connect AI agents with LINE Official Accounts, enabling agents to send messages to users.
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      Enables AI agents to send messages, manage rich menus, and interact with users through LINE Official Accounts via the LINE Messaging API. Supports both individual messaging and broadcasting to all followers with text and customizable flex messages.
      18
      Apache 2.0
    • A
      license
      A
      quality
      Not graded
      maintenance
      Connects an AI agent to a LINE Official Account through the LINE Messaging API, enabling it to push and broadcast text or flex messages to users. It also supports retrieving user profiles, message quotas, follower IDs, and group summaries, plus creating and managing rich menus.
      13
      Apache 2.0
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to operate one or many LINE Official Accounts through natural language — broadcasts, Flex and tappable Rich Messages with zero-setup image hosting, rich menus, coupons, audiences, insights, webhooks, and LINE Shopping — with pre-flight quota and quiet-hour guardrails. It ships 51 tools (37 messaging + 14 shopping) plus resources and guided prompts, and runs over stdio or token-authenticated HTTP with any MCP-compatible host.
      200 npm
      MIT