py-mcp-line: LINE Chat MCP Server

What does “py-mcp-line” MCP Server do?

The py-mcp-line MCP Server is a Python-based implementation of the Model Context Protocol (MCP) designed to provide AI assistants, such as language models, with standardized access to LINE Bot messages. By acting as a bridge between AI clients and LINE conversations, the server enables LLMs to read, analyze, and interact with LINE data in real-time. Built with FastAPI and leveraging asynchronous Python features for responsiveness, py-mcp-line makes it possible to process webhook events, validate data, and store messages in structured JSON format. This greatly enhances development workflows for projects requiring conversational analysis, bot development, or integration of LINE messaging data into broader AI-driven applications by exposing LINE resources, validating requests, and handling various message types.

List of Prompts

List of Resources

• LINE Message Resources
  • Exposes message types as resources with URIs like line://<message_type>/data, enabling clients to access different categories of LINE messages.
• Resource Descriptions
  • Each resource includes metadata such as description and MIME type to help clients understand and utilize the data correctly.
• Message Filtering
  • Resources support filtering by date, user, or content, allowing for targeted retrieval of conversation data.

List of Tools

• list_resources
  • Lists all available message types and provides resource URIs for clients to access.
• read_resource
  • Reads and returns messages of a specified type, supporting advanced filtering (e.g., by date or user).

Use Cases of this MCP Server

• Conversational Data Analysis
  • Developers can retrieve and analyze historical LINE chat data for sentiment analysis, topic modeling, or user behavior insights.
• Chatbot Development
  • Enables AI-driven assistants to interact with and respond to LINE messages, facilitating sophisticated conversational bots.
• Message Archiving
  • Automates the storage and archival of LINE messages in JSON format for compliance or record-keeping purposes.
• Multimodal Data Integration
  • Supports text, sticker, and image messages, allowing for analysis and processing of diverse data types in LINE conversations.

How to set it up

Windsurf

Claude

1. Prerequisites: Ensure Python 3.8+ is installed and all dependencies from requirements.txt are installed.
2. Locate Configuration File: On MacOS, open ~/Library/Application Support/Claude/claude_desktop_config.json. On Windows, open %APPDATA%/Claude/claude_desktop_config.json.
3. Add MCP Server: Insert the following JSON snippet into the mcpServers object:

   {
     "mcpServers": {
       "line": {
         "command": "python",
         "args": [
           "server.py"
         ],
         "env": {
           "LINE_CHANNEL_SECRET": "your_channel_secret",
           "LINE_ACCESS_TOKEN": "your_access_token",
           "SERVER_PORT": "8000",
           "MESSAGES_FILE": "data/messages.json"
         }
       }
     }
   }
   

4. Save and Restart: Save the file and restart Claude Desktop to apply the changes.
5. Verify Setup: Ensure the MCP server is running and accessible from Claude.

Securing API Keys

Store sensitive credentials in environment variables using the env key as shown above to prevent accidental exposure.

Cursor

Cline

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "line": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “line” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the above, py-mcp-line provides a solid MCP implementation focused on LINE message access, with clear resource and tool exposure, environment-based security, and real-world setup guidance for Claude. The lack of prompt templates and explicit sampling/root features limits broader score, but for conversational analysis and bot integration, it is functional and well-documented.

MCP Score

Overall, I would rate this MCP implementation a 6.5/10. It covers the core functionalities for LINE message integration and is well-suited for developers needing conversational data access, but lacks advanced MCP features like prompt templates, sampling, and roots support.