line-render-mcp

line-render-mcp

Enables sending LINE text messages and Flex Messages to user or group IDs, checking message quota, and receiving group webhooks via a remote MCP endpoint for ChatGPT integration.

Category
Visit Server

README

LINE Webhook + Remote MCP for Render

This service has two public endpoints:

  • POST /callback — LINE Messaging API webhook, protected by LINE_CHANNEL_SECRET.
  • GET, POST, DELETE /mcp — Streamable HTTP MCP endpoint, protected by MCP_API_KEY as a bearer token.

What it can do

  • Send LINE text messages to a User ID (U...) or Group ID (C...).
  • Send LINE Flex Messages.
  • Report message quota.
  • Receive a group webhook and expose Group IDs received since the service started.

Deploy to Render

  1. Push this directory to a private GitHub repository. Do not commit .env.
  2. In Render, select New > Blueprint, choose the repository, and create the service from render.yaml.
  3. In the Render service's Environment tab, set:
    • CHANNEL_ACCESS_TOKEN
    • LINE_CHANNEL_SECRET
    • DESTINATION_ID (optional)
    • keep the generated MCP_API_KEY private.
  4. After the deploy succeeds, copy the public URL. It will look like https://line-render-mcp.onrender.com.
  5. In LINE Developers Console > Messaging API:
    • set Webhook URL to https://line-render-mcp.onrender.com/callback;
    • click Verify;
    • turn on Use webhook;
    • enable Allow bot to join group chats if you need group delivery.
  6. In a ChatGPT Business workspace, create a custom app with the endpoint: https://line-render-mcp.onrender.com/mcp Configure it to send Authorization: Bearer <MCP_API_KEY> and only enable the tools you want.

Local test

npm install
Copy-Item .env.example .env
# Fill the values in .env, then:
npm run dev

For a webhook test, use a public HTTPS tunnel only during development. Use the Render URL in production.

Security notes

  • Never put the LINE access token or MCP_API_KEY into source code, an issue, or a public repository.
  • Keep the Render repository private.
  • MCP_API_KEY grants the ability to send LINE messages. Rotate it immediately if exposed.
  • get_known_groups currently stores IDs in process memory only. Use a database before relying on it across redeploys or multiple service instances.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured