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.
README
LINE Webhook + Remote MCP for Render
This service has two public endpoints:
POST /callback— LINE Messaging API webhook, protected byLINE_CHANNEL_SECRET.GET, POST, DELETE /mcp— Streamable HTTP MCP endpoint, protected byMCP_API_KEYas 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
- Push this directory to a private GitHub repository. Do not commit
.env. - In Render, select New > Blueprint, choose the repository, and create the service from
render.yaml. - In the Render service's Environment tab, set:
CHANNEL_ACCESS_TOKENLINE_CHANNEL_SECRETDESTINATION_ID(optional)- keep the generated
MCP_API_KEYprivate.
- After the deploy succeeds, copy the public URL. It will look like
https://line-render-mcp.onrender.com. - 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.
- set Webhook URL to
- In a ChatGPT Business workspace, create a custom app with the endpoint:
https://line-render-mcp.onrender.com/mcpConfigure it to sendAuthorization: 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_KEYinto source code, an issue, or a public repository. - Keep the Render repository private.
MCP_API_KEYgrants the ability to send LINE messages. Rotate it immediately if exposed.get_known_groupscurrently stores IDs in process memory only. Use a database before relying on it across redeploys or multiple service instances.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.