mcp-server-ngrok
Exposes a local MCP server via ngrok with SSE and Streamable HTTP transports for use in Kiro Web.
README
MCP Server for ngrok + Kiro Web
A local MCP (Model Context Protocol) server with SSE and Streamable HTTP transports, designed to be exposed via ngrok and used as a true MCP server in Kiro Web.
Quick Start
# 1. Install
npm install
# 2. Run the server
npm run dev
# 3. In another terminal, expose via ngrok
ngrok http 3000
Copy the ngrok HTTPS URL (e.g., https://abc123.ngrok-free.app).
Add to Kiro Web Config
{
"mcpServers": {
"my-local-server": {
"type": "sse",
"url": "https://YOUR-NGROK-URL.ngrok-free.app/sse"
}
}
}
Then start a new Kiro session - the AI will have access to all your custom tools!
Available Tools
| Tool | Description |
|---|---|
greet |
Generate a personalized greeting message |
get_current_time |
Get the current date/time (with optional timezone) |
calculate |
Perform arithmetic (add, subtract, multiply, divide) |
save_note |
Save a note with a key |
get_note |
Retrieve a saved note by key |
list_notes |
List all saved note keys |
system_info |
Get server system information |
Endpoints
| Endpoint | Method | Transport | Description |
|---|---|---|---|
/health |
GET | - | Health check |
/sse |
GET | SSE | SSE connection (legacy transport) |
/messages |
POST | SSE | SSE message handler |
/mcp |
POST | Streamable HTTP | Modern transport |
Adding Your Own Tools
Edit src/server.ts and add tools inside the createMcpServer() function:
server.registerTool(
"my_tool_name",
{
title: "My Tool",
description: "What this tool does",
inputSchema: {
param1: z.string().describe("Description of param1"),
param2: z.number().optional().describe("Optional param"),
},
},
async ({ param1, param2 }) => {
const result = `Got: ${param1}, ${param2}`;
return { content: [{ type: "text", text: result }] };
}
);
Architecture
┌─────────────────┐ ┌─────────────┐ ┌─────────────────────┐
│ Kiro Web │◀─────▶│ ngrok │◀─────▶│ Your Local Machine │
│ (AI Client) │ HTTPS │ tunnel │ HTTP │ MCP Server :3000 │
└─────────────────┘ └─────────────┘ └─────────────────────┘
Configuration
| Environment Variable | Default | Description |
|---|---|---|
PORT |
3000 |
Port the server listens on |
Security Notes
- Your ngrok URL is publicly accessible - keep it private
- For production, add authentication (API keys, OAuth)
- ngrok paid plans offer IP restrictions and fixed subdomains
License
MIT
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.