MCP.so
Sign In
L

LivePort MCP

@dundas

Repository

About LivePort MCP

Give AI agents access to your localhost dev server. Zero-config tunnel that works with Claude Code, OpenClaw, and any MCP-compatible agent. No interstitial pages, no account required.

#tunnel#localhost#ai-agents#ngrok-alternative#developer-tools#mcp#claude-code

Basic information

Category

AI & Agents

Transports

stdio

Publisher

dundas

Submitted by

David K. Dundas

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "liveport": {
      "command": "npx",
      "args": [
        "@liveport/mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is LivePort MCP?

LivePort MCP is a secure tunneling tool that creates temporary URLs for applications running on your localhost. It provides key-based authentication and an Agent SDK, enabling AI coding assistants (like Claude, Cursor, etc.) to wait for and access these tunnels for testing.

How to use LivePort MCP?

To use LivePort MCP, install the CLI globally with npm install -g @liveport/cli, obtain a bridge key from app.liveport.dev, and create a tunnel with liveport connect <port> --key <bridge-key>. For AI agent integration, install @liveport/agent-sdk and call agent.waitForTunnel() in your TypeScript code.

Key features of LivePort MCP

  • Secure temporary localhost tunnels with key-based authentication
  • CLI for manual tunnel creation and management
  • Agent SDK for AI coding assistants (e.g., Claude, Cursor)
  • Cross-platform CLI commands (connect, status, disconnect)
  • Programmatic tunnel waiting with configurable timeout and polling

Use cases of LivePort MCP

  • AI coding assistants testing web applications on a developer’s localhost
  • Running end‑to‑end tests against a tunneled local server
  • Collaborative debugging by sharing a temporary public URL of a local service
  • Integrating automated test suites that need to reach a development server

FAQ from LivePort MCP

What is the difference between LivePort MCP and traditional ngrok/localhost.run?

LivePort MCP is built specifically for AI agents, providing a dedicated Agent SDK that lets agents wait for a tunnel to be ready rather than requiring developers to manually share a URL. It uses key-based authentication and temporary tunnels.

What are the runtime requirements for LivePort MCP?

The CLI and Agent SDK require Node.js and npm. The tunnel server infrastructure uses Node.js, PostgreSQL, Redis, and is hosted on Cloudflare and Fly.io.

Where does data live when using LivePort MCP?

Tunnel traffic passes through a tunnel server (based on a LocalTunnel fork). The tunnels are temporary; authentication uses a bridge key managed via the dashboard. No user application data is persisted by the tunnel server.

What are the known limits of LivePort MCP?

The README does not specify explicit limits. Tunnels have an expiry time (visible via the expiresAt field in the Agent SDK). The CLI and SDK assume Node.js environments.

What transport and authentication does LivePort MCP use?

All communication uses HTTPS. Authentication is performed via a bridge key (string starting with lpk_) provided at tunnel creation and during agent SDK initialization.

Comments

More AI & Agents MCP servers

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

Perplexity Ask MCP Server

ppl-ai

The official MCP server implementation for the Perplexity API Platform

2.4K

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468