LivePort MCP
@dundas
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.
Basic information
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.
More AI & Agents MCP servers
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
🛡️ A.I.G（AI-Infra-Guard）
TencentA full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Intervals.icu MCP Server
mvilanovaModel Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.
Gemini MCP Server
aliargunMCP server implementation for Google's Gemini API
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。
Comments