Where is the source code for Harbor?
The source code is at https://github.com/luke-fairbanks/harbor-mcp (MIT licensed).
@luke-fairbanks
基本信息
Native macOS app that boots all your local dev servers with one button: smart port allocation, crash recovery, live resource monitoring, and an in-process MCP server so Claude/Codex can drive your dev environment.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"harbor": {
"type": "http",
"url": "http://127.0.0.1:7777/mcp",
"headers": {
"Authorization": "Bearer <token from Harbor's Connect screen>"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,直接连接服务器端点实时获取工具列表。
Harbor is a native macOS app that boots all your local dev servers with one button: smart port allocation probed on both IPv4 and IPv6, crash recovery with bounded backoff, live logs, and per-service resource monitoring. An embedded Streamable HTTP MCP server exposes all of it to AI agents.
Install the signed and notarized dmg from GitHub Releases (or brew install --cask luke-fairbanks/tap/harbor), drag a project folder onto the window, and Harbor proposes the run config. Open the Connect your Claude screen for one-click MCP setup of Claude Code, Claude Desktop, or Codex.
The source code is at https://github.com/luke-fairbanks/harbor-mcp (MIT licensed).
Yes. Harbor runs a local Streamable HTTP MCP server at http://127.0.0.1:7777/mcp, authenticated with a per-install bearer token shown in Harbor's Connect screen.

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links
MeroFoundry is a remote MCP server available at https://platform.merofoundry.com/mcp.

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url

DrUrls audits websites for SEO, and its MCP server lets Claude, ChatGPT, Claude Code, Cursor or VS Code work with those audits directly: list your sites with their latest score and grade, read each issue across SEO, perf

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
评论