This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Let your coding agent see and control the local dev servers it starts.
If you run Claude Code, Cursor or Codex across several git worktrees, each one starts dev
servers you never typed a command for. Ports collide, and an agent that hits EADDRINUSE
often can't tell a port conflict from a bug — so it "fixes" working code instead.
These integrations give the agent a way to look, rather than guess.
An MCP server — typed tools for any MCP client (Claude Code, Cursor, Claude Desktop, Windsurf, Zed). | |
A Claude Code skill, if you'd rather it shelled out to the CLI directly. | |
Wrap your dev command so | |
A Raycast extension for the same list, without leaving the launcher. |
Tool | What it does |
| Listening dev servers: port, process, branch, owner, idle. Read-only. |
| Stop the server on a given port. |
| A stable, collision-free port for this worktree — the fix for parallel agents fighting over |
| A port nothing is listening on right now, to bind immediately. |
Related MCP server: Harbor MCP Server
The skill, for any agent (Claude Code, Cursor, Copilot, Gemini…):
npx skills add dan-fetch-studio/tidyports-integrationsThe MCP server:
npm install -g @tidyports/mcpThen register it with your client, pointing at the installed tidyports-mcp binary. For
Claude Code:
claude mcp add tidyports -- tidyports-mcpThese are a thin layer over the tidy-ports CLI, which ships inside
TidyPorts — a free macOS menu-bar app that shows every dev server
running on your Mac and which agent started it.
brew install --cask dan-fetch-studio/tap/tidyportsOr download it from tidyports.app/download. macOS 15+.
The integrations here are MIT (see LICENSE). The TidyPorts app itself is source-available under its own licence.
This server cannot be deployed
Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.
Remote shell and detached long-running jobs on your own machines — no SSH, open ports or VPN.
Cloud console for a fleet of AI coding agents running on your own machines. OAuth.
Give your AI hands on every computer you own. Remote control of your Windows, Mac and Linux machines from one ChatGPT, Claude or Cursor chat — even from your phone. Ask it to find out why the office server is crawling, update every PC in the house, sort out your mom's laptop from another city, or ship the site from your work machine while you're on a train. It runs commands, reads files and takes a screenshot when it needs to see the screen. You decide what each computer allows, and you can cut any of them off in a second.
