Featured

Deploy OpenClaw in 60 seconds β€” 20% off logoDeploy OpenClaw in 60 seconds β€” 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger β†’
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger β†’
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free β†’
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now β†’
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data β€” no proxies, no parsers, no maintenance.

Start building free β†’
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it β€” secured from day one.

Get it set up for you β†’
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free β†’
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here β†’

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

localhost-mcp MCP server](https://glama.ai/mcp/servers/HasanJahidul/localhost-mcp/badges/score.svg)](https://glama.ai/mcp/servers/HasanJahidul/localhost-mcp) πŸ“‡ 🏠 🍎 πŸͺŸ 🐧 - Inspect, manage, and kill local dev servers.

README.md

<p align="center"> <img src="assets/logo.png" alt="localhost-mcp" width="200" /> </p>

localhost-mcp

![localhost-mcp MCP server](https://glama.ai/mcp/servers/HasanJahidul/localhost-mcp) ![CI](https://github.com/HasanJahidul/localhost-mcp/actions/workflows/ci.yml) ![npm version](https://www.npmjs.com/package/localhost-mcp) ![License: MIT](LICENSE)

MCP server that inspects, manages, and kills local dev servers. Stop guessing what's on :3000.

!demo

Pairs with terminal-history-mcp β€” together they give your AI agent full memory of your dev environment: what you ran, what's running.

Why

Every dev hits these daily:

  • Error: listen EADDRINUSE :::3000 β€” what's holding the port?
  • 5 forgotten node / vite / next PIDs from last week eating RAM
  • Switching projects β†’ no idea which dev servers still running
  • lsof -i :3000, kill -9 <pid>, repeat

localhost-mcp makes it one tool call.

Install

npm install -g localhost-mcp

Wire into Claude Code:

claude mcp add --scope user localhost -- localhost-mcp

Or any MCP-compatible client. The command runs as a stdio MCP server.

Tools

| Tool | Purpose | |------|---------| | list_dev_servers | All listening dev servers w/ port, pid, framework, project, uptime, mem, cpu | | port_info | Inspect single port β€” who holds it | | kill_server | Kill by pid or port. Dry-run by default; pass confirm=true to execute | | find_zombies | Detect long-running, idle, memory-heavy dev servers | | port_conflict | Why is port X busy + 5 free alternatives nearby |

Sample output

{
  "port": 3000,
  "pid": 48211,
  "process": "node",
  "cmdline": "next dev",
  "cwd": "/Users/me/code/myapp",
  "project_name": "myapp",
  "framework": "next.js",
  "uptime_seconds": 14523,
  "memory_mb": 412,
  "cpu_pct": 0.3,
  "user": "me"
}

Safety

  • kill_server defaults to dry-run. Must pass confirm=true.
  • Refuses to kill PIDs < 1000 (system processes).
  • Refuses processes outside the dev whitelist (node, python, ruby, go, deno, bun, php, java, rails, vite, next, etc).
  • SIGTERM first, escalates to SIGKILL after 5s timeout.

Frameworks detected

next.js, vite, nuxt, remix, astro, webpack-dev-server, esbuild, create-react-app, express, fastify, koa, hono, rails, django, flask, fastapi, uvicorn, gunicorn, deno, bun, php-builtin, jekyll, hugo.

Falls back to package.json sniffing when the cmdline is generic (node server.js).

Platform support

  • macOS β€” full support (uses lsof)
  • Linux β€” full support (uses lsof + /proc)
  • Windows β€” basic port scan only (uses netstat); cwd / framework detection limited

CLI usage

localhost-mcp list      # JSON list of all dev servers
localhost-mcp zombies   # JSON list of zombie candidates
localhost-mcp           # Start MCP stdio server

Build from source

git clone https://github.com/hasanjahidul/localhost-mcp.git
cd localhost-mcp
npm install
npm run build
node dist/cli.js list

License

MIT

See related servers & alternatives β†’

Related MCP servers

Browse all β†’

Related guides

Hand-picked reading to help you choose and use Vector & Memory servers.