MCP-Server, der lokale Entwicklungsserver inspiziert, verwaltet und beendet. Hören Sie auf zu raten, was auf :3000 läuft.
Lässt sich mit terminal-history-mcp kombinieren – zusammen geben sie Ihrem KI-Agenten ein vollständiges Gedächtnis Ihrer Entwicklungsumgebung: was Sie ausgeführt haben und was gerade läuft.
Jeder Entwickler stößt täglich auf diese Probleme:
Error: listen EADDRINUSE :::3000 — was belegt den Port?
5 vergessene node / vite / next PIDs von letzter Woche, die RAM verbrauchen
Projektwechsel → keine Ahnung, welche Entwicklungsserver noch laufen
lsof -i :3000, kill -9 <pid>, wiederholen
localhost-mcp macht daraus einen einzigen Tool-Aufruf.
Related MCP server: Git Insight MCP
npm install -g localhost-mcpIn Claude Code einbinden:
claude mcp add --scope user localhost -- localhost-mcpOder in einen beliebigen MCP-kompatiblen Client. Der Befehl läuft als stdio-MCP-Server.
Tool | Zweck |
| Alle aktiven Entwicklungsserver mit Port, PID, Framework, Projekt, Laufzeit, RAM, CPU |
| Einzelnen Port inspizieren — wer belegt ihn |
| Beenden nach PID oder Port. Standardmäßig Trockenlauf; |
| Langlebige, inaktive oder speicherintensive Entwicklungsserver erkennen |
| Warum ist Port X belegt + 5 freie Alternativen in der Nähe |
{
"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"
}kill_server ist standardmäßig ein Trockenlauf. confirm=true muss übergeben werden.
Weigert sich, PIDs < 1000 (Systemprozesse) zu beenden.
Weigert sich, Prozesse außerhalb der Entwicklungs-Whitelist (node, python, ruby, go, deno, bun, php, java, rails, vite, next, etc.) zu beenden.
Zuerst SIGTERM, Eskalation zu SIGKILL nach 5s Timeout.
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.
Fällt auf package.json-Analyse zurück, wenn die Befehlszeile generisch ist (node server.js).
macOS — volle Unterstützung (nutzt lsof)
Linux — volle Unterstützung (nutzt lsof + /proc)
Windows — nur grundlegender Port-Scan (nutzt netstat); CWD / Framework-Erkennung eingeschränkt
localhost-mcp list # JSON list of all dev servers
localhost-mcp zombies # JSON list of zombie candidates
localhost-mcp # Start MCP stdio servergit clone https://github.com/hasanjahidul/localhost-mcp.git
cd localhost-mcp
npm install
npm run build
node dist/cli.js listMIT
Read-only. Flags dev servers that look abandoned — all three of: uptime > 6h AND CPU < 1% AND memory > 100MB. By default it excludes known always-on noise (VS Code server, language servers, other MCP servers, postgres/redis, sidekiq, etc.); set include_excluded: true to also list those. Each candidate comes with the reasons it matched. This tool never kills anything — pass results to kill_server. Returns { count, candidates[] }.
Inputs: include_excluded. Returns: count, candidates
Terminates a local dev server by pid or port. DESTRUCTIVE. Safe by default: with no confirm, this is a DRY RUN — it reports what it would kill and changes nothing. Pass confirm: true to actually terminate: sends SIGTERM, waits up to 5s, then escalates to SIGKILL (or SIGKILL immediately if force: true). Refuses PIDs below 1000 and processes that don't look like dev servers. Provide exactly one of pid or port. Returns what was (or would be) killed and the signal used.
Inputs: pid, port, force, confirm. Returns: pid, port, killed, signal, +3 more
Read-only. Lists every local development server (next, vite, nuxt, remix, astro, rails, django, flask, express, deno, bun, etc.) currently LISTENING on a TCP port. For each: port, pid, process name, command line, working directory, project name, detected framework, uptime, memory (MB), CPU %, and owning user. Uses lsof on macOS/Linux and netstat on Windows; on Windows the cwd/framework fields are limited. Takes no arguments. Returns { count, servers[] }.
Inputs: no named parameters. Returns: count, servers
Read-only. Diagnoses an EADDRINUSE situation: given a port, returns the dev server currently blocking it plus 5 free alternative ports nearby. Use it when a listen EADDRINUSE error fires and you want both the culprit and a port to switch to.
Inputs: port (required). Returns: port, blocked_by, alternatives
Read-only. Inspects a single TCP port and reports the dev server holding it (same fields as list_dev_servers). If nothing is listening, or the listener is not a recognised dev process, returns { port, status: "free" }. Useful for answering "what's on :3000?" before starting or killing something.
Inputs: port (required). Returns: Either a dev-server record (see list_dev_servers) or `{ port, status: "free" }`.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose: listing servers, inspecting a single port, finding zombies, killing servers, and diagnosing port conflicts. There is no functional overlap.
Tool names use snake_case, and most follow a verb_noun pattern (find_zombies, kill_server, list_dev_servers). However, port_conflict and port_info are noun-first, which is a minor inconsistency.
With 5 tools, the set is well-scoped for managing local dev servers: query, inspect, cleanup, and conflict resolution. No tool feels superfluous or missing.
The tools cover listing, inspecting, zombie identification, killing, and conflict diagnosis. There is a minor gap in that bulk operations (e.g., kill all zombies) are not directly supported, but the intended workflow is clear.
2,000+ MCP servers read at source level. Know what one does before you connect. Free, no key.
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Self-hosted MCP server: 26 deterministic dev, security, and EVM tools.