Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Orphan MCP Hunter

    1

    Finds the MCP servers and node processes your AI coding tools left running after their session died, with evidence per row. Nothing is stopped until you say which.

    $7

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Orphan MCP Hunter

    Orphan MCP Hunter

    Example session with this skill installed

    My Mac has been slow all week. Check if Claude Code or Cursor left any MCP servers or node processes running behind.

    • Read your context and instructions
    • Compiled the orphan mcp hunter

    Scanned 412 processes with ps -axo pid=,ppid=,lstart=,command= at Sat Nov 15 00:22. Applied the three Stray rules. Two findings, one of them a judgement call.

    #FindingPID(s)StartedEvidenceSuggested action
    1claude-mem worker (orphan runtime)14964Oct 29 02:01, 17d agoPPID 1, bun .../claude-mem/10.6.0/scripts/worker-service.cjs, matches /.claude/stop
    2claude-mem ×2 (duplicate)63584 (keep 50619)Nov 13 18:00, 29h before newestsame name, two parent sessionsstop 63584 if that session is closed
    3playwright-mcp ×2 (duplicate)63760 (keep 50715)Nov 13 18:00, 29h before newestsame name, two parent sessionsstop 63760 if that session is closed

    Not flagged, and why

    • obsidian-mcp ×2: both started Nov 13 21:37, two seconds apart, one Claude Desktop session with two vaults. Wrapper (npm exec) and leaf (node .../obsidian-mcp) counted as one instance each. Not duplicates.
    • claude daemon run under PPID 1: that is where it belongs.
    • 6 Claude Desktop renderer helpers whose args contain claude-mcp: Electron --type= processes, excluded.

    Totals: 1 orphan, 2 duplicate instances, ~214 MB resident.

    Rows 2 and 3 come from a Claude Code session started Thursday evening. If that terminal is still open, keep them. If not, say "stop 14964, 63584, 63760" and I will send SIGTERM, wait 3 seconds, SIGKILL anything still alive, then re-scan and show you what is gone.

    Nothing has been stopped yet.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Claude Code, Cursor, Codex and Claude Desktop start MCP servers per session and often do not stop them. The session ends, launchd adopts the server, and it stays resident until you reboot. A real audit of one laptop on an ordinary afternoon: 3× claude-mem, 2× context7, 2× playwright-mcp, 4× obsidian-mcp. Eleven servers, zero living parents.

    ps aux | grep finds them if you already suspect they exist. This skill is for when you do not.

    What it does

    Your agent runs one ps command and applies the same three rules as the Stray macOS app:

    1. Orphan MCP server (strong). Parent PID is 1 and the command line matches MCP tooling (/_npx/, mcp-server, -mcp, /.claude/, modelcontextprotocol).
    2. Duplicate instances (warning). Same server name running under two different parents, started more than an hour apart. Two windows of one session are not duplicates.
    3. Orphan runtime (warning). A node, bun or deno process reparented to launchd and up for more than 24 hours. A fresh dev server you are still using is not flagged.

    Every row shows the evidence: PID, parent, matched pattern, start time, and the process named after what it runs (claude-mem, playwright-mcp), never a bare node.

    What it does not do

    It does not kill anything on its own. The report comes first, then the agent waits for you to name PIDs. Termination is SIGTERM, a 3-second wait, then SIGKILL only if still alive, and the PID is re-checked against the report before anything is sent. Editor helper processes are excluded.

    What you need

    macOS. A shell. Nothing installed: ps and kill are built in. No network access.

    Also available

    dev-port-finder (what is on :3000), dev-cache-reclaimer (free disk safely), launchd-orphan-cleaner, or all four as the stray bundle.

    Strictly for macOS. Requires Bash access. Does not flag orphan runtimes under 24 hours old to avoid killing active dev servers.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    Requires

    macOS only
    Node.js
    Context7 MCP
    playwright
    Python

    Permissions

    Terminal / Shell
    Browser
    Network Access
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill targets 'zombie' processes that remain active after you close AI editors like Claude Desktop or Cursor. It specifically identifies MCP servers that have been adopted by the system (PPID 1) and are silently consuming RAM.

    Orphan MCP Hunter is optimized for macOS and is compatible with any AI agent capable of executing shell commands, including Claude Code, Cursor, and Windsurf. It specifically recognizes runtimes like Node.js, Bun, and Deno commonly used in the MCP ecosystem.

    No, the skill uses a sophisticated filtering system that ignores Electron renderers and active development servers. It specifically flags processes based on parent-child relationships and MCP-specific command arguments to ensure only genuine leaks are terminated.

    The skill is ready to use immediately upon import into your AI agent's environment. It leverages native macOS system binaries like `ps` and `kill`, so you don't need to install any heavy third-party dependencies.

    You receive the full skill logic designed for your AI agent, including the specialized detection rules for 'Strong' orphans and 'Warning' duplicates. You also get any maintenance updates released to address changes in how popular AI editors wrap their MCP processes.

    New in LLM Ops