How do I install the Kill Stale MCP skill?

Run npx skillmds@latest add hamid-bhz/kill-stale-mcp in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Kill Stale MCP safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Kill Stale MCP?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Kill Stale MCP free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Kill Stale MCP?

hamid-bhz (@hamid-bhz) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Kill Stale MCP by hamid-bhz — Agent Skill

Name: Kill Stale MCP
Author: hamid-bhz

Kill Stale MCP

Kill stale/orphaned MCP server processes leaked by ended sessions — npx-launched servers (chrome-devtools-mcp, sentry-mcp, any npm exec *mcp*), their wrappers and watchdogs — while keeping the ones live sessions are using. Use when MCP processes pile up across sessions and eat memory.

hamid-bhz Updated Sep 22, 2026

File contents

/kill-stale-mcp

npx-launched MCP servers leak. The launch chain is npm exec <server>@... → server → (sometimes) a telemetry watchdog. When a session ends uncleanly, the termination signal stops at the npm exec wrapper — npx does not forward it to its children — so the whole group keeps running. Every dead session leaves one group behind (~100–250 MB each).

This skill kills the stale groups and keeps the live ones.

Staleness test: a live group's npm exec wrapper is parented to a running host process (Claude Code, an IDE extension host). When the host dies, the orphaned processes are re-parented to PID 1 (launchd on macOS, init/systemd on Linux). PPID 1 → stale. PPID = a live host → in use, keep.

Steps

List every MCP-related process with its parent PID:

ps -eo pid,ppid,lstart,command | grep -i mcp | grep -v grep

Classify each process:
- Not ours — never touch: anything owned by an IDE or app rather than launched via npx (e.g. Cursor mcp-process, GitLens/GitKraken gk mcp, Electron app helpers). Only handle processes whose command contains npm exec or a ~/.npm/_npx/ path, plus their direct children.
- Stale: an npx-launched process with PPID 1; or a watchdog whose --parent-pid=<N> is dead (check with kill -0 <N>).
- Live: the wrapper's PPID is a running session process. Keep the whole group.
Kill the stale PIDs explicitly (never pkill -f mcp — that would take down live sessions' servers and IDE-owned processes):
```
kill <stale pids...>
```
Re-run the listing from step 1. Killing a wrapper re-parents its children to PID 1, so they now show up as stale themselves — repeat step 3 until no npx-launched process with PPID 1 remains.
Report: how many groups were killed (with spawn times) and which live groups were kept.

Notes

Live servers respawn on demand the next time a session uses them — this skill removes leaked instances, it does not disable any MCP.
Root cause is npx signal handling. If one server leaks constantly, launch it directly by its bin path in the MCP config instead of via npx.

---name: kill-stale-mcpdescription: Kill stale/orphaned MCP server processes leaked by ended sessions — npx-launched servers (chrome-devtools-mcp, sentry-mcp, any npm exec *mcp*), their wrappers and watchdogs — while keeping the ones live sessions are using. Use when MCP processes pile up across sessions and eat memory.---# /kill-stale-mcpnpx-launched MCP servers leak. The launch chain is `npm exec <server>@...` → server → (sometimes) a telemetry watchdog. When a session ends uncleanly, the termination signal stops at the `npm exec` wrapper — npx does not forward it to its children — so the whole group keeps running. Every dead session leaves one group behind (~100–250 MB each).This skill kills the **stale** groups and keeps the **live** ones.**Staleness test:** a live group's `npm exec` wrapper is parented to a running host process (Claude Code, an IDE extension host). When the host dies, the orphaned processes are re-parented to PID 1 (`launchd` on macOS, `init`/`systemd` on Linux). **PPID 1 → stale. PPID = a live host → in use, keep.**## Steps1. List every MCP-related process with its parent PID: ```bash ps -eo pid,ppid,lstart,command | grep -i mcp | grep -v grep ```2. Classify each process: - **Not ours — never touch:** anything owned by an IDE or app rather than launched via npx (e.g. Cursor `mcp-process`, GitLens/GitKraken `gk mcp`, Electron app helpers). Only handle processes whose command contains `npm exec` or a `~/.npm/_npx/` path, plus their direct children. - **Stale:** an npx-launched process with `PPID 1`; or a watchdog whose `--parent-pid=<N>` is dead (check with `kill -0 <N>`). - **Live:** the wrapper's PPID is a running session process. Keep the whole group.3. Kill the stale PIDs explicitly (never `pkill -f mcp` — that would take down live sessions' servers and IDE-owned processes): ```bash kill <stale pids...> ```4. Re-run the listing from step 1. Killing a wrapper re-parents its children to PID 1, so they now show up as stale themselves — repeat step 3 until no npx-launched process with PPID 1 remains.5. Report: how many groups were killed (with spawn times) and which live groups were kept.## Notes- Live servers respawn on demand the next time a session uses them — this skill removes leaked instances, it does not disable any MCP.- Root cause is npx signal handling. If one server leaks constantly, launch it directly by its bin path in the MCP config instead of via `npx`.

Frequently asked questions