- Home
- MCP servers
- Kill Process
Kill Process
- python
11
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"misiektoja-kill-process-mcp": {
"command": "uvx",
"args": [
"kill-process-mcp@latest"
]
}
}
}You can run a cross-platform MCP server that exposes tools to list and terminate OS processes using natural language. This server lets you ask in plain language to identify resource-heavy processes and stop them, helping you reclaim performance and maintain control over your system.
How to use
You interact with the server through an MCP client. You can request lists of running processes filtered by name, user, status, CPU or memory thresholds, and sort order, then select one or more processes to terminate. Typical workflows include identifying top CPU or memory offenders, filtering for specific applications, and issuing a kill command for the chosen processes. Use natural language prompts like: “List the top 5 CPU hogs” or “Kill the Spotify process.” The server translates your prompts into the underlying operations and returns the results you need to act on.
What you can do with the exposed tools
-
process_list: Retrieve a list of running processes with filters for name, user, status, CPU/memory thresholds, system-process filtering, sort order, and a limit. Processes can be listed by CPU or memory usage to help you identify resource hogs.
-
process_kill: Terminate the selected process or processes. This action stops the chosen process(es) immediately, so use it carefully and confirm your targets before proceeding.
Available tools
process_list
Lists running processes with optional filters for name, user, status, CPU/m memory thresholds, system-process filtering, sort order, and limit.
process_kill
Terminates the selected process or processes as requested.