convez.ai
MCP ServerAutomaçãoIntermediário
misiektoja

Kill Process MCP

misiektoja/kill-process-mcp

Controle de processos do SO via linguagem natural para Claude

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que expõe ferramentas para listar e encerrar processos do SO via consultas em linguagem natural. Permite que LLMs identifiquem e eliminem processos problemáticos de forma inteligente, com filtros por CPU, memória e outros critérios.

Instalação

$npx convez-ai misiektoja/kill-process-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
15
Forks
6
Acompanhando
2
Saúde
42%
Último commit
há 9 meses
Versão
—
Issues abertas
2
Contribuidores
3

Casos de uso

  • Identificar e encerrar processos que consomem muita CPU/memória
  • Automatizar limpeza de aplicações travadas via prompts em linguagem natural
  • Integrar gerenciamento de processos em workflows com Claude Desktop

Veredito

Ferramenta especializada e bem-executada para automação de tarefas do sistema. Útil para quem precisa de controle programático de processos, mas com escopo bem definido e limitado ao gerenciamento de SO.

README

A tradução para o português deste README ainda está na fila.

kill-process-mcp 🔫

Cross-platform MCP (Model Context Protocol) server exposing LLM-accessible tools to list and kill OS processes via natural language queries.

Perfect for shy ninjas who just want rogue processes gone: "Find and nuke the damn CPU glutton choking my system!"

Demo

kill-process-mcp-demo

Tools

The following tools are exposed to MCP clients:

  • process_list: Lists running processes sorted by CPU or memory with optional name, user, status, CPU/memory thresholds, system-process filtering, sort order and limit
  • process_kill: Terminates the selected process (with extreme prejudice!)

Requirements

  • MCP-compatible LLM client (like Claude Desktop or Cursor)
  • OS: macOS/Windows/Linux
  • Python 3.13 or higher
  • uv
  • Libraries: mcp psutil

Installation

You can install kill-process-mcp in two ways:

  1. Preferred: use uvx - no cloning or setup needed.
  2. Alternative: clone the repo and set up manually.

1. Install uv (required for both methods)

Install uv if missing:

pip install uv

# or on macOS:
brew install uv

In case of the preferred uvx method you can now configure your MCP client (skip the cloning step below).

2. Clone the repo and install (only required for alternative mode, skip for uvx)

git clone https://github.com/misiektoja/kill-process-mcp.git
cd kill-process-mcp

Install dependencies:

uv sync

3. Configure MCP Client


🟣 Claude Desktop

Register the kill-process-mcp as an MCP server in Claude Desktop.

Add the following to claude_desktop_config.json file if you want to use uvx method (recommended):

{
    "mcpServers": {
        "kill-process-mcp": {
            "command": "uvx",
            "args": ["kill-process-mcp@latest"]
        }
    }
}

In case of an alternative manual method using a cloned repo:

{
    "mcpServers": {
        "kill-process-mcp": {
            "command": "uv",
            "args": [
                "run",
                "--directory",
                "/path/to/kill-process-mcp",
                "kill_process_mcp.py"
            ]
        }
    }
}

Default claude_desktop_config.json location (if the file is missing - create it):

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Replace /path/to/kill-process-mcp with the actual path of your project folder (remember to escape backslash characters if you're on Windows, e.g.: C:\\path\\to\\kill-process-mcp)

Restart Claude Desktop and it should be able to talk to the kill-process-mcp server.

You can check if the server is loaded by going to Profile → Settings → Connectors.


🟢 Cursor

Register the kill-process-mcp as an MCP server in Cursor.

Open Cursor settings and click Tools & MCP → Add Custom MCP.

Once the mcp.json file opens, add the following if you want to use uvx method (recommended):

{
    "mcpServers": {
        "kill-process-mcp": {
            "command": "uvx",
            "args": ["kill-process-mcp@latest"]
        }
    }
}

In case of an alternative manual method using a cloned repo:

{
    "mcpServers": {
        "kill-process-mcp": {
            "command": "uv",
            "args": [
                "run",
                "--directory",
                "/path/to/kill-process-mcp",
                "kill_process_mcp.py"
            ]
        }
    }
}

Default mcp.json location:

  • macOS/Linux: ~/.cursor/mcp.json
  • Windows: %USERPROFILE%\.cursor\mcp.json

Replace /path/to/kill-process-mcp with the actual path of your project folder (remember to escape backslash characters if you're on Windows, e.g.: C:\\path\\to\\kill-process-mcp)

You should be able to talk to the kill-process-mcp server now.

You can check if the server is loaded by going to Cursor settings and clicking Tools & MCP.


Optional: Install a Persistent Shim

If you prefer faster startup or offline use while using the uvx method, you can install a local shim once:

uv tool install kill-process-mcp

Then change your LLM client config to:

{
  "mcpServers": {
    "kill-process-mcp": {
      "command": "kill-process-mcp"
    }
  }
}

Example Hit Contracts

Here are some example prompts you can use with your MCP-compatible AI assistant when interacting with this MCP server:

  • Kill the damn process slowing down my system!
  • Check my top 5 CPU parasites and flag any that look like malware
  • List the 3 greediest processes by RAM usage
  • Exterminate every process with Spotify in its name
  • List Alice's Python processes, max 10 entries
  • Which processes are over 2% CPU and 100 MB RAM
  • anything else your imagination brings ...

Upgrade

When using uvx, it automatically fetches and runs the latest published version each time your LLM client starts.

If you're using the alternative manual method with a cloned repo, update with:

cd kill-process-mcp
git pull
uv sync --reinstall

Known issues

We do not pin Python. New minor versions are usually supported on day one via wheels.

If you're using the alternative manual method with a cloned repo and you hit a build error (e.g pydantic-core or rpds-py failing with a Rust toolchain message), it usually means the ecosystem is catching up with the latest Python version. In most cases this is temporary and fixed shortly by upstream packages.

Try a clean rebuild in such case:

cd kill-process-mcp
rm -rf .venv
uv sync

If that still fails, temporarily use your previous Python minor version until compatible wheels are published (typically within a few days).

Disclaimer

This MCP server is armed and dangerous. If you snipe the wrong process, that's on you.

Proceed with caution.

Change Log

See RELEASE_NOTES.md for details.

License

Licensed under GPLv3. See LICENSE.

Ver o original no GitHub

Bom para

Relacionados